1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Access to user system call parameters and results * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * See asm-generic/syscall.h for descriptions of what we must do here. */ #ifndef _ASM_X86_SYSCALL_H #define _ASM_X86_SYSCALL_H #include <uapi/linux/audit.h> #include <linux/sched.h> #include <linux/err.h> #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; #if defined(CONFIG_X86_32) #define ia32_sys_call_table sys_call_table #endif #if defined(CONFIG_IA32_EMULATION) extern const sys_call_ptr_t ia32_sys_call_table[]; #endif #ifdef CONFIG_X86_X32_ABI extern const sys_call_ptr_t x32_sys_call_table[]; #endif /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons * sign-extend the low 32 bits. */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { return regs->orig_ax; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { regs->ax = regs->orig_ax; } static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { unsigned long error = regs->ax; #ifdef CONFIG_IA32_EMULATION /* * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. */ error = (long) (int) error; #endif return IS_ERR_VALUE(error) ? error : 0; } static inline long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs) { return regs->ax; } static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { regs->ax = (long) error ?: val; } #ifdef CONFIG_X86_32 static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { memcpy(args, &regs->bx, 6 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, unsigned int i, unsigned int n, const unsigned long *args) { BUG_ON(i + n > 6); memcpy(&regs->bx + i, args, n * sizeof(args[0])); } static inline int syscall_get_arch(struct task_struct *task) { return AUDIT_ARCH_I386; } #else /* CONFIG_X86_64 */ static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION if (task->thread_info.status & TS_COMPAT) { *args++ = regs->bx; *args++ = regs->cx; *args++ = regs->dx; *args++ = regs->si; *args++ = regs->di; *args = regs->bp; } else # endif { *args++ = regs->di; *args++ = regs->si; *args++ = regs->dx; *args++ = regs->r10; *args++ = regs->r8; *args = regs->r9; } } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION if (task->thread_info.status & TS_COMPAT) { regs->bx = *args++; regs->cx = *args++; regs->dx = *args++; regs->si = *args++; regs->di = *args++; regs->bp = *args; } else # endif { regs->di = *args++; regs->si = *args++; regs->dx = *args++; regs->r10 = *args++; regs->r8 = *args++; regs->r9 = *args; } } static inline int syscall_get_arch(struct task_struct *task) { /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ return (IS_ENABLED(CONFIG_IA32_EMULATION) && task->thread_info.status & TS_COMPAT) ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } void do_syscall_64(unsigned long nr, struct pt_regs *regs); void do_int80_syscall_32(struct pt_regs *regs); long do_fast_syscall_32(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ #endif /* _ASM_X86_SYSCALL_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __VDSO_MATH64_H #define __VDSO_MATH64_H static __always_inline u32 __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) { u32 ret = 0; while (dividend >= divisor) { /* The following asm() prevents the compiler from optimising this loop into a modulo operation. */ asm("" : "+rm"(dividend)); dividend -= divisor; ret++; } *remainder = dividend; return ret; } #endif /* __VDSO_MATH64_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H #include <linux/kernel.h> struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; struct __una_u64 { u64 x; } __packed; static inline u16 __get_unaligned_cpu16(const void *p) { const struct __una_u16 *ptr = (const struct __una_u16 *)p; return ptr->x; } static inline u32 __get_unaligned_cpu32(const void *p) { const struct __una_u32 *ptr = (const struct __una_u32 *)p; return ptr->x; } static inline u64 __get_unaligned_cpu64(const void *p) { const struct __una_u64 *ptr = (const struct __una_u64 *)p; return ptr->x; } static inline void __put_unaligned_cpu16(u16 val, void *p) { struct __una_u16 *ptr = (struct __una_u16 *)p; ptr->x = val; } static inline void __put_unaligned_cpu32(u32 val, void *p) { struct __una_u32 *ptr = (struct __una_u32 *)p; ptr->x = val; } static inline void __put_unaligned_cpu64(u64 val, void *p) { struct __una_u64 *ptr = (struct __una_u64 *)p; ptr->x = val; } #endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* request_key authorisation token key type * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _KEYS_REQUEST_KEY_AUTH_TYPE_H #define _KEYS_REQUEST_KEY_AUTH_TYPE_H #include <linux/key.h> /* * Authorisation record for request_key(). */ struct request_key_auth { struct rcu_head rcu; struct key *target_key; struct key *dest_keyring; const struct cred *cred; void *callout_info; size_t callout_len; pid_t pid; char op[8]; } __randomize_layout; static inline struct request_key_auth *get_request_key_auth(const struct key *key) { return key->payload.data[0]; } #endif /* _KEYS_REQUEST_KEY_AUTH_TYPE_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ /* * mballoc.c contains the multiblocks allocation routines */ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> #include <trace/events/ext4.h> /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() * - search for metadata in few groups * * TODO v4: * - normalization should take into account whether file is still open * - discard preallocations if no free space left (policy?) * - don't normalize tails * - quota * - reservation for superuser * * TODO v3: * - bitmap read-ahead (proposed by Oleg Drokin aka green) * - track min/max extents in each group for better group selection * - mb_mark_used() may allocate chunk right after splitting buddy * - tree of groups sorted by number of free blocks * - error handling */ /* * The allocation request involve request for multiple number of blocks * near to the goal(block) value specified. * * During initialization phase of the allocator we decide to use the * group preallocation or inode preallocation depending on the size of * the file. The size of the file could be the resulting file size we * would have after allocation, or the current file size, which ever * is larger. If the size is less than sbi->s_mb_stream_request we * select to use the group preallocation. The default value of * s_mb_stream_request is 16 blocks. This can also be tuned via * /sys/fs/ext4/<partition>/mb_stream_req. The value is represented in * terms of number of blocks. * * The main motivation for having small file use group preallocation is to * ensure that we have small files closer together on the disk. * * First stage the allocator looks at the inode prealloc list, * ext4_inode_info->i_prealloc_list, which contains list of prealloc * spaces for this particular inode. The inode prealloc space is * represented as: * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space * pa_len -> length for this prealloc space (in clusters) * pa_free -> free space available in this prealloc space (in clusters) * * The inode preallocation space is used looking at the _logical_ start * block. If only the logical file block falls within the range of prealloc * space we will consume the particular prealloc space. This makes sure that * we have contiguous physical blocks representing the file blocks * * The important thing to be noted in case of inode prealloc space is that * we don't modify the values associated to inode prealloc space except * pa_free. * * If we are not able to find blocks in the inode prealloc space and if we * have the group allocation flag set then we look at the locality group * prealloc space. These are per CPU prealloc list represented as * * ext4_sb_info.s_locality_groups[smp_processor_id()] * * The reason for having a per cpu locality group is to reduce the contention * between CPUs. It is possible to get scheduled at this point. * * The locality group prealloc space is used looking at whether we have * enough free space (pa_free) within the prealloc space. * * If we can't allocate blocks via inode prealloc or/and locality group * prealloc then we look at the buddy cache. The buddy cache is represented * by ext4_sb_info.s_buddy_cache (struct inode) whose file offset gets * mapped to the buddy and bitmap information regarding different * groups. The buddy information is attached to buddy cache inode so that * we can access them through the page cache. The information regarding * each group is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are stored in the * inode as: * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. So for each group we * take up 2 blocks. A page can contain blocks_per_page (PAGE_SIZE / * blocksize) blocks. So it can have information regarding groups_per_page * which is blocks_per_page/2 * * The buddy cache inode is not stored on disk. The inode is thrown * away when the filesystem is unmounted. * * We look for count number of blocks in the buddy cache. If we were able * to locate that many free blocks we return with additional information * regarding rest of the contiguous physical block available * * Before allocating blocks via buddy cache we normalize the request * blocks. This ensure we ask for more blocks that we needed. The extra * blocks that we get after allocation is added to the respective prealloc * list. In case of inode preallocation we follow a list of heuristics * based on file size. This can be found in ext4_mb_normalize_request. If * we are doing a group prealloc we try to normalize the request to * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is * dependent on the cluster size; for non-bigalloc file systems, it is * 512 blocks. This can be tuned via * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in * terms of number of blocks. If we have mounted the file system with -O * stripe=<value> option the group prealloc request is normalized to the * smallest multiple of the stripe value (sbi->s_stripe) which is * greater than the default mb_group_prealloc. * * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan * /sys/fs/ext4/<partition>/mb_order2_req * * The regular allocator uses buddy scan only if the request len is power of * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The * value of s_mb_order2_reqs can be tuned via * /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to * stripe size (sbi->s_stripe), we try to search for contiguous block in * stripe size. This should result in better allocation on RAID setups. If * not, we search in the specific group using bitmap for best extents. The * tunable min_to_scan and max_to_scan control the behaviour here. * min_to_scan indicate how long the mballoc __must__ look for a best * extent and max_to_scan indicates how long the mballoc __can__ look for a * best extent in the found extents. Searching for the blocks starts with * the group specified as the goal value in allocation context via * ac_g_ex. Each group is first checked based on the criteria whether it * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * * Both the prealloc space are getting populated as above. So for the first * request we will hit the buddy cache which will result in this prealloc * space getting filled. The prealloc space is then later used for the * subsequent request. */ /* * mballoc operates on the following data: * - on-disk bitmap * - in-core buddy (actually includes buddy and bitmap) * - preallocation descriptors (PAs) * * there are two types of preallocations: * - inode * assiged to specific inode and can be used for this inode only. * it describes part of inode's space preallocated to specific * physical blocks. any block from that preallocated can be used * independent. the descriptor just tracks number of blocks left * unused. so, before taking some block from descriptor, one must * make sure corresponded logical block isn't allocated yet. this * also means that freeing any block within descriptor's range * must discard all preallocated blocks. * - locality group * assigned to specific locality group which does not translate to * permanent set of inodes: inode can join and leave group. space * from this type of preallocation can be used for any inode. thus * it's consumed from the beginning to the end. * * relation between them can be expressed as: * in-core buddy = on-disk bitmap + preallocation descriptors * * this mean blocks mballoc considers used are: * - allocated blocks (persistent) * - preallocated blocks (non-persistent) * * consistency in mballoc world means that at any time a block is either * free or used in ALL structures. notice: "any time" should not be read * literally -- time is discrete and delimited by locks. * * to keep it simple, we don't use block numbers, instead we count number of * blocks: how many blocks marked used/free in on-disk bitmap, buddy and PA. * * all operations can be expressed as: * - init buddy: buddy = on-disk + PAs * - new PA: buddy += N; PA = N * - use inode PA: on-disk += N; PA -= N * - discard inode PA buddy -= on-disk - PA; PA = 0 * - use locality group PA on-disk += N; PA -= N * - discard locality group PA buddy -= PA; PA = 0 * note: 'buddy -= on-disk - PA' is used to show that on-disk bitmap * is used in real operation because we can't know actual used * bits from PA, only from on-disk bitmap * * if we follow this strict logic, then all operations above should be atomic. * given some of them can block, we'd have to use something like semaphores * killing performance on high-end SMP hardware. let's try to relax it using * the following knowledge: * 1) if buddy is referenced, it's already initialized * 2) while block is used in buddy and the buddy is referenced, * nobody can re-allocate that block * 3) we work on bitmaps and '+' actually means 'set bits'. if on-disk has * bit set and PA claims same block, it's OK. IOW, one can set bit in * on-disk bitmap if buddy has same bit set or/and PA covers corresponded * block * * so, now we're building a concurrency table: * - init buddy vs. * - new PA * blocks for PA are allocated in the buddy, buddy must be referenced * until PA is linked to allocation group to avoid concurrent buddy init * - use inode PA * we need to make sure that either on-disk bitmap or PA has uptodate data * given (3) we care that PA-=N operation doesn't interfere with init * - discard inode PA * the simplest way would be to have buddy initialized by the discard * - use locality group PA * again PA-=N must be serialized with init * - discard locality group PA * the simplest way would be to have buddy initialized by the discard * - new PA vs. * - use inode PA * i_data_sem serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * some mutex should serialize them * - discard locality group PA * discard process must wait until PA isn't used by another process * - use inode PA * - use inode PA * i_data_sem or another mutex should serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * nothing wrong here -- they're different PAs covering different blocks * - discard locality group PA * discard process must wait until PA isn't used by another process * * now we're ready to make few consequences: * - PA is referenced and while it is no discard is possible * - PA is referenced until block isn't marked in on-disk bitmap * - PA changes only after on-disk bitmap * - discard must not compete with init. either init is done before * any discard or they're serialized somehow * - buddy init as sum of on-disk bitmap and PAs is done atomically * * a special case when we've used PA to emptiness. no need to modify buddy * in this case, but we should care about concurrent init * */ /* * Logic in few words: * * - allocation: * load group * find blocks * mark bits in on-disk bitmap * release group * * - use preallocation: * find proper PA (per-inode or group) * load group * mark bits in on-disk bitmap * release group * release PA * * - free: * load group * mark bits in on-disk bitmap * release group * * - discard preallocations in group: * mark PAs deleted * move them onto local list * load on-disk bitmap * load group * remove PA from object (inode or locality group) * mark free blocks in-core * * - discard inode's preallocations: */ /* * Locking rules * * Locks: * - bitlock on a group (group) * - object (inode/locality) (object) * - per-pa lock (pa) * * Paths: * - new pa * object * group * * - find and use pa: * pa * * - release consumed pa: * pa * group * object * * - generate in-core bitmap: * group * pa * * - discard all for given object (inode, locality group): * object * pa * group * * - discard all for given group: * group * pa * group * object * */ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_data_cachep; /* We create slab caches for groupinfo data structures based on the * superblock block size. There will be one per mounted filesystem for * each unique s_blocksize_bits */ #define NR_GRPINFO_CACHES 8 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k", "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k", "ext4_groupinfo_64k", "ext4_groupinfo_128k" }; static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); /* * The algorithm using this percpu seq counter goes below: * 1. We sample the percpu discard_pa_seq counter before trying for block * allocation in ext4_mb_new_blocks(). * 2. We increment this percpu discard_pa_seq counter when we either allocate * or free these blocks i.e. while marking those blocks as used/free in * mb_mark_used()/mb_free_blocks(). * 3. We also increment this percpu seq counter when we successfully identify * that the bb_prealloc_list is not empty and hence proceed for discarding * of those PAs inside ext4_mb_discard_group_preallocations(). * * Now to make sure that the regular fast path of block allocation is not * affected, as a small optimization we only sample the percpu seq counter * on that cpu. Only when the block allocation fails and when freed blocks * found were 0, that is when we sample percpu seq counter for all cpus using * below function ext4_get_discard_pa_seq_sum(). This happens after making * sure that all the PAs on grp->bb_prealloc_list got freed or if it's empty. */ static DEFINE_PER_CPU(u64, discard_pa_seq); static inline u64 ext4_get_discard_pa_seq_sum(void) { int __cpu; u64 __seq = 0; for_each_possible_cpu(__cpu) __seq += per_cpu(discard_pa_seq, __cpu); return __seq; } static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline int mb_test_bit(int bit, void *addr) { /* * ext4_test_bit on architecture like powerpc * needs unsigned long aligned address */ addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_bit(bit, addr); } static inline void mb_set_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit(bit, addr); } static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } static inline int mb_test_and_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_and_clear_bit(bit, addr); } static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_zero_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static inline int mb_find_next_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) { char *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(max == NULL); if (order > e4b->bd_blkbits + 1) { *max = 0; return NULL; } /* at order 0 we see each particular block */ if (order == 0) { *max = 1 << (e4b->bd_blkbits + 3); return e4b->bd_bitmap; } bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order]; *max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order]; return bb; } #ifdef DOUBLE_CHECK static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int i; struct super_block *sb = e4b->bd_sb; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(EXT4_SB(sb), first + i); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing block already freed " "(bit %u)", first + i); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { int i; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) { unsigned char *b1, *b2; int i; b1 = (unsigned char *) e4b->bd_info->bb_bitmap; b2 = (unsigned char *) bitmap; for (i = 0; i < e4b->bd_sb->s_blocksize; i++) { if (b1[i] != b2[i]) { ext4_msg(e4b->bd_sb, KERN_ERR, "corruption in group %u " "at byte %u(%u): %x in copy != %x " "on disk/prealloc", e4b->bd_group, i, i * 8, b1[i], b2[i]); BUG(); } } } } static void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { struct buffer_head *bh; grp->bb_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS); if (!grp->bb_bitmap) return; bh = ext4_read_block_bitmap(sb, group); if (IS_ERR_OR_NULL(bh)) { kfree(grp->bb_bitmap); grp->bb_bitmap = NULL; return; } memcpy(grp->bb_bitmap, bh->b_data, sb->s_blocksize); put_bh(bh); } static void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { kfree(grp->bb_bitmap); } #else static inline void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { return; } static inline void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { return; } static inline void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { return; } #endif #ifdef AGGRESSIVE_CHECK #define MB_CHECK_ASSERT(assert) \ do { \ if (!(assert)) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: \"%s\"\n", \ function, file, line, # assert); \ BUG(); \ } \ } while (0) static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { struct super_block *sb = e4b->bd_sb; int order = e4b->bd_blkbits + 1; int max; int max2; int i; int j; int k; int count; struct ext4_group_info *grp; int fragments = 0; int fstart; struct list_head *cur; void *buddy; void *buddy2; if (e4b->bd_info->bb_check_counter++ % 10) return 0; while (order > 1) { buddy = mb_find_buddy(e4b, order, &max); MB_CHECK_ASSERT(buddy); buddy2 = mb_find_buddy(e4b, order - 1, &max2); MB_CHECK_ASSERT(buddy2); MB_CHECK_ASSERT(buddy != buddy2); MB_CHECK_ASSERT(max * 2 == max2); count = 0; for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { /* only single bit in buddy2 may be 1 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); } else if (!mb_test_bit((i << 1) + 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit(i << 1, buddy2)); } continue; } /* both bits in buddy2 must be 1 */ MB_CHECK_ASSERT(mb_test_bit(i << 1, buddy2)); MB_CHECK_ASSERT(mb_test_bit((i << 1) + 1, buddy2)); for (j = 0; j < (1 << order); j++) { k = (i * (1 << order)) + j; MB_CHECK_ASSERT( !mb_test_bit(k, e4b->bd_bitmap)); } count++; } MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count); order--; } fstart = -1; buddy = mb_find_buddy(e4b, 0, &max); for (i = 0; i < max; i++) { if (!mb_test_bit(i, buddy)) { MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free); if (fstart == -1) { fragments++; fstart = i; } continue; } fstart = -1; /* check used bits only */ for (j = 0; j < e4b->bd_blkbits + 1; j++) { buddy2 = mb_find_buddy(e4b, j, &max2); k = i >> j; MB_CHECK_ASSERT(k < max2); MB_CHECK_ASSERT(mb_test_bit(k, buddy2)); } } MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info)); MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k); MB_CHECK_ASSERT(groupnr == e4b->bd_group); for (i = 0; i < pa->pa_len; i++) MB_CHECK_ASSERT(mb_test_bit(k + i, buddy)); } return 0; } #undef MB_CHECK_ASSERT #define mb_check_buddy(e4b) __mb_check_buddy(e4b, \ __FILE__, __func__, __LINE__) #else #define mb_check_buddy(e4b) #endif /* * Divide blocks started from @first with length @len into * smaller chunks with power of 2 blocks. * Clear the bits in bitmap which the blocks of the chunk(s) covered, * then increase bb_counters[] for corresponded chunk size. */ static void ext4_mb_mark_free_simple(struct super_block *sb, void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t min; ext4_grpblk_t max; ext4_grpblk_t chunk; unsigned int border; BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb)); border = 2 << sb->s_blocksize_bits; while (len > 0) { /* find how many blocks can be covered since this position */ max = ffs(first | border) - 1; /* find how many blocks of power 2 we need to mark */ min = fls(len) - 1; if (max < min) min = max; chunk = 1 << min; /* mark multiblock chunks only */ grp->bb_counters[min]++; if (min > 0) mb_clear_bit(first >> min, buddy + sbi->s_mb_offsets[min]); len -= chunk; first += chunk; } } /* * Cache the order of the largest free extent we have available in this block * group. */ static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { int i; int bits; grp->bb_largest_free_order = -1; /* uninit */ bits = sb->s_blocksize_bits + 1; for (i = bits; i >= 0; i--) { if (grp->bb_counters[i] > 0) { grp->bb_largest_free_order = i; break; } } } static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_grpblk_t first; ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); /* initialize buddy from bitmap which is aggregation * of on-disk bitmap and preallocations */ i = mb_find_next_zero_bit(bitmap, max, 0); grp->bb_first_free = i; while (i < max) { fragments++; first = i; i = mb_find_next_bit(bitmap, max, i); len = i - first; free += len; if (len > 1) ext4_mb_mark_free_simple(sb, buddy, first, len, grp); else grp->bb_counters[0]++; if (i < max) i = mb_find_next_zero_bit(bitmap, max, i); } grp->bb_fragments = fragments; if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, "block bitmap and bg descriptor " "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; spin_lock(&sbi->s_bal_lock); sbi->s_mb_buddies_generated++; sbi->s_mb_generation_time += period; spin_unlock(&sbi->s_bal_lock); } static void mb_regenerate_buddy(struct ext4_buddy *e4b) { int count; int order = 1; void *buddy; while ((buddy = mb_find_buddy(e4b, order++, &count))) { ext4_set_bits(buddy, 0, count); } e4b->bd_info->bb_fragments = 0; memset(e4b->bd_info->bb_counters, 0, sizeof(*e4b->bd_info->bb_counters) * (e4b->bd_sb->s_blocksize_bits + 2)); ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, e4b->bd_bitmap, e4b->bd_group); } /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are * stored in the inode as * * { page } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. * So for each group we take up 2 blocks. A page can * contain blocks_per_page (PAGE_SIZE / blocksize) blocks. * So it can have information regarding groups_per_page which * is blocks_per_page/2 * * Locking note: This routine takes the block group lock of all groups * for this page; do not hold this lock when calling this routine! */ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) { ext4_group_t ngroups; int blocksize; int blocks_per_page; int groups_per_page; int err = 0; int i; ext4_group_t first_group, group; int first_block; struct super_block *sb; struct buffer_head *bhs; struct buffer_head **bh = NULL; struct inode *inode; char *data; char *bitmap; struct ext4_group_info *grinfo; inode = page->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = i_blocksize(inode); blocks_per_page = PAGE_SIZE / blocksize; mb_debug(sb, "init page %lu\n", page->index); groups_per_page = blocks_per_page >> 1; if (groups_per_page == 0) groups_per_page = 1; /* allocate buffer_heads to read bitmaps */ if (groups_per_page > 1) { i = sizeof(struct buffer_head *) * groups_per_page; bh = kzalloc(i, gfp); if (bh == NULL) { err = -ENOMEM; goto out; } } else bh = &bhs; first_group = page->index * blocks_per_page / 2; /* read all groups the page covers into the cache */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { if (group >= ngroups) break; grinfo = ext4_get_group_info(sb, group); /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so * we must skip all initialized uptodate buddies on the page, * which may be currently in use by an allocating task. */ if (PageUptodate(page) && !EXT4_MB_GRP_NEED_INIT(grinfo)) { bh[i] = NULL; continue; } bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; goto out; } mb_debug(sb, "read bitmap for group %u\n", group); } /* wait for I/O completion */ for (i = 0, group = first_group; i < groups_per_page; i++, group++) { int err2; if (!bh[i]) continue; err2 = ext4_wait_block_bitmap(sb, group, bh[i]); if (!err) err = err2; } first_block = page->index * blocks_per_page; for (i = 0; i < blocks_per_page; i++) { group = (first_block + i) >> 1; if (group >= ngroups) break; if (!bh[group - first_group]) /* skip initialized uptodate buddy */ continue; if (!buffer_verified(bh[group - first_group])) /* Skip faulty bitmaps */ continue; err = 0; /* * data carry information regarding this * particular group in the format specified * above * */ data = page_address(page) + (i * blocksize); bitmap = bh[group - first_group]->b_data; /* * We place the buddy block and bitmap block * close together */ if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo = ext4_get_group_info(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * (sb->s_blocksize_bits+2)); /* * incore got set to the group block bitmap below */ ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); ext4_mb_generate_buddy(sb, data, incore, group); ext4_unlock_group(sb, group); incore = NULL; } else { /* this is block of bitmap */ BUG_ON(incore != NULL); mb_debug(sb, "put bitmap for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_bitmap_load(sb, group); /* see comments in ext4_mb_put_pa() */ ext4_lock_group(sb, group); memcpy(data, bitmap, blocksize); /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); ext4_mb_generate_from_freelist(sb, data, group); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be * generated using this */ incore = data; } } SetPageUptodate(page); out: if (bh) { for (i = 0; i < groups_per_page; i++) brelse(bh[i]); if (bh != &bhs) kfree(bh); } return err; } /* * Lock the buddy and bitmap pages. This make sure other parallel init_group * on the same buddy page doesn't happen whild holding the buddy page lock. * Return locked buddy and bitmap pages on e4b struct. If buddy and bitmap * are on the same page e4b->bd_buddy_page is NULL and return value is 0. */ static int ext4_mb_get_buddy_page_lock(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { struct inode *inode = EXT4_SB(sb)->s_buddy_cache; int block, pnum, poff; int blocks_per_page; struct page *page; e4b->bd_buddy_page = NULL; e4b->bd_bitmap_page = NULL; blocks_per_page = PAGE_SIZE / sb->s_blocksize; /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, gfp); if (!page) return -ENOMEM; BUG_ON(page->mapping != inode->i_mapping); e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); if (blocks_per_page >= 2) { /* buddy and bitmap are on the same page */ return 0; } block++; pnum = block / blocks_per_page; page = find_or_create_page(inode->i_mapping, pnum, gfp); if (!page) return -ENOMEM; BUG_ON(page->mapping != inode->i_mapping); e4b->bd_buddy_page = page; return 0; } static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) { unlock_page(e4b->bd_bitmap_page); put_page(e4b->bd_bitmap_page); } if (e4b->bd_buddy_page) { unlock_page(e4b->bd_buddy_page); put_page(e4b->bd_buddy_page); } } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) { struct ext4_group_info *this_grp; struct ext4_buddy e4b; struct page *page; int ret = 0; might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. * The call to ext4_mb_get_buddy_page_lock will mark the * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { /* * somebody initialized the group * return without doing anything */ goto err; } page = e4b.bd_bitmap_page; ret = ext4_mb_init_cache(page, NULL, gfp); if (ret) goto err; if (!PageUptodate(page)) { ret = -EIO; goto err; } if (e4b.bd_buddy_page == NULL) { /* * If both the bitmap and buddy are in * the same page we don't need to force * init the buddy */ ret = 0; goto err; } /* init buddy cache */ page = e4b.bd_buddy_page; ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp); if (ret) goto err; if (!PageUptodate(page)) { ret = -EIO; goto err; } err: ext4_mb_put_buddy_page_lock(&e4b); return ret; } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { int blocks_per_page; int block; int pnum; int poff; struct page *page; int ret; struct ext4_group_info *grp; struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; might_sleep(); mb_debug(sb, "load group %u\n", group); blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; e4b->bd_sb = sb; e4b->bd_group = group; e4b->bd_buddy_page = NULL; e4b->bd_bitmap_page = NULL; if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { /* * we need full data about the group * to make a good selection */ ret = ext4_mb_init_group(sb, group, gfp); if (ret) return ret; } /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = block / blocks_per_page; poff = block % blocks_per_page; /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* * drop the page reference and try * to get the page with lock. If we * are not uptodate that implies * somebody just created the page but * is yet to initialize the same. So * wait for it to initialize. */ put_page(page); page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); if (!PageUptodate(page)) { ret = ext4_mb_init_cache(page, NULL, gfp); if (ret) { unlock_page(page); goto err; } mb_cmp_bitmaps(e4b, page_address(page) + (poff * sb->s_blocksize)); } unlock_page(page); } } if (page == NULL) { ret = -ENOMEM; goto err; } if (!PageUptodate(page)) { ret = -EIO; goto err; } /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) put_page(page); page = find_or_create_page(inode->i_mapping, pnum, gfp); if (page) { BUG_ON(page->mapping != inode->i_mapping); if (!PageUptodate(page)) { ret = ext4_mb_init_cache(page, e4b->bd_bitmap, gfp); if (ret) { unlock_page(page); goto err; } } unlock_page(page); } } if (page == NULL) { ret = -ENOMEM; goto err; } if (!PageUptodate(page)) { ret = -EIO; goto err; } /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); return 0; err: if (page) put_page(page); if (e4b->bd_bitmap_page) put_page(e4b->bd_bitmap_page); if (e4b->bd_buddy_page) put_page(e4b->bd_buddy_page); e4b->bd_buddy = NULL; e4b->bd_bitmap = NULL; return ret; } static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) { return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS); } static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_page) put_page(e4b->bd_bitmap_page); if (e4b->bd_buddy_page) put_page(e4b->bd_buddy_page); } static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { int order = 1; int bb_incr = 1 << (e4b->bd_blkbits - 1); void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(block >= (1 << (e4b->bd_blkbits + 3))); bb = e4b->bd_buddy; while (order <= e4b->bd_blkbits + 1) { block = block >> 1; if (!mb_test_bit(block, bb)) { /* this block is part of buddy of order 'order' */ return order; } bb += bb_incr; bb_incr >>= 1; order++; } return 0; } static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); *addr = 0; cur += 32; continue; } mb_clear_bit(cur, bm); cur++; } } /* clear bits in given range * will return first found zero bit if any, -1 otherwise */ static int mb_test_and_clear_bits(void *bm, int cur, int len) { __u32 *addr; int zero_bit = -1; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); if (*addr != (__u32)(-1) && zero_bit == -1) zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); *addr = 0; cur += 32; continue; } if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) zero_bit = cur; cur++; } return zero_bit; } void ext4_set_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: set whole word at once */ addr = bm + (cur >> 3); *addr = 0xffffffff; cur += 32; continue; } mb_set_bit(cur, bm); cur++; } } static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) { if (mb_test_bit(*bit + side, bitmap)) { mb_clear_bit(*bit, bitmap); (*bit) -= side; return 1; } else { (*bit) += side; mb_set_bit(*bit, bitmap); return -1; } } static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) { int max; int order = 1; void *buddy = mb_find_buddy(e4b, order, &max); while (buddy) { void *buddy2; /* Bits in range [first; last] are known to be set since * corresponding blocks were allocated. Bits in range * (first; last) will stay set because they form buddies on * upper layer. We just deal with borders if they don't * align with upper layer and then go up. * Releasing entire group is all about clearing * single bit of highest order buddy. */ /* Example: * --------------------------------- * | 1 | 1 | 1 | 1 | * --------------------------------- * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | * --------------------------------- * 0 1 2 3 4 5 6 7 * \_____________________/ * * Neither [1] nor [6] is aligned to above layer. * Left neighbour [0] is free, so mark it busy, * decrease bb_counters and extend range to * [0; 6] * Right neighbour [7] is busy. It can't be coaleasced with [6], so * mark [6] free, increase bb_counters and shrink range to * [0; 5]. * Then shift range to [0; 2], go up and do the same. */ if (first & 1) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); if (!(last & 1)) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); if (first > last) break; order++; if (first == last || !(buddy2 = mb_find_buddy(e4b, order, &max))) { mb_clear_bits(buddy, first, last - first + 1); e4b->bd_info->bb_counters[order - 1] += last - first + 1; break; } first >>= 1; last >>= 1; buddy = buddy2; } } static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int left_is_free = 0; int right_is_free = 0; int block; int last = first + count - 1; struct super_block *sb = e4b->bd_sb; if (WARN_ON(count == 0)) return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return; mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free += count; if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ if (first != 0) left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); if (unlikely(block != -1)) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing already freed block (bit %u); block bitmap corrupt.", block); ext4_mark_group_bitmap_corrupted( sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_regenerate_buddy(e4b); goto done; } /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; else if (!left_is_free && !right_is_free) e4b->bd_info->bb_fragments++; /* buddy[0] == bd_bitmap is a special case, so handle * it right away and let mb_buddy_mark_free stay free of * zero order checks. * Check if neighbours are to be coaleasced, * adjust bitmap bb_counters and borders appropriately. */ if (first & 1) { first += !left_is_free; e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; } if (!(last & 1)) { last -= !right_is_free; e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; } if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); done: mb_set_largest_free_order(sb, e4b->bd_info); mb_check_buddy(e4b); } static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int next = block; int max, order; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; return 0; } /* find actual order */ order = mb_find_order_for_block(e4b, block); block = block >> order; ex->fe_len = 1 << order; ex->fe_start = block << order; ex->fe_group = e4b->bd_group; /* calc difference from given start */ next = next - ex->fe_start; ex->fe_len -= next; ex->fe_start += next; while (needed > ex->fe_len && mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; next = (block + 1) * (1 << order); if (mb_test_bit(next, e4b->bd_bitmap)) break; order = mb_find_order_for_block(e4b, next); block = next >> order; ex->fe_len += 1 << order; } if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0, "corruption or bug in mb_find_extent " "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", block, order, needed, ex->fe_group, ex->fe_start, ex->fe_len, ex->fe_logical); ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; } return ex->fe_len; } static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) { int ord; int mlen = 0; int max = 0; int cur; int start = ex->fe_start; int len = ex->fe_len; unsigned ret = 0; int len0 = len; void *buddy; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free -= len; if (e4b->bd_info->bb_first_free == start) e4b->bd_info->bb_first_free += len; /* let's maintain fragments counter */ if (start != 0) mlen = !mb_test_bit(start - 1, e4b->bd_bitmap); if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0]) max = !mb_test_bit(start + len, e4b->bd_bitmap); if (mlen && max) e4b->bd_info->bb_fragments++; else if (!mlen && !max) e4b->bd_info->bb_fragments--; /* let's maintain buddy itself */ while (len) { ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; buddy = mb_find_buddy(e4b, ord, &max); BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; start += mlen; len -= mlen; BUG_ON(len < 0); continue; } /* store for history */ if (ret == 0) ret = len | (ord << 16); /* we have to split large buddy */ BUG_ON(ord <= 0); buddy = mb_find_buddy(e4b, ord, &max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; ord--; cur = (start >> ord) & ~1U; buddy = mb_find_buddy(e4b, ord, &max); mb_clear_bit(cur, buddy); mb_clear_bit(cur + 1, buddy); e4b->bd_info->bb_counters[ord]++; e4b->bd_info->bb_counters[ord]++; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; } /* * Must be called under group lock! */ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int ret; BUG_ON(ac->ac_b_ex.fe_group != e4b->bd_group); BUG_ON(ac->ac_status == AC_STATUS_FOUND); ac->ac_b_ex.fe_len = min(ac->ac_b_ex.fe_len, ac->ac_g_ex.fe_len); ac->ac_b_ex.fe_logical = ac->ac_g_ex.fe_logical; ret = mb_mark_used(e4b, &ac->ac_b_ex); /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; ac->ac_status = AC_STATUS_FOUND; ac->ac_tail = ret & 0xffff; ac->ac_buddy = ret >> 16; /* * take the page reference. We want the page to be pinned * so that we don't get a ext4_mb_init_cache_call for this * group until we update the bitmap. That would mean we * double allocate blocks. The reference is dropped * in ext4_mb_release_context */ ac->ac_bitmap_page = e4b->bd_bitmap_page; get_page(ac->ac_bitmap_page); ac->ac_buddy_page = e4b->bd_buddy_page; get_page(ac->ac_buddy_page); /* store last allocated for subsequent stream allocation */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { spin_lock(&sbi->s_md_lock); sbi->s_mb_last_group = ac->ac_f_ex.fe_group; sbi->s_mb_last_start = ac->ac_f_ex.fe_start; spin_unlock(&sbi->s_md_lock); } /* * As we've just preallocated more space than * user requested originally, we store allocated * space in a special descriptor. */ if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) ext4_mb_new_preallocation(ac); } static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; struct ext4_free_extent ex; int max; if (ac->ac_status == AC_STATUS_FOUND) return; /* * We don't want to scan for a whole year */ if (ac->ac_found > sbi->s_mb_max_to_scan && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { ac->ac_status = AC_STATUS_BREAK; return; } /* * Haven't found good chunk so far, let's continue */ if (bex->fe_len < gex->fe_len) return; if ((finish_group || ac->ac_found > sbi->s_mb_min_to_scan) && bex->fe_group == e4b->bd_group) { /* recheck chunk's availability - we don't know * when it was found (within this lock-unlock * period or not) */ max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex); if (max >= gex->fe_len) { ext4_mb_use_best_found(ac, e4b); return; } } } /* * The routine checks whether found extent is good enough. If it is, * then the extent gets marked used and flag is set to the context * to stop scanning. Otherwise, the extent is compared with the * previous found extent and if new one is better, then it's stored * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, struct ext4_free_extent *ex, struct ext4_buddy *e4b) { struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; BUG_ON(ex->fe_len <= 0); BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ac->ac_status != AC_STATUS_CONTINUE); ac->ac_found++; /* * The special case - take what you catch first */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_FIRST)) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * Let's check whether the chuck is good enough */ if (ex->fe_len == gex->fe_len) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * If this is first found extent, just store it in the context */ if (bex->fe_len == 0) { *bex = *ex; return; } /* * If new found extent is better, store it in the context */ if (bex->fe_len < gex->fe_len) { /* if the request isn't satisfied, any found extent * larger than previous best one is better */ if (ex->fe_len > bex->fe_len) *bex = *ex; } else if (ex->fe_len > gex->fe_len) { /* if the request is satisfied, then we try to find * an extent that still satisfy the request, but is * smaller than previous one */ if (ex->fe_len < bex->fe_len) *bex = *ex; } ext4_mb_check_limits(ac, e4b, 0); } static noinline_for_stack int ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; ext4_group_t group = ex.fe_group; int max; int err; BUG_ON(ex.fe_len <= 0); err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; ext4_lock_group(ac->ac_sb, group); max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } static noinline_for_stack int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL)) return 0; if (grp->bb_free == 0) return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { ext4_mb_unload_buddy(e4b); return 0; } ext4_lock_group(ac->ac_sb, group); max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) { ext4_fsblk_t start; start = ext4_group_first_block_no(ac->ac_sb, e4b->bd_group) + ex.fe_start; /* use do_div to get remainder (would be 64-bit modulo) */ if (do_div(start, sbi->s_stripe) == 0) { ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } } else if (max >= ac->ac_g_ex.fe_len) { BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } else if (max > 0 && (ac->ac_flags & EXT4_MB_HINT_MERGE)) { /* Sometimes, caller may want to merge even small * number of blocks to an existing extent */ BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } /* * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ static noinline_for_stack void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_group_info *grp = e4b->bd_info; void *buddy; int i; int k; int max; BUG_ON(ac->ac_2order <= 0); for (i = ac->ac_2order; i <= sb->s_blocksize_bits + 1; i++) { if (grp->bb_counters[i] == 0) continue; buddy = mb_find_buddy(e4b, i, &max); BUG_ON(buddy == NULL); k = mb_find_next_zero_bit(buddy, max, 0); if (k >= max) { ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, "%d free clusters of order %d. But found 0", grp->bb_counters[i], i); ext4_mark_group_bitmap_corrupted(ac->ac_sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } ac->ac_found++; ac->ac_b_ex.fe_len = 1 << i; ac->ac_b_ex.fe_start = k << i; ac->ac_b_ex.fe_group = e4b->bd_group; ext4_mb_use_best_found(ac, e4b); BUG_ON(ac->ac_f_ex.fe_len != ac->ac_g_ex.fe_len); if (EXT4_SB(sb)->s_mb_stats) atomic_inc(&EXT4_SB(sb)->s_bal_2orders); break; } } /* * The routine scans the group and measures all found extents. * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ static noinline_for_stack void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; int i; int free; free = e4b->bd_info->bb_free; if (WARN_ON(free <= 0)) return; i = e4b->bd_info->bb_first_free; while (free && ac->ac_status == AC_STATUS_CONTINUE) { i = mb_find_next_zero_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) { /* * IF we have corrupt bitmap, we won't find any * free blocks even though group info says we * have free blocks */ ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But bitmap says 0", free); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); if (WARN_ON(ex.fe_len <= 0)) break; if (free < ex.fe_len) { ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit * without claiming the space. */ break; } ex.fe_logical = 0xDEADC0DE; /* debug value */ ext4_mb_measure_extent(ac, &ex, e4b); i += ex.fe_len; free -= ex.fe_len; } ext4_mb_check_limits(ac, e4b, 1); } /* * This is a special case for storages like raid5 * we try to find stripe-aligned chunks for stripe-size-multiple requests */ static noinline_for_stack void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; ext4_fsblk_t first_group_block; ext4_fsblk_t a; ext4_grpblk_t i; int max; BUG_ON(sbi->s_stripe == 0); /* find first stripe-aligned block in group */ first_group_block = ext4_group_first_block_no(sb, e4b->bd_group); a = first_group_block + sbi->s_stripe - 1; do_div(a, sbi->s_stripe); i = (a * sbi->s_stripe) - first_group_block; while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { max = mb_find_extent(e4b, i, sbi->s_stripe, &ex); if (max >= sbi->s_stripe) { ac->ac_found++; ex.fe_logical = 0xDEADF00D; /* debug value */ ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); break; } } i += sbi->s_stripe; } } /* * This is also called BEFORE we load the buddy bitmap. * Returns either 1 or 0 indicating that the group is either suitable * for the allocation or not. */ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, int cr) { ext4_grpblk_t free, fragments; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < 0 || cr >= 4); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; if (free == 0) return false; fragments = grp->bb_fragments; if (fragments == 0) return false; switch (cr) { case 0: BUG_ON(ac->ac_2order == 0); /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) && ((group % flex_size) == 0)) return false; if (free < ac->ac_g_ex.fe_len) return false; if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) return true; if (grp->bb_largest_free_order < ac->ac_2order) return false; return true; case 1: if ((free / fragments) >= ac->ac_g_ex.fe_len) return true; break; case 2: if (free >= ac->ac_g_ex.fe_len) return true; break; case 3: return true; default: BUG(); } return false; } /* * This could return negative error code if something goes wrong * during ext4_mb_init_group(). This should not be called with * ext4_lock_group() held. */ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_group_t group, int cr) { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; if (should_lock) ext4_lock_group(sb, group); free = grp->bb_free; if (free == 0) goto out; if (cr <= 2 && free < ac->ac_g_ex.fe_len) goto out; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) goto out; if (should_lock) ext4_unlock_group(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; /* cr=0/1 is a very optimistic search to find large * good chunks almost for free. If buddy data is not * ready, then this optimization makes no sense. But * we never skip the first block group in a flex_bg, * since this gets used for metadata block allocation, * and we want to make sure we locate metadata blocks * in the first block group in the flex_bg if possible. */ if (cr < 2 && (!sbi->s_log_groups_per_flex || ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) return 0; ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } if (should_lock) ext4_lock_group(sb, group); ret = ext4_mb_good_group(ac, group, cr); out: if (should_lock) ext4_unlock_group(sb, group); return ret; } /* * Start prefetching @nr block bitmaps starting at @group. * Return the next group which needs to be prefetched. */ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct buffer_head *bh; struct blk_plug plug; blk_start_plug(&plug); while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); /* * Prefetch block groups with free blocks; but don't * bother if it is marked uninitialized on disk, since * it won't require I/O to read. Also only try to * prefetch once, so we avoid getblk() call, which can * be expensive. */ if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { bh = ext4_read_block_bitmap_nowait(sb, group, true); if (bh && !IS_ERR(bh)) { if (!buffer_uptodate(bh) && cnt) (*cnt)++; brelse(bh); } } if (++group >= ngroups) group = 0; } blk_finish_plug(&plug); return group; } /* * Prefetching reads the block bitmap into the buffer cache; but we * need to make sure that the buddy bitmap in the page cache has been * initialized. Note that ext4_mb_init_group() will block if the I/O * is not yet completed, or indeed if it was not initiated by * ext4_mb_prefetch did not start the I/O. * * TODO: We should actually kick off the buddy bitmap setup in a work * queue when the buffer I/O is completed, so that we don't block * waiting for the block allocation bitmap read to finish when * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). */ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr) { while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); if (!group) group = ext4_get_groups_count(sb); group--; grp = ext4_get_group_info(sb, group); if (EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { if (ext4_mb_init_group(sb, group, GFP_NOFS)) break; } } } static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; int cr = -1; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); ngroups = ext4_get_groups_count(sb); /* non-extent files are limited to low blocks/groups */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) ngroups = sbi->s_blockfile_groups; BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ err = ext4_mb_find_by_goal(ac, &e4b); if (err || ac->ac_status == AC_STATUS_FOUND) goto out; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) goto out; /* * ac->ac_2order is set only if the fe_len is a power of 2 * if ac->ac_2order is set we also set criteria to 0 so that we * try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); ac->ac_2order = 0; /* * We search using buddy data only if the order of the request * is greater than equal to the sbi_s_mb_order2_reqs * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req * We also support searching for power-of-two requests only for * requests upto maximum buddy size we have constructed. */ if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) { /* * This should tell if fe_len is exactly power of 2 */ if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0) ac->ac_2order = array_index_nospec(i - 1, sb->s_blocksize_bits + 2); } /* if stream allocation is enabled, use global goal */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { /* TBD: may be hot point */ spin_lock(&sbi->s_md_lock); ac->ac_g_ex.fe_group = sbi->s_mb_last_group; ac->ac_g_ex.fe_start = sbi->s_mb_last_start; spin_unlock(&sbi->s_md_lock); } /* Let's just scan groups to find more-less suitable blocks */ cr = ac->ac_2order ? 0 : 1; /* * cr == 0 try to get exact allocation, * cr == 3 try to get anything */ repeat: for (; cr < 4 && ac->ac_status == AC_STATUS_CONTINUE; cr++) { ac->ac_criteria = cr; /* * searching for the right group start * from the goal value specified */ group = ac->ac_g_ex.fe_group; prefetch_grp = group; for (i = 0; i < ngroups; group++, i++) { int ret = 0; cond_resched(); /* * Artificially restricted ngroups for non-extent * files makes group > ngroups possible on first loop. */ if (group >= ngroups) group = 0; /* * Batch reads of the block allocation bitmaps * to get multiple READs in flight; limit * prefetching at cr=0/1, otherwise mballoc can * spend a lot of time loading imperfect groups */ if ((prefetch_grp == group) && (cr > 1 || prefetch_ios < sbi->s_mb_prefetch_limit)) { unsigned int curr_ios = prefetch_ios; nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(sb)) { nr = 1 << sbi->s_log_groups_per_flex; nr -= group & (nr - 1); nr = min(nr, sbi->s_mb_prefetch); } prefetch_grp = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); if (prefetch_ios == curr_ios) nr = 0; } /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!first_err) first_err = ret; continue; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) goto out; ext4_lock_group(sb, group); /* * We need to check again after locking the * block group */ ret = ext4_mb_good_group(ac, group, cr); if (ret == 0) { ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); continue; } ac->ac_groups_scanned++; if (cr == 0) ext4_mb_simple_scan_group(ac, &e4b); else if (cr == 1 && sbi->s_stripe && !(ac->ac_g_ex.fe_len % sbi->s_stripe)) ext4_mb_scan_aligned(ac, &e4b); else ext4_mb_complex_scan_group(ac, &e4b); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); if (ac->ac_status != AC_STATUS_CONTINUE) break; } } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { /* * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) */ lost = atomic_inc_return(&sbi->s_mb_lost_chunks); mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, lost); ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; cr = 3; goto repeat; } } out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = first_err; mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, cr, err); if (nr) ext4_mb_prefetch_fini(sb, prefetch_grp, nr); return err; } static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = PDE_DATA(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = PDE_DATA(file_inode(seq->file)); ext4_group_t group; ++*pos; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { struct super_block *sb = PDE_DATA(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; int err, buddy_loaded = 0; struct ext4_buddy e4b; struct ext4_group_info *grinfo; unsigned char blocksize_bits = min_t(unsigned char, sb->s_blocksize_bits, EXT4_MAX_BLOCK_LOG_SIZE); struct sg { struct ext4_group_info info; ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; } sg; group--; if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { seq_printf(seq, "#%-5u: I/O error\n", group); return 0; } buddy_loaded = 1; } memcpy(&sg, ext4_get_group_info(sb, group), i); if (buddy_loaded) ext4_mb_unload_buddy(&e4b); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); seq_puts(seq, " ]\n"); return 0; } static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, .show = ext4_mb_seq_groups_show, }; static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; BUG_ON(!cachep); return cachep; } /* * Allocate the top-level s_group_info array for the specified number * of groups */ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); if (size <= sbi->s_group_info_size) return 0; size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); new_groupinfo = kvzalloc(size, GFP_KERNEL); if (!new_groupinfo) { ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } rcu_read_lock(); old_groupinfo = rcu_dereference(sbi->s_group_info); if (old_groupinfo) memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); rcu_read_unlock(); rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); if (old_groupinfo) ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; } /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { int i; int metalen = 0; int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. * If it's true, we have to allocate a new table of pointers * to ext4_group_info structures */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); meta_group_info = kmalloc(metalen, GFP_NOFS); if (meta_group_info == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate mem " "for a buddy group"); goto exit_meta_group_info; } rcu_read_lock(); rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; rcu_read_unlock(); } meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); /* * initialize bb_free to be able to skip * empty groups without initialization */ if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { meta_group_info[i]->bb_free = ext4_free_clusters_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = ext4_free_group_clusters(sb, desc); } INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { struct ext4_group_info ***group_info; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); kfree(group_info[idx]); group_info[idx] = NULL; rcu_read_unlock(); } exit_meta_group_info: return -ENOMEM; } /* ext4_mb_add_groupinfo */ static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); if (err) return err; sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); goto err_freesgi; } /* To avoid potentially colliding with an valid on-disk inode number, * use EXT4_BAD_INO for the buddy cache inode number. This inode is * not in the inode hash, so it should never be found by iget(), but * this will avoid confusion if it ever shows up during debugging. */ sbi->s_buddy_cache->i_ino = EXT4_BAD_INO; EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { cond_resched(); desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i); goto err_freebuddy; } if (ext4_mb_add_groupinfo(sb, i, desc) != 0) goto err_freebuddy; } if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO. * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is * unsigned integer, so the maximum shift is 32. */ if (sbi->s_es->s_log_groups_per_flex >= 32) { ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); goto err_freebuddy; } sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32; } if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) sbi->s_mb_prefetch = ext4_get_groups_count(sb); /* now many real IOs to prefetch within a single allocation at cr=0 * given cr=0 is an CPU-related optimization we shouldn't try to * load too many groups, at some point we should start to use what * we've got in memory. * with an average random access time 5ms, it'd take a second to get * 200 groups (* N with flex_bg), so let's make this limit 4 */ sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); return 0; err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) kfree(group_info[i]); rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: rcu_read_lock(); kvfree(rcu_dereference(sbi->s_group_info)); rcu_read_unlock(); return -ENOMEM; } static void ext4_groupinfo_destroy_slabs(void) { int i; for (i = 0; i < NR_GRPINFO_CACHES; i++) { kmem_cache_destroy(ext4_groupinfo_caches[i]); ext4_groupinfo_caches[i] = NULL; } } static int ext4_groupinfo_create_slab(size_t size) { static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex); int slab_size; int blocksize_bits = order_base_2(size); int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep; if (cache_index >= NR_GRPINFO_CACHES) return -EINVAL; if (unlikely(cache_index < 0)) cache_index = 0; mutex_lock(&ext4_grpinfo_slab_create_mutex); if (ext4_groupinfo_caches[cache_index]) { mutex_unlock(&ext4_grpinfo_slab_create_mutex); return 0; /* Already created */ } slab_size = offsetof(struct ext4_group_info, bb_counters[blocksize_bits + 2]); cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index], slab_size, 0, SLAB_RECLAIM_ACCOUNT, NULL); ext4_groupinfo_caches[cache_index] = cachep; mutex_unlock(&ext4_grpinfo_slab_create_mutex); if (!cachep) { printk(KERN_EMERG "EXT4-fs: no memory for groupinfo slab cache\n"); return -ENOMEM; } return 0; } int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; unsigned offset, offset_incr; unsigned max; int ret; i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { ret = -ENOMEM; goto out; } i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { ret = -ENOMEM; goto out; } ret = ext4_groupinfo_create_slab(sb->s_blocksize); if (ret < 0) goto out; /* order 0 is regular bitmap */ sbi->s_mb_maxs[0] = sb->s_blocksize << 3; sbi->s_mb_offsets[0] = 0; i = 1; offset = 0; offset_incr = 1 << (sb->s_blocksize_bits - 1); max = sb->s_blocksize << 2; do { sbi->s_mb_offsets[i] = offset; sbi->s_mb_maxs[i] = max; offset += offset_incr; offset_incr = offset_incr >> 1; max = max >> 1; i++; } while (i <= sb->s_blocksize_bits + 1); spin_lock_init(&sbi->s_md_lock); spin_lock_init(&sbi->s_bal_lock); sbi->s_mb_free_pending = 0; INIT_LIST_HEAD(&sbi->s_freed_data_list); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file * systems, this is probably too big (i.e, if the cluster size * is 1 megabyte, then group preallocation size becomes half a * gigabyte!). As a default, we will keep a two megabyte * group pralloc size for cluster sizes up to 64k, and after * that, we will force a minimum group preallocation size of * 32 clusters. This translates to 8 megs when the cluster * size is 256k, and 32 megs when the cluster size is 1 meg, * which seems reasonable as a default. */ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >> sbi->s_cluster_bits, 32); /* * If there is a s_stripe > 1, then we set the s_mb_group_prealloc * to the lowest multiple of s_stripe which is bigger than * the s_mb_group_prealloc as determined above. We want * the preallocation size to be an exact multiple of the * RAID stripe size so that preallocations don't fragment * the stripes. */ if (sbi->s_stripe > 1) { sbi->s_mb_group_prealloc = roundup( sbi->s_mb_group_prealloc, sbi->s_stripe); } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { ret = -ENOMEM; goto out; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; lg = per_cpu_ptr(sbi->s_locality_groups, i); mutex_init(&lg->lg_mutex); for (j = 0; j < PREALLOC_TB_SIZE; j++) INIT_LIST_HEAD(&lg->lg_prealloc_list[j]); spin_lock_init(&lg->lg_prealloc_lock); } /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) goto out_free_locality_groups; return 0; out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: kfree(sbi->s_mb_offsets); sbi->s_mb_offsets = NULL; kfree(sbi->s_mb_maxs); sbi->s_mb_maxs = NULL; return ret; } /* need to called with the ext4 group lock held */ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; struct list_head *cur, *tmp; int count = 0; list_for_each_safe(cur, tmp, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); list_del(&pa->pa_group_list); count++; kmem_cache_free(ext4_pspace_cachep, pa); } return count; } int ext4_mb_release(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); if (count) mb_debug(sb, "mballoc: %d PAs left\n", count); ext4_unlock_group(sb, i); kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); rcu_read_unlock(); } kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); iput(sbi->s_buddy_cache); if (sbi->s_mb_stats) { ext4_msg(sb, KERN_INFO, "mballoc: %u blocks %u reqs (%u success)", atomic_read(&sbi->s_bal_allocated), atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, "mballoc: %u extents scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, "mballoc: %lu generated and it took %Lu", sbi->s_mb_buddies_generated, sbi->s_mb_generation_time); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), atomic_read(&sbi->s_mb_discarded)); } free_percpu(sbi->s_locality_groups); return 0; } static inline int ext4_issue_discard(struct super_block *sb, ext4_group_t block_group, ext4_grpblk_t cluster, int count, struct bio **biop) { ext4_fsblk_t discard_block; discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) + ext4_group_first_block_no(sb, block_group)); count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); if (biop) { return __blkdev_issue_discard(sb->s_bdev, (sector_t)discard_block << (sb->s_blocksize_bits - 9), (sector_t)count << (sb->s_blocksize_bits - 9), GFP_NOFS, 0, biop); } else return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } static void ext4_free_data_in_buddy(struct super_block *sb, struct ext4_free_data *entry) { struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0, count2 = 0; mb_debug(sb, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); spin_lock(&EXT4_SB(sb)->s_md_lock); EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count; spin_unlock(&EXT4_SB(sb)->s_md_lock); db = e4b.bd_info; /* there are blocks to put in buddy to make them really free */ count += entry->efd_count; count2++; ext4_lock_group(sb, entry->efd_group); /* Take it out of per group rb tree */ rb_erase(&entry->efd_node, &(db->bb_free_root)); mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count); /* * Clear the trimmed flag for the group so that the next * ext4_trim_fs can trim it. * If the volume is mounted with -o discard, online discard * is supported and the free blocks will be trimmed online. */ if (!test_opt(sb, DISCARD)) EXT4_MB_GRP_CLEAR_TRIMMED(db); if (!db->bb_free_root.rb_node) { /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() */ put_page(e4b.bd_buddy_page); put_page(e4b.bd_bitmap_page); } ext4_unlock_group(sb, entry->efd_group); kmem_cache_free(ext4_free_data_cachep, entry); ext4_mb_unload_buddy(&e4b); mb_debug(sb, "freed %d blocks in %d structures\n", count, count2); } /* * This function is called by the jbd2 layer once the commit has finished, * so we know we can free the blocks that were released with that commit. */ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; struct bio *discard_bio = NULL; struct list_head freed_data_list; struct list_head *cut_pos = NULL; int err; INIT_LIST_HEAD(&freed_data_list); spin_lock(&sbi->s_md_lock); list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { if (entry->efd_tid != commit_tid) break; cut_pos = &entry->efd_list; } if (cut_pos) list_cut_position(&freed_data_list, &sbi->s_freed_data_list, cut_pos); spin_unlock(&sbi->s_md_lock); if (test_opt(sb, DISCARD)) { list_for_each_entry(entry, &freed_data_list, efd_list) { err = ext4_issue_discard(sb, entry->efd_group, entry->efd_start_cluster, entry->efd_count, &discard_bio); if (err && err != -EOPNOTSUPP) { ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%d failed" " with %d", entry->efd_group, entry->efd_start_cluster, entry->efd_count, err); } else if (err == -EOPNOTSUPP) break; } if (discard_bio) { submit_bio_wait(discard_bio); bio_put(discard_bio); } } list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); } int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) goto out; ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, SLAB_RECLAIM_ACCOUNT); if (ext4_ac_cachep == NULL) goto out_pa_free; ext4_free_data_cachep = KMEM_CACHE(ext4_free_data, SLAB_RECLAIM_ACCOUNT); if (ext4_free_data_cachep == NULL) goto out_ac_free; return 0; out_ac_free: kmem_cache_destroy(ext4_ac_cachep); out_pa_free: kmem_cache_destroy(ext4_pspace_cachep); out: return -ENOMEM; } void ext4_exit_mballoc(void) { /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. */ rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_data_cachep); ext4_groupinfo_destroy_slabs(); } /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps * Returns 0 if success or error code */ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle, unsigned int reserv_clstrs) { struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); sb = ac->ac_sb; sbi = EXT4_SB(sb); bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto out_err; } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto out_err; err = -EIO; gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, &gdp_bh); if (!gdp) goto out_err; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); BUFFER_TRACE(gdp_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdp_bh); if (err) goto out_err; block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) err = -EFSCORRUPTED; goto out_err; } ext4_lock_group(sb, ac->ac_b_ex.fe_group); #ifdef AGGRESSIVE_CHECK { int i; for (i = 0; i < ac->ac_b_ex.fe_len; i++) { BUG_ON(mb_test_bit(ac->ac_b_ex.fe_start + i, bitmap_bh->b_data)); } } #endif ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, ac->ac_b_ex.fe_group, gdp)); } len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; ext4_free_group_clusters_set(sb, gdp, len); ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative */ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, ac->ac_b_ex.fe_group); atomic64_sub(ac->ac_b_ex.fe_len, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (err) goto out_err; err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); out_err: brelse(bitmap_bh); return err; } /* * Idempotent helper for Ext4 fast commit replay path to set the state of * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, int state) { struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; int i, clen, err; int already; clen = EXT4_B2C(sbi, len); ext4_get_group_no_and_offset(sb, block, &group, &blkoff); bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto out_err; } err = -EIO; gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) goto out_err; ext4_lock_group(sb, group); already = 0; for (i = 0; i < clen; i++) if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state) already++; if (state) ext4_set_bits(bitmap_bh->b_data, blkoff, clen); else mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); } if (state) clen = ext4_free_group_clusters(sb, gdp) - clen + already; else clen = ext4_free_group_clusters(sb, gdp) + clen - already; ext4_free_group_clusters_set(sb, gdp, clen); ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, group); atomic64_sub(len, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) goto out_err; sync_dirty_buffer(bitmap_bh); err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); sync_dirty_buffer(gdp_bh); out_err: brelse(bitmap_bh); } /* * here we normalize request for locality group * Group request are normalized to s_mb_group_prealloc, which goes to * s_strip if we set the same via mount option. * s_mb_group_prealloc can be configured via * /sys/fs/ext4/<partition>/mb_group_prealloc * * XXX: should we try to preallocate more than the group has now? */ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; BUG_ON(lg == NULL); ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; mb_debug(sb, "goal %u blocks for locality group\n", ac->ac_g_ex.fe_len); } /* * Normalization means making request better in terms of * size and alignment */ static noinline_for_stack void ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits, max; ext4_lblk_t end; loff_t size, start_off; loff_t orig_size __maybe_unused; ext4_lblk_t start; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_prealloc_space *pa; /* do normalize only data requests, metadata requests do not need preallocation */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; /* sometime caller may want exact blocks */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; /* caller may indicate that preallocation isn't * required (it's a tail, for example) */ if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC) return; if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) { ext4_mb_normalize_group_request(ac); return ; } bsbits = ac->ac_sb->s_blocksize_bits; /* first, let's learn actual file size * given current request is allocated */ size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); orig_size = size; /* max size of free chunks */ max = 2 << bsbits; #define NRL_CHECK_SIZE(req, size, max, chunk_size) \ (req <= (size) || max <= (chunk_size)) /* first, try to predict filesize */ /* XXX: should this table be tunable? */ start_off = 0; if (size <= 16 * 1024) { size = 16 * 1024; } else if (size <= 32 * 1024) { size = 32 * 1024; } else if (size <= 64 * 1024) { size = 64 * 1024; } else if (size <= 128 * 1024) { size = 128 * 1024; } else if (size <= 256 * 1024) { size = 256 * 1024; } else if (size <= 512 * 1024) { size = 512 * 1024; } else if (size <= 1024 * 1024) { size = 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (21 - bsbits)) << 21; size = 2 * 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (22 - bsbits)) << 22; size = 4 * 1024 * 1024; } else if (NRL_CHECK_SIZE(ac->ac_o_ex.fe_len, (8<<20)>>bsbits, max, 8 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (23 - bsbits)) << 23; size = 8 * 1024 * 1024; } else { start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits; size = (loff_t) EXT4_C2B(EXT4_SB(ac->ac_sb), ac->ac_o_ex.fe_len) << bsbits; } size = size >> bsbits; start = start_off >> bsbits; /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; start = ar->lleft + 1; } if (ar->pright && start + size - 1 >= ar->lright) size -= start + size - ar->lright; /* * Trim allocation request for filesystems with artificially small * groups. */ if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb); end = start + size; /* check we don't cross already preallocated blocks */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { ext4_lblk_t pa_end; if (pa->pa_deleted) continue; spin_lock(&pa->pa_lock); if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb), pa->pa_len); /* PA must not overlap original request */ BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end || ac->ac_o_ex.fe_logical < pa->pa_lstart)); /* skip PAs this normalized request doesn't overlap with */ if (pa->pa_lstart >= end || pa_end <= start) { spin_unlock(&pa->pa_lock); continue; } BUG_ON(pa->pa_lstart <= start && pa_end >= end); /* adjust start or end to be adjacent to this pa */ if (pa_end <= ac->ac_o_ex.fe_logical) { BUG_ON(pa_end < start); start = pa_end; } else if (pa->pa_lstart > ac->ac_o_ex.fe_logical) { BUG_ON(pa->pa_lstart > end); end = pa->pa_lstart; } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); size = end - start; /* XXX: extra loop to check we really don't overlap preallocations */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { ext4_lblk_t pa_end; spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0) { pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb), pa->pa_len); BUG_ON(!(start >= pa_end || end <= pa->pa_lstart)); } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); if (start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", (unsigned long) start, (unsigned long) size, (unsigned long) ac->ac_o_ex.fe_logical); BUG(); } BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ /* XXX: is it better to align blocks WRT to logical * placement or satisfy big request as is */ ac->ac_g_ex.fe_logical = start; ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); /* define goal start in order to merge */ if (ar->pright && (ar->lright == (start + size))) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, &ac->ac_f_ex.fe_group, &ac->ac_f_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } if (ar->pleft && (ar->lleft + 1 == start)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, &ac->ac_f_ex.fe_group, &ac->ac_f_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } mb_debug(ac->ac_sb, "goal: %lld(was %lld) blocks at %u\n", size, orig_size, start); } static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); if (ac->ac_found > sbi->s_mb_max_to_scan) atomic_inc(&sbi->s_bal_breaks); } if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) trace_ext4_mballoc_alloc(ac); else trace_ext4_mballoc_prealloc(ac); } /* * Called on failure; free up any blocks from the inode PA for this * context. We don't need this for MB_GROUP_PA because we only change * pa_free in ext4_mb_release_context(), but on failure, we've already * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. */ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; struct ext4_buddy e4b; int err; if (pa == NULL) { if (ac->ac_f_ex.fe_len == 0) return; err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); if (err) { /* * This should never happen since we pin the * pages in the ext4_allocation_context so * ext4_mb_load_buddy() should never fail. */ WARN(1, "mb_load_buddy failed (%d)", err); return; } ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, ac->ac_f_ex.fe_len); ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ext4_mb_unload_buddy(&e4b); return; } if (pa->pa_type == MB_INODE_PA) pa->pa_free += ac->ac_b_ex.fe_len; } /* * use blocks preallocated to inode */ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; ext4_fsblk_t end; int len; /* found preallocated blocks, use them */ start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart); end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len), start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len)); len = EXT4_NUM_B2C(sbi, end - start); ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); pa->pa_free -= len; mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); } /* * use blocks preallocated to locality group */ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; /* we don't correct pa_pstart or pa_plen here to avoid * possible race when the group is being loaded concurrently * instead we correct pa later, after blocks are marked * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa); } /* * Return the prealloc space that have minimal distance * from the goal block. @cpa is the prealloc * space that is having currently known minimal distance * from the goal block. */ static struct ext4_prealloc_space * ext4_mb_check_group_pa(ext4_fsblk_t goal_block, struct ext4_prealloc_space *pa, struct ext4_prealloc_space *cpa) { ext4_fsblk_t cur_distance, new_distance; if (cpa == NULL) { atomic_inc(&pa->pa_count); return pa; } cur_distance = abs(goal_block - cpa->pa_pstart); new_distance = abs(goal_block - pa->pa_pstart); if (cur_distance <= new_distance) return cpa; /* drop the previous reference */ atomic_dec(&cpa->pa_count); atomic_inc(&pa->pa_count); return pa; } /* * search goal blocks in preallocated space */ static noinline_for_stack bool ext4_mb_use_preallocated(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int order, i; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_locality_group *lg; struct ext4_prealloc_space *pa, *cpa = NULL; ext4_fsblk_t goal_block; /* only data can be preallocated */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return false; /* first, try per-file preallocation */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { /* all fields in this condition don't change, * so we can skip locking for them */ if (ac->ac_o_ex.fe_logical < pa->pa_lstart || ac->ac_o_ex.fe_logical >= (pa->pa_lstart + EXT4_C2B(sbi, pa->pa_len))) continue; /* non-extent files can't have physical blocks past 2^32 */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) && (pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len) > EXT4_MAX_BLOCK_FILE_PHYS)) continue; /* found preallocated blocks, use them */ spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0 && pa->pa_free) { atomic_inc(&pa->pa_count); ext4_mb_use_inode_pa(ac, pa); spin_unlock(&pa->pa_lock); ac->ac_criteria = 10; rcu_read_unlock(); return true; } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); /* can we use group allocation? */ if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)) return false; /* inode may have no locality group for some reason */ lg = ac->ac_lg; if (lg == NULL) return false; order = fls(ac->ac_o_ex.fe_len) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex); /* * search for the prealloc space that is having * minimal distance from the goal block. */ for (i = order; i < PREALLOC_TB_SIZE; i++) { rcu_read_lock(); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[i], pa_inode_list) { spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0 && pa->pa_free >= ac->ac_o_ex.fe_len) { cpa = ext4_mb_check_group_pa(goal_block, pa, cpa); } spin_unlock(&pa->pa_lock); } rcu_read_unlock(); } if (cpa) { ext4_mb_use_group_pa(ac, cpa); ac->ac_criteria = 20; return true; } return false; } /* * the function goes through all block freed in the group * but not yet committed and marks them used in in-core bitmap. * buddy must be generated from this bitmap * Need to be called with the ext4 group lock held */ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group) { struct rb_node *n; struct ext4_group_info *grp; struct ext4_free_data *entry; grp = ext4_get_group_info(sb, group); n = rb_first(&(grp->bb_free_root)); while (n) { entry = rb_entry(n, struct ext4_free_data, efd_node); ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); n = rb_next(n); } return; } /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ static noinline_for_stack void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_prealloc_space *pa; struct list_head *cur; ext4_group_t groupnr; ext4_grpblk_t start; int preallocated = 0; int len; /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here * notice we do NOT ignore preallocations with pa_deleted * otherwise we could leave used blocks available for * allocation in buddy when concurrent ext4_mb_put_pa() * is dropping preallocation */ list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &start); len = pa->pa_len; spin_unlock(&pa->pa_lock); if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); ext4_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } static void ext4_mb_mark_pa_deleted(struct super_block *sb, struct ext4_prealloc_space *pa) { struct ext4_inode_info *ei; if (pa->pa_deleted) { ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", pa->pa_type, pa->pa_pstart, pa->pa_lstart, pa->pa_len); return; } pa->pa_deleted = 1; if (pa->pa_type == MB_INODE_PA) { ei = EXT4_I(pa->pa_inode); atomic_dec(&ei->i_prealloc_active); } } static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); BUG_ON(atomic_read(&pa->pa_count)); BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } /* * drops a reference to preallocated space descriptor * if this was the last reference and the space is consumed */ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, struct super_block *sb, struct ext4_prealloc_space *pa) { ext4_group_t grp; ext4_fsblk_t grp_blk; /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { spin_unlock(&pa->pa_lock); return; } if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; } ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; /* * If doing group-based preallocation, pa_pstart may be in the * next group when pa is used up */ if (pa->pa_type == MB_GROUP_PA) grp_blk--; grp = ext4_get_group_number(sb, grp_blk); /* * possible race: * * P1 (buddy init) P2 (regular allocation) * find block B in PA * copy on-disk bitmap to buddy * mark B in on-disk bitmap * drop PA from group * mark all PAs in buddy * * thus, P1 initializes buddy with B available. to prevent this * we make "copy" and "mark all PAs" atomic and serialize "drop PA" * against that pair */ ext4_lock_group(sb, grp); list_del(&pa->pa_group_list); ext4_unlock_group(sb, grp); spin_lock(pa->pa_obj_lock); list_del_rcu(&pa->pa_inode_list); spin_unlock(pa->pa_obj_lock); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } /* * creates new preallocated space for given inode */ static noinline_for_stack void ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_prealloc_space *pa; struct ext4_group_info *grp; struct ext4_inode_info *ei; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { int winl; int wins; int win; int offs; /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart * to cover original request */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); /* we're limited by original request in that * logical block must be covered any way * winl is window we can move our chunk within */ winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical; /* also, we should cover whole original request */ wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len); /* the smallest one defines real window */ win = min(winl, wins); offs = ac->ac_o_ex.fe_logical % EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (offs && offs < win) win = offs; ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - EXT4_NUM_B2C(sbi, win); BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); } /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; pa->pa_lstart = ac->ac_b_ex.fe_logical; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_inode_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; mb_debug(sb, "new inode pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); ext4_mb_use_inode_pa(ac, pa); atomic_add(pa->pa_free, &sbi->s_mb_preallocated); ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); pa->pa_obj_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); spin_lock(pa->pa_obj_lock); list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); atomic_inc(&ei->i_prealloc_active); } /* * creates new preallocated space for locality group inodes belongs to */ static noinline_for_stack void ext4_mb_new_group_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg; struct ext4_prealloc_space *pa; struct ext4_group_info *grp; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_lstart = pa->pa_pstart; pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_inode_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; mb_debug(sb, "new group pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); lg = ac->ac_lg; BUG_ON(lg == NULL); pa->pa_obj_lock = &lg->lg_prealloc_lock; pa->pa_inode = NULL; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); /* * We will later add the new pa to the right bucket * after updating the pa_free in ext4_mb_release_context */ } static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) { if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) ext4_mb_new_group_pa(ac); else ext4_mb_new_inode_pa(ac); } /* * finds all unused blocks in on-disk bitmap, frees them in * in-core bitmap and buddy. * @pa must be unlinked from inode and group lists, so that * nobody else can find/use it. * the caller MUST hold group/inode locks. * TODO: optimize the case when there are no in-core structures yet */ static noinline_for_stack int ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int end; unsigned int next; ext4_group_t group; ext4_grpblk_t bit; unsigned long long grp_blk_start; int free = 0; BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); end = bit + pa->pa_len; while (bit < end) { bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) break; next = mb_find_next_bit(bitmap_bh->b_data, end, bit); mb_debug(sb, "free preallocated %u/%u in group %u\n", (unsigned) ext4_group_first_block_no(sb, group) + bit, (unsigned) next - bit, (unsigned) group); free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); trace_ext4_mb_release_inode_pa(pa, (grp_blk_start + EXT4_C2B(sbi, bit)), next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } if (free != pa->pa_free) { ext4_msg(e4b->bd_sb, KERN_CRIT, "pa %p: logic %lu, phys. %lu, len %d", pa, (unsigned long) pa->pa_lstart, (unsigned long) pa->pa_pstart, pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* * pa is already deleted so we use the value obtained * from the bitmap and continue. */ } atomic_add(free, &sbi->s_mb_discarded); return 0; } static noinline_for_stack int ext4_mb_release_group_pa(struct ext4_buddy *e4b, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; ext4_group_t group; ext4_grpblk_t bit; trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); return 0; } /* * releases all preallocations in given group * * first, we need to decide discard policy: * - when do we discard * 1) ENOSPC * - how many do we discard * 1) how many requested */ static noinline_for_stack int ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_group_t group, int needed) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; struct list_head list; struct ext4_buddy e4b; int err; int busy = 0; int free, free_total = 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); goto out_dbg; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { ext4_warning(sb, "Error %d loading buddy information for %u", err, group); put_bh(bitmap_bh); goto out_dbg; } if (needed == 0) needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; INIT_LIST_HEAD(&list); repeat: free = 0; ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { spin_unlock(&pa->pa_lock); busy = 1; continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); if (!free) this_cpu_inc(discard_pa_seq); /* we can trust pa_free ... */ free += pa->pa_free; spin_unlock(&pa->pa_lock); list_del(&pa->pa_group_list); list_add(&pa->u.pa_tmp_list, &list); } /* now free all selected PAs */ list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { /* remove from object (inode or locality group) */ spin_lock(pa->pa_obj_lock); list_del_rcu(&pa->pa_inode_list); spin_unlock(pa->pa_obj_lock); if (pa->pa_type == MB_GROUP_PA) ext4_mb_release_group_pa(&e4b, pa); else ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } free_total += free; /* if we still need more blocks and some PAs were used, try again */ if (free_total < needed && busy) { ext4_unlock_group(sb, group); cond_resched(); busy = 0; goto repeat; } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", free_total, group, grp->bb_free); return free_total; } /* * releases all non-used preallocated blocks for given inode * * It's important to discard preallocations under i_data_sem * We don't want another block to be served from the prealloc * space when we are discarding the inode prealloc space. * * FIXME!! Make sure it is valid at all the call sites */ void ext4_discard_preallocations(struct inode *inode, unsigned int needed) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; ext4_group_t group = 0; struct list_head list; struct ext4_buddy e4b; int err; if (!S_ISREG(inode->i_mode)) { /*BUG_ON(!list_empty(&ei->i_prealloc_list));*/ return; } if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return; mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, atomic_read(&ei->i_prealloc_active), needed); INIT_LIST_HEAD(&list); if (needed == 0) needed = UINT_MAX; repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); while (!list_empty(&ei->i_prealloc_list) && needed) { pa = list_entry(ei->i_prealloc_list.prev, struct ext4_prealloc_space, pa_inode_list); BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* this shouldn't happen often - nobody should * use preallocation while we're discarding it */ spin_unlock(&pa->pa_lock); spin_unlock(&ei->i_prealloc_lock); ext4_msg(sb, KERN_ERR, "uh-oh! used pa while discarding"); WARN_ON(1); schedule_timeout_uninterruptible(HZ); goto repeat; } if (pa->pa_deleted == 0) { ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &list); needed--; continue; } /* someone is deleting pa right now */ spin_unlock(&pa->pa_lock); spin_unlock(&ei->i_prealloc_lock); /* we have to wait here because pa_deleted * doesn't mean pa is already unlinked from * the list. as we might be called from * ->clear_inode() the inode will get freed * and concurrent thread which is unlinking * pa from inode's list may access already * freed memory, bad-bad-bad */ /* XXX: if this happens too often, we can * add a flag to force wait only in case * of ->clear_inode(), but not in case of * regular truncate */ schedule_timeout_uninterruptible(HZ); goto repeat; } spin_unlock(&ei->i_prealloc_lock); list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); ext4_mb_unload_buddy(&e4b); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa; BUG_ON(ext4_pspace_cachep == NULL); pa = kmem_cache_zalloc(ext4_pspace_cachep, GFP_NOFS); if (!pa) return -ENOMEM; atomic_set(&pa->pa_count, 1); ac->ac_pa = pa; return 0; } static void ext4_mb_pa_free(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; BUG_ON(!pa); ac->ac_pa = NULL; WARN_ON(!atomic_dec_and_test(&pa->pa_count)); kmem_cache_free(ext4_pspace_cachep, pa); } #ifdef CONFIG_EXT4_DEBUG static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; ngroups = ext4_get_groups_count(sb); mb_debug(sb, "groups: "); for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); mb_debug(sb, "PA:%u:%d:%d\n", i, start, pa->pa_len); } ext4_unlock_group(sb, i); mb_debug(sb, "%u: %d/%d\n", i, grp->bb_free, grp->bb_fragments); } } static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; mb_debug(sb, "Can't allocate:" " Allocation context details:"); mb_debug(sb, "status %u flags 0x%x", ac->ac_status, ac->ac_flags); mb_debug(sb, "orig %lu/%lu/%lu@%lu, " "goal %lu/%lu/%lu@%lu, " "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, (unsigned long)ac->ac_o_ex.fe_len, (unsigned long)ac->ac_o_ex.fe_logical, (unsigned long)ac->ac_g_ex.fe_group, (unsigned long)ac->ac_g_ex.fe_start, (unsigned long)ac->ac_g_ex.fe_len, (unsigned long)ac->ac_g_ex.fe_logical, (unsigned long)ac->ac_b_ex.fe_group, (unsigned long)ac->ac_b_ex.fe_start, (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); mb_debug(sb, "%u found", ac->ac_found); ext4_mb_show_pa(sb); } #else static inline void ext4_mb_show_pa(struct super_block *sb) { return; } static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { ext4_mb_show_pa(ac->ac_sb); return; } #endif /* * We use locality group preallocation for small size file. The size of the * file is determined by the current size or the resulting size after * allocation which ever is larger * * One can tune this size via /sys/fs/ext4/<partition>/mb_stream_req */ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; if ((size == isize) && !ext4_fs_is_busy(sbi) && !inode_is_open_for_write(ac->ac_inode)) { ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } if (sbi->s_mb_group_prealloc <= 0) { ac->ac_flags |= EXT4_MB_STREAM_ALLOC; return; } /* don't use group allocation for large files */ size = max(size, isize); if (size > sbi->s_mb_stream_request) { ac->ac_flags |= EXT4_MB_STREAM_ALLOC; return; } BUG_ON(ac->ac_lg != NULL); /* * locality group prealloc space are per cpu. The reason for having * per cpu locality group is to reduce the contention between block * request from multiple CPUs. */ ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups); /* we're going to use group allocation */ ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC; /* serialize all allocations in the group */ mutex_lock(&ac->ac_lg->lg_mutex); } static noinline_for_stack int ext4_mb_initialize_context(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_group_t group; unsigned int len; ext4_fsblk_t goal; ext4_grpblk_t block; /* we can't allocate > group size */ len = ar->len; /* just a dirty hack to filter too big requests */ if (len >= EXT4_CLUSTERS_PER_GROUP(sb)) len = EXT4_CLUSTERS_PER_GROUP(sb); /* start searching from the goal */ goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical; ac->ac_o_ex.fe_group = group; ac->ac_o_ex.fe_start = block; ac->ac_o_ex.fe_len = len; ac->ac_g_ex = ac->ac_o_ex; ac->ac_flags = ar->flags; /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); mb_debug(sb, "init ac: %u blocks @ %u, goal %u, flags 0x%x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, (unsigned) ar->lleft, (unsigned) ar->pleft, (unsigned) ar->lright, (unsigned) ar->pright, inode_is_open_for_write(ar->inode) ? "" : "non-"); return 0; } static noinline_for_stack void ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_locality_group *lg, int order, int total_entries) { ext4_group_t group = 0; struct ext4_buddy e4b; struct list_head discard_list; struct ext4_prealloc_space *pa, *tmp; mb_debug(sb, "discard locality group preallocation\n"); INIT_LIST_HEAD(&discard_list); spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], pa_inode_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* * This is the pa that we just used * for block allocation. So don't * free that */ spin_unlock(&pa->pa_lock); continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* only lg prealloc space */ BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &discard_list); total_entries--; if (total_entries <= 5) { /* * we want to keep only 5 entries * allowing it to grow to 8. This * mak sure we don't call discard * soon for this list. */ break; } } spin_unlock(&lg->lg_prealloc_lock); list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { int err; group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_group_pa(&e4b, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } /* * We have incremented pa_count. So it cannot be freed at this * point. Also we hold lg_mutex. So no parallel allocation is * possible from this lg. That means pa_free cannot be updated. * * A parallel ext4_mb_discard_group_preallocations is possible. * which can cause the lg_prealloc_list to be updated. */ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) { int order, added = 0, lg_prealloc_count = 1; struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa; order = fls(pa->pa_free) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; /* Add the prealloc space to lg */ spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order], pa_inode_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted) { spin_unlock(&tmp_pa->pa_lock); continue; } if (!added && pa->pa_free < tmp_pa->pa_free) { /* Add to the tail of the previous entry */ list_add_tail_rcu(&pa->pa_inode_list, &tmp_pa->pa_inode_list); added = 1; /* * we want to count the total * number of entries in the list */ } spin_unlock(&tmp_pa->pa_lock); lg_prealloc_count++; } if (!added) list_add_tail_rcu(&pa->pa_inode_list, &lg->lg_prealloc_list[order]); spin_unlock(&lg->lg_prealloc_lock); /* Now trim the list to be not more than 8 elements */ if (lg_prealloc_count > 8) { ext4_mb_discard_lg_preallocations(sb, lg, order, lg_prealloc_count); return; } return ; } /* * if per-inode prealloc list is too long, trim some PA */ static void ext4_mb_trim_inode_pa(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int count, delta; count = atomic_read(&ei->i_prealloc_active); delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1; if (count > sbi->s_mb_max_inode_prealloc + delta) { count -= sbi->s_mb_max_inode_prealloc; ext4_discard_preallocations(inode, count); } } /* * release all resource we used in allocation */ static int ext4_mb_release_context(struct ext4_allocation_context *ac) { struct inode *inode = ac->ac_inode; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { if (pa->pa_type == MB_GROUP_PA) { /* see comment in ext4_mb_use_group_pa() */ spin_lock(&pa->pa_lock); pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); /* * We want to add the pa to the right bucket. * Remove it from the list and while adding * make sure the list to which we are adding * doesn't grow big. */ if (likely(pa->pa_free)) { spin_lock(pa->pa_obj_lock); list_del_rcu(&pa->pa_inode_list); spin_unlock(pa->pa_obj_lock); ext4_mb_add_n_trim(ac); } } if (pa->pa_type == MB_INODE_PA) { /* * treat per-inode prealloc list as a lru list, then try * to trim the least recently used PA. */ spin_lock(pa->pa_obj_lock); list_move(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); } ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_page) put_page(ac->ac_bitmap_page); if (ac->ac_buddy_page) put_page(ac->ac_buddy_page); if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); ext4_mb_trim_inode_pa(inode); return 0; } static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0; trace_ext4_mb_discard_preallocations(sb, needed); for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, needed); freed += ret; needed -= ret; } return freed; } static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb, struct ext4_allocation_context *ac, u64 *seq) { int freed; u64 seq_retry = 0; bool ret = false; freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); if (freed) { ret = true; goto out_dbg; } seq_retry = ext4_get_discard_pa_seq_sum(); if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) { ac->ac_flags |= EXT4_MB_STRICT_CHECK; *seq = seq_retry; ret = true; } out_dbg: mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no"); return ret; } static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct ext4_allocation_request *ar, int *errp); /* * Main entry point into mballoc to allocate blocks * it tries to use preallocation first, then falls back * to usual allocation */ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct ext4_allocation_context *ac = NULL; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; u64 seq; might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); trace_ext4_request_blocks(ar); if (sbi->s_mount_state & EXT4_FC_REPLAY) return ext4_mb_new_blocks_simple(handle, ar, errp); /* Allow to use superuser reservation for quota file */ if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { /* Without delayed allocation we need to verify * there is enough free blocks to do block allocation * and verify allocation doesn't exceed the quota limits. */ while (ar->len && ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ cond_resched(); ar->len = ar->len >> 1; } if (!ar->len) { ext4_mb_show_pa(sb); *errp = -ENOSPC; return 0; } reserv_clstrs = ar->len; if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) { dquot_alloc_block_nofail(ar->inode, EXT4_C2B(sbi, ar->len)); } else { while (ar->len && dquot_alloc_block(ar->inode, EXT4_C2B(sbi, ar->len))) { ar->flags |= EXT4_MB_HINT_NOPREALLOC; ar->len--; } } inquota = ar->len; if (ar->len == 0) { *errp = -EDQUOT; goto out; } } ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; goto out; } *errp = ext4_mb_initialize_context(ac, ar); if (*errp) { ar->len = 0; goto out; } ac->ac_op = EXT4_MB_HISTORY_PREALLOC; seq = this_cpu_read(discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); *errp = ext4_mb_pa_alloc(ac); if (*errp) goto errout; repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); /* * pa allocated above is added to grp->bb_prealloc_list only * when we were able to allocate some block i.e. when * ac->ac_status == AC_STATUS_FOUND. * And error from above mean ac->ac_status != AC_STATUS_FOUND * So we have to free this pa here itself. */ if (*errp) { ext4_mb_pa_free(ac); ext4_discard_allocated_blocks(ac); goto errout; } if (ac->ac_status == AC_STATUS_FOUND && ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len) ext4_mb_pa_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } } else { if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above * needs to be freed here itself. */ ext4_mb_pa_free(ac); *errp = -ENOSPC; } errout: if (*errp) { ac->ac_b_ex.fe_len = 0; ar->len = 0; ext4_mb_show_ac(ac); } ext4_mb_release_context(ac); out: if (ac) kmem_cache_free(ext4_ac_cachep, ac); if (inquota && ar->len < inquota) dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len)); if (!ar->len) { if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) /* release all the reserved blocks if non delalloc */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); } trace_ext4_allocate_blocks(ar, (unsigned long long)block); return block; } /* * We can merge two free data extents only if the physical blocks * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi, struct ext4_free_data *entry, struct ext4_free_data *new_entry, struct rb_root *entry_rb_root) { if ((entry->efd_tid != new_entry->efd_tid) || (entry->efd_group != new_entry->efd_group)) return; if (entry->efd_start_cluster + entry->efd_count == new_entry->efd_start_cluster) { new_entry->efd_start_cluster = entry->efd_start_cluster; new_entry->efd_count += entry->efd_count; } else if (new_entry->efd_start_cluster + new_entry->efd_count == entry->efd_start_cluster) { new_entry->efd_count += entry->efd_count; } else return; spin_lock(&sbi->s_md_lock); list_del(&entry->efd_list); spin_unlock(&sbi->s_md_lock); rb_erase(&entry->efd_node, entry_rb_root); kmem_cache_free(ext4_free_data_cachep, entry); } static noinline_for_stack int ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, struct ext4_free_data *new_entry) { ext4_group_t group = e4b->bd_group; ext4_grpblk_t cluster; ext4_grpblk_t clusters = new_entry->efd_count; struct ext4_free_data *entry; struct ext4_group_info *db = e4b->bd_info; struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct rb_node **n = &db->bb_free_root.rb_node, *node; struct rb_node *parent = NULL, *new_node; BUG_ON(!ext4_handle_valid(handle)); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); new_node = &new_entry->efd_node; cluster = new_entry->efd_start_cluster; if (!*n) { /* first free block exent. We need to protect buddy cache from being freed, * otherwise we'll refresh it from * on-disk bitmap and lose not-yet-available * blocks */ get_page(e4b->bd_buddy_page); get_page(e4b->bd_bitmap_page); } while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_free_data, efd_node); if (cluster < entry->efd_start_cluster) n = &(*n)->rb_left; else if (cluster >= (entry->efd_start_cluster + entry->efd_count)) n = &(*n)->rb_right; else { ext4_grp_locked_error(sb, group, 0, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); kmem_cache_free(ext4_free_data_cachep, new_entry); return 0; } } rb_link_node(new_node, parent, n); rb_insert_color(new_node, &db->bb_free_root); /* Now try to see the extent can be merged to left and right */ node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); ext4_try_merge_freed_extent(sbi, entry, new_entry, &(db->bb_free_root)); } spin_lock(&sbi->s_md_lock); list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); return 0; } /* * Simple allocator for Ext4 fast commit replay path. It searches for blocks * linearly starting at the goal block and also excludes the blocks which * are going to be in use after fast commit replay. */ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct buffer_head *bitmap_bh; struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; int i = sb->s_blocksize; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ar->len = 0; ext4_get_group_no_and_offset(sb, goal, &group, &blkoff); for (; group < ext4_get_groups_count(sb); group++) { bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { *errp = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return 0; } ext4_get_group_no_and_offset(sb, max(ext4_group_first_block_no(sb, group), goal), NULL, &blkoff); i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize, blkoff); brelse(bitmap_bh); if (i >= sb->s_blocksize) continue; if (ext4_fc_replay_check_excluded(sb, ext4_group_first_block_no(sb, group) + i)) continue; break; } if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize) return 0; block = ext4_group_first_block_no(sb, group) + i; ext4_mb_mark_bb(sb, block, 1, 1); ar->len = 1; return block; } static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { struct buffer_head *bitmap_bh; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; ext4_group_t group; ext4_grpblk_t blkoff; int already_freed = 0, err, i; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return; } gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) return; for (i = 0; i < count; i++) { if (!mb_test_bit(blkoff + i, bitmap_bh->b_data)) already_freed++; } mb_clear_bits(bitmap_bh->b_data, blkoff, count); err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) return; ext4_free_group_clusters_set( sb, gdp, ext4_free_group_clusters(sb, gdp) + count - already_freed); ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); sync_dirty_buffer(bitmap_bh); sync_dirty_buffer(gdp_bh); brelse(bitmap_bh); } /** * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags) { struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; unsigned int overflow; ext4_grpblk_t bit; struct buffer_head *gd_bh; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; int ret; sbi = EXT4_SB(sb); if (sbi->s_mount_state & EXT4_FC_REPLAY) { ext4_free_blocks_simple(inode, block, count); return; } might_sleep(); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); else block = bh->b_blocknr; } if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return; } ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { BUG_ON(count > 1); ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, inode, bh, block); } /* * If the extent to be freed does not begin on a cluster * boundary, we need to deal with partial clusters at the * beginning and end of the extent. Normally we will free * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; block += overflow; if (count > overflow) count -= overflow; else return; } else { block -= overflow; count += overflow; } } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) count -= overflow; else return; } else count += sbi->s_cluster_ratio - overflow; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { int i; int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; for (i = 0; i < count; i++) { cond_resched(); if (is_metadata) bh = sb_find_get_block(inode->i_sb, block + i); ext4_forget(handle, is_metadata, inode, bh, block + i); } } do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT( ext4_get_group_info(sb, block_group)))) return; /* * Check to see if we are freeing blocks across a group * boundary. */ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) { overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto error_return; } gdp = ext4_get_group_desc(sb, block_group, &gd_bh); if (!gdp) { err = -EIO; goto error_return; } if (in_range(ext4_block_bitmap(sb, gdp), block, count) || in_range(ext4_inode_bitmap(sb, gdp), block, count) || in_range(block, ext4_inode_table(sb, gdp), sbi->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, gdp), sbi->s_itb_per_group)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_return; } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto error_return; /* * We are about to modify some metadata. Call the journal APIs * to unshare ->b_data if a currently-committing transaction is * using it */ BUFFER_TRACE(gd_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gd_bh); if (err) goto error_return; #ifdef AGGRESSIVE_CHECK { int i; for (i = 0; i < count_clusters; i++) BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data)); } #endif trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) goto error_return; /* * We need to make sure we don't reuse the freed block until after the * transaction is committed. We make an exception if the inode is to be * written in writeback mode since writeback mode has weak data * consistency guarantees. */ if (ext4_handle_valid(handle) && ((flags & EXT4_FREE_BLOCKS_METADATA) || !ext4_should_writeback_data(inode))) { struct ext4_free_data *new_entry; /* * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed * to fail. */ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { /* need to update group_info->bb_free and bitmap * with group lock held. generate_buddy look at * them with group lock_held */ if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count, NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); } ret = ext4_free_group_clusters(sb, gdp) + count_clusters; ext4_free_group_clusters_set(sb, gdp, ret); ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(count_clusters, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they * can determine if a cluster freed here should be rereserved */ if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) { if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); } ext4_mb_unload_buddy(&e4b); /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); /* And the group descriptor block */ BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); if (!err) err = ret; if (overflow && !err) { block += count; count = overflow; put_bh(bitmap_bh); goto do_more; } error_return: brelse(bitmap_bh); ext4_std_error(sb, err); return; } /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. */ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { struct buffer_head *bitmap_bh = NULL; struct buffer_head *gd_bh; ext4_group_t block_group; ext4_grpblk_t bit; unsigned int i; struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; int err = 0, ret, free_clusters_count; ext4_grpblk_t clusters_freed; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); if (count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); /* * Check to see if we are freeing blocks across a group * boundary. */ if (bit + cluster_count > EXT4_CLUSTERS_PER_GROUP(sb)) { ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; goto error_return; } bitmap_bh = ext4_read_block_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto error_return; } desc = ext4_get_group_desc(sb, block_group, &gd_bh); if (!desc) { err = -EIO; goto error_return; } if (in_range(ext4_block_bitmap(sb, desc), block, count) || in_range(ext4_inode_bitmap(sb, desc), block, count) || in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || in_range(block + count - 1, ext4_inode_table(sb, desc), sbi->s_itb_per_group)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; goto error_return; } BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, bitmap_bh); if (err) goto error_return; /* * We are about to modify some metadata. Call the journal APIs * to unshare ->b_data if a currently-committing transaction is * using it */ BUFFER_TRACE(gd_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gd_bh); if (err) goto error_return; for (i = 0, clusters_freed = 0; i < cluster_count; i++) { BUFFER_TRACE(bitmap_bh, "clear bit"); if (!mb_test_bit(bit + i, bitmap_bh->b_data)) { ext4_error(sb, "bit already cleared for block %llu", (ext4_fsblk_t)(block + i)); BUFFER_TRACE(bitmap_bh, "bit already cleared"); } else { clusters_freed++; } } err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) goto error_return; /* * need to update group_info->bb_free and bitmap * with group lock held. generate_buddy look at * them with group lock_held */ ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, cluster_count); mb_free_blocks(NULL, &e4b, bit, cluster_count); free_clusters_count = clusters_freed + ext4_free_group_clusters(sb, desc); ext4_free_group_clusters_set(sb, desc, free_clusters_count); ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh); ext4_group_desc_csum_set(sb, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, clusters_freed); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); atomic64_add(clusters_freed, &sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_clusters); } ext4_mb_unload_buddy(&e4b); /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); /* And the group descriptor block */ BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); if (!err) err = ret; error_return: brelse(bitmap_bh); ext4_std_error(sb, err); return err; } /** * ext4_trim_extent -- function to TRIM one single free extent in the group * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM * @group: alloc. group we are working with * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ static int ext4_trim_extent(struct super_block *sb, int start, int count, ext4_group_t group, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); assert_spin_locked(ext4_group_lock_ptr(sb, group)); ex.fe_start = start; ex.fe_group = group; ex.fe_len = count; /* * Mark blocks used, so no one can reuse them while * being trimmed. */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); ret = ext4_issue_discard(sb, group, start, count, NULL); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; } /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system * @group: group to be trimmed * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count * * ext4_trim_all_free walks through group's buddy bitmap searching for free * extents. When the free block is found, ext4_trim_extent is called to TRIM * the extent. * * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy * bitmap. Then issue a TRIM command on this extent and free the extent in * the group buddy bitmap. This is done until whole group is scanned. */ static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { void *bitmap; ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; int ret = 0; trace_ext4_trim_all_free(sb, group, start, max); ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { ext4_warning(sb, "Error %d loading buddy information for %u", ret, group); return ret; } bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) && minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) goto out; start = (e4b.bd_info->bb_first_free > start) ? e4b.bd_info->bb_first_free : start; while (start <= max) { start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { ret = ext4_trim_extent(sb, start, next - start, group, &e4b); if (ret && ret != -EOPNOTSUPP) break; ret = 0; count += next - start; } free_count += next - start; start = next + 1; if (fatal_signal_pending(current)) { count = -ERESTARTSYS; break; } if (need_resched()) { ext4_unlock_group(sb, group); cond_resched(); ext4_lock_group(sb, group); } if ((e4b.bd_info->bb_free - free_count) < minblocks) break; } if (!ret) { ret = count; EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); } out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", count, group); return ret; } /** * ext4_trim_fs() -- trim ioctl handle function * @sb: superblock for filesystem * @range: fstrim_range structure * * start: First Byte to trim * len: number of Bytes to trim from start * minlen: minimum extent length in Bytes * ext4_trim_fs goes through all allocation groups containing Bytes from * start to start+len. For each such a group ext4_trim_all_free function * is invoked to trim all free space. */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; uint64_t start, end, minlen, trimmed = 0; ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); int ret = 0; start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = EXT4_NUM_B2C(EXT4_SB(sb), range->minlen >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) || start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; if (end >= max_blks) end = max_blks - 1; if (end <= first_data_blk) goto out; if (start < first_data_blk) start = first_data_blk; /* Determine first and last group to examine based on start and end */ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start, &first_group, &first_cluster); ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end, &last_group, &last_cluster); /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) break; } /* * For all the groups except the last one, last cluster will * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ if (group == last_group) end = last_cluster; if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, end, minlen); if (cnt < 0) { ret = cnt; break; } trimmed += cnt; } /* * For every group except the first one, we are sure * that the first cluster to discard will be cluster #0. */ first_cluster = 0; } if (!ret) atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } /* Iterate all the free extents in the group. */ int ext4_mballoc_query_range( struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t end, ext4_mballoc_query_range_fn formatter, void *priv) { void *bitmap; ext4_grpblk_t next; struct ext4_buddy e4b; int error; error = ext4_mb_load_buddy(sb, group, &e4b); if (error) return error; bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); start = (e4b.bd_info->bb_first_free > start) ? e4b.bd_info->bb_first_free : start; if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; while (start <= end) { start = mb_find_next_zero_bit(bitmap, end + 1, start); if (start > end) break; next = mb_find_next_bit(bitmap, end + 1, start); ext4_unlock_group(sb, group); error = formatter(sb, group, start, next - start, priv); if (error) goto out_unload; ext4_lock_group(sb, group); start = next + 1; } ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(&e4b); return error; }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_POLL_H #define _LINUX_POLL_H #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #ifdef __clang__ #define MAX_STACK_ALLOC 768 #else #define MAX_STACK_ALLOC 832 #endif #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) #define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; /* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* * Do not touch the structure directly, use the access functions * poll_does_not_wait() and poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; __poll_t _key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { if (p && p->_qproc && wait_address) p->_qproc(filp, wait_address, p); } /* * Return true if it is guaranteed that poll will not wait. This is the case * if the poll() of another file descriptor in the set got an event, so there * is no need for waiting. */ static inline bool poll_does_not_wait(const poll_table *p) { return p == NULL || p->_qproc == NULL; } /* * Return the set of events that the application wants to poll for. * This is useful for drivers that need to know whether a DMA transfer has * to be started implicitly on poll(). You typically only want to do that * if the application is actually polling for POLLIN and/or POLLOUT. */ static inline __poll_t poll_requested_events(const poll_table *p) { return p ? p->_key : ~(__poll_t)0; } static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->_qproc = qproc; pt->_key = ~(__poll_t)0; /* all events enabled */ } static inline bool file_can_poll(struct file *file) { return file->f_op->poll; } static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { if (unlikely(!file->f_op->poll)) return DEFAULT_POLLMASK; return file->f_op->poll(file, pt); } struct poll_table_entry { struct file *filp; __poll_t key; wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; /* * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; struct poll_table_page *table; struct task_struct *polling_task; int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); #define __MAP(v, from, to) \ (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) static inline __u16 mangle_poll(__poll_t val) { __u16 v = (__force __u16)val; #define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } static inline __poll_t demangle_poll(u16 val) { #define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } #undef __MAP #endif /* _LINUX_POLL_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !atomic_read(&lock.val); } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { u32 val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { u32 val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */
1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EMe(WB_REASON_FORKER_THREAD, "forker_thread") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_page_template, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = mapping ? mapping->host->i_ino : 0; __entry->index = page->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_page_template, writeback_dirty_page, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DEFINE_EVENT(writeback_page_template, wait_on_page_writeback, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct page *page, struct bdi_writeback *wb), TP_ARGS(page, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_congest_waited_template, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed), TP_STRUCT__entry( __field( unsigned int, usec_timeout ) __field( unsigned int, usec_delayed ) ), TP_fast_assign( __entry->usec_timeout = usec_timeout; __entry->usec_delayed = usec_delayed; ), TP_printk("usec_timeout=%u usec_delayed=%u", __entry->usec_timeout, __entry->usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #ifndef _LRU_LIST_H #define _LRU_LIST_H #include <linux/list.h> #include <linux/nodemask.h> #include <linux/shrinker.h> struct mem_cgroup; /* list_lru_walk_cb has to always return one of those */ enum lru_status { LRU_REMOVED, /* item removed from list */ LRU_REMOVED_RETRY, /* item removed, but lock has been dropped and reacquired */ LRU_ROTATE, /* item referenced, give another pass */ LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock internally, but has to return locked. */ }; struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; }; struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup lists, indexed by memcg_cache_id */ struct list_lru_one *lru[]; }; struct list_lru_node { /* protects all lists on the node, including per cgroup */ spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; #ifdef CONFIG_MEMCG_KMEM /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg __rcu *memcg_lrus; #endif long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { struct list_lru_node *node; #ifdef CONFIG_MEMCG_KMEM struct list_head list; int shrinker_id; bool memcg_aware; #endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker); #define list_lru_init(lru) \ __list_lru_init((lru), false, NULL, NULL) #define list_lru_init_key(lru, key) \ __list_lru_init((lru), false, (key), NULL) #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, NULL, shrinker) int memcg_update_all_list_lrus(int num_memcgs); void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); /** * list_lru_add: add an element to the lru list's tail * @list_lru: the lru pointer * @item: the item to be added. * * If the element is already part of a list, this function returns doing * nothing. Therefore the caller does not need to keep state about whether or * not the element already belongs in the list and is allowed to lazy update * it. Note however that this is valid for *a* list, not *this* list. If * the caller organize itself in a way that elements can be in more than * one type of list, it is up to the caller to fully remove the item from * the previous list (with list_lru_del() for instance) before moving it * to @list_lru * * Return value: true if the list was updated, false otherwise */ bool list_lru_add(struct list_lru *lru, struct list_head *item); /** * list_lru_del: delete an element to the lru list * @list_lru: the lru pointer * @item: the item to be deleted. * * This function works analogously as list_lru_add in terms of list * manipulation. The comments about an element already pertaining to * a list are also valid for list_lru_del. * * Return value: true if the list was updated, false otherwise */ bool list_lru_del(struct list_lru *lru, struct list_head *item); /** * list_lru_count_one: return the number of objects currently held by @lru * @lru: the lru pointer. * @nid: the node id to count from. * @memcg: the cgroup to count from. * * Always return a non-negative number, 0 for empty lists. There is no * guarantee that the list is not updated while the count is being computed. * Callers that want such a guarantee need to provide an outer lock. */ unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg); unsigned long list_lru_count_node(struct list_lru *lru, int nid); static inline unsigned long list_lru_shrink_count(struct list_lru *lru, struct shrink_control *sc) { return list_lru_count_one(lru, sc->nid, sc->memcg); } static inline unsigned long list_lru_count(struct list_lru *lru) { long count = 0; int nid; for_each_node_state(nid, N_NORMAL_MEMORY) count += list_lru_count_node(lru, nid); return count; } void list_lru_isolate(struct list_lru_one *list, struct list_head *item); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, struct list_lru_one *list, spinlock_t *lock, void *cb_arg); /** * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. * @isolate: callback function that is resposible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * * This function will scan all elements in a particular list_lru, calling the * @isolate callback for each of those items, along with the current list * spinlock and a caller-provided opaque. The @isolate callback can choose to * drop the lock internally, but *must* return with the lock held. The callback * will return an enum lru_status telling the list_lru infrastructure what to * do with the object being scanned. * * Please note that nr_to_walk does not mean how many objects will be freed, * just how many objects will be scanned. * * Return value: the number of objects effectively removed from the LRU. */ unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); /** * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. * @isolate: callback function that is resposible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * * Same as @list_lru_walk_one except that the spinlock is acquired with * spin_lock_irq(). */ unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); static inline unsigned long list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg, &sc->nr_to_scan); } static inline unsigned long list_lru_shrink_walk_irq(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { return list_lru_walk_one_irq(lru, sc->nid, sc->memcg, isolate, cb_arg, &sc->nr_to_scan); } static inline unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk) { long isolated = 0; int nid; for_each_node_state(nid, N_NORMAL_MEMORY) { isolated += list_lru_walk_node(lru, nid, isolate, cb_arg, &nr_to_walk); if (nr_to_walk <= 0) break; } return isolated; } #endif /* _LRU_LIST_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 /* * include/linux/ktime.h * * ktime_t - nanosecond-resolution time format. * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes and macros. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * * Roman Zippel provided the ideas and primary code snippets of * the ktime_t union and further simplifications of the original * code. * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_KTIME_H #define _LINUX_KTIME_H #include <linux/time.h> #include <linux/jiffies.h> #include <asm/bug.h> /* Nanosecond scalar representation for kernel time values */ typedef s64 ktime_t; /** * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value * @secs: seconds to set * @nsecs: nanoseconds to set * * Return: The ktime_t representation of the value. */ static inline ktime_t ktime_set(const s64 secs, const unsigned long nsecs) { if (unlikely(secs >= KTIME_SEC_MAX)) return KTIME_MAX; return secs * NSEC_PER_SEC + (s64)nsecs; } /* Subtract two ktime_t variables. rem = lhs -rhs: */ #define ktime_sub(lhs, rhs) ((lhs) - (rhs)) /* Add two ktime_t variables. res = lhs + rhs: */ #define ktime_add(lhs, rhs) ((lhs) + (rhs)) /* * Same as ktime_add(), but avoids undefined behaviour on overflow; however, * this means that you must check the result for overflow yourself. */ #define ktime_add_unsafe(lhs, rhs) ((u64) (lhs) + (rhs)) /* * Add a ktime_t variable and a scalar nanosecond value. * res = kt + nsval: */ #define ktime_add_ns(kt, nsval) ((kt) + (nsval)) /* * Subtract a scalar nanosecod from a ktime_t variable * res = kt - nsval: */ #define ktime_sub_ns(kt, nsval) ((kt) - (nsval)) /* convert a timespec64 to ktime_t format: */ static inline ktime_t timespec64_to_ktime(struct timespec64 ts) { return ktime_set(ts.tv_sec, ts.tv_nsec); } /* Map the ktime_t to timespec conversion to ns_to_timespec function */ #define ktime_to_timespec64(kt) ns_to_timespec64((kt)) /* Convert ktime_t to nanoseconds */ static inline s64 ktime_to_ns(const ktime_t kt) { return kt; } /** * ktime_compare - Compares two ktime_t variables for less, greater or equal * @cmp1: comparable1 * @cmp2: comparable2 * * Return: ... * cmp1 < cmp2: return <0 * cmp1 == cmp2: return 0 * cmp1 > cmp2: return >0 */ static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2) { if (cmp1 < cmp2) return -1; if (cmp1 > cmp2) return 1; return 0; } /** * ktime_after - Compare if a ktime_t value is bigger than another one. * @cmp1: comparable1 * @cmp2: comparable2 * * Return: true if cmp1 happened after cmp2. */ static inline bool ktime_after(const ktime_t cmp1, const ktime_t cmp2) { return ktime_compare(cmp1, cmp2) > 0; } /** * ktime_before - Compare if a ktime_t value is smaller than another one. * @cmp1: comparable1 * @cmp2: comparable2 * * Return: true if cmp1 happened before cmp2. */ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) { return ktime_compare(cmp1, cmp2) < 0; } #if BITS_PER_LONG < 64 extern s64 __ktime_divns(const ktime_t kt, s64 div); static inline s64 ktime_divns(const ktime_t kt, s64 div) { /* * Negative divisors could cause an inf loop, * so bug out here. */ BUG_ON(div < 0); if (__builtin_constant_p(div) && !(div >> 32)) { s64 ns = kt; u64 tmp = ns < 0 ? -ns : ns; do_div(tmp, div); return ns < 0 ? -tmp : tmp; } else { return __ktime_divns(kt, div); } } #else /* BITS_PER_LONG < 64 */ static inline s64 ktime_divns(const ktime_t kt, s64 div) { /* * 32-bit implementation cannot handle negative divisors, * so catch them on 64bit as well. */ WARN_ON(div < 0); return kt / div; } #endif static inline s64 ktime_to_us(const ktime_t kt) { return ktime_divns(kt, NSEC_PER_USEC); } static inline s64 ktime_to_ms(const ktime_t kt) { return ktime_divns(kt, NSEC_PER_MSEC); } static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) { return ktime_to_us(ktime_sub(later, earlier)); } static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier) { return ktime_to_ms(ktime_sub(later, earlier)); } static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { return ktime_add_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_add_ms(const ktime_t kt, const u64 msec) { return ktime_add_ns(kt, msec * NSEC_PER_MSEC); } static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) { return ktime_sub_ns(kt, usec * NSEC_PER_USEC); } static inline ktime_t ktime_sub_ms(const ktime_t kt, const u64 msec) { return ktime_sub_ns(kt, msec * NSEC_PER_MSEC); } extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); /** * ktime_to_timespec64_cond - convert a ktime_t variable to timespec64 * format only if the variable contains data * @kt: the ktime_t variable to convert * @ts: the timespec variable to store the result in * * Return: %true if there was a successful conversion, %false if kt was 0. */ static inline __must_check bool ktime_to_timespec64_cond(const ktime_t kt, struct timespec64 *ts) { if (kt) { *ts = ktime_to_timespec64(kt); return true; } else { return false; } } #include <vdso/ktime.h> static inline ktime_t ns_to_ktime(u64 ns) { return ns; } static inline ktime_t ms_to_ktime(u64 ms) { return ms * NSEC_PER_MSEC; } # include <linux/timekeeping.h> # include <linux/timekeeping32.h> #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 /* SPDX-License-Identifier: GPL-2.0 */ /* * Dynamic queue limits (dql) - Definitions * * Copyright (c) 2011, Tom Herbert <therbert@google.com> * * This header file contains the definitions for dynamic queue limits (dql). * dql would be used in conjunction with a producer/consumer type queue * (possibly a HW queue). Such a queue would have these general properties: * * 1) Objects are queued up to some limit specified as number of objects. * 2) Periodically a completion process executes which retires consumed * objects. * 3) Starvation occurs when limit has been reached, all queued data has * actually been consumed, but completion processing has not yet run * so queuing new data is blocked. * 4) Minimizing the amount of queued data is desirable. * * The goal of dql is to calculate the limit as the minimum number of objects * needed to prevent starvation. * * The primary functions of dql are: * dql_queued - called when objects are enqueued to record number of objects * dql_avail - returns how many objects are available to be queued based * on the object limit and how many objects are already enqueued * dql_completed - called at completion time to indicate how many objects * were retired from the queue * * The dql implementation does not implement any locking for the dql data * structures, the higher layer should provide this. dql_queued should * be serialized to prevent concurrent execution of the function; this * is also true for dql_completed. However, dql_queued and dlq_completed can * be executed concurrently (i.e. they can be protected by different locks). */ #ifndef _LINUX_DQL_H #define _LINUX_DQL_H #ifdef __KERNEL__ #include <asm/bug.h> struct dql { /* Fields accessed in enqueue path (dql_queued) */ unsigned int num_queued; /* Total ever queued */ unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ /* Fields accessed only by completion path (dql_completed) */ unsigned int limit ____cacheline_aligned_in_smp; /* Current limit */ unsigned int num_completed; /* Total ever completed */ unsigned int prev_ovlimit; /* Previous over limit */ unsigned int prev_num_queued; /* Previous queue total */ unsigned int prev_last_obj_cnt; /* Previous queuing cnt */ unsigned int lowest_slack; /* Lowest slack found */ unsigned long slack_start_time; /* Time slacks seen */ /* Configuration */ unsigned int max_limit; /* Max limit */ unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ }; /* Set some static maximums */ #define DQL_MAX_OBJECT (UINT_MAX / 16) #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT) /* * Record number of objects queued. Assumes that caller has already checked * availability in the queue with dql_avail. */ static inline void dql_queued(struct dql *dql, unsigned int count) { BUG_ON(count > DQL_MAX_OBJECT); dql->last_obj_cnt = count; /* We want to force a write first, so that cpu do not attempt * to get cache line containing last_obj_cnt, num_queued, adj_limit * in Shared state, but directly does a Request For Ownership * It is only a hint, we use barrier() only. */ barrier(); dql->num_queued += count; } /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { return READ_ONCE(dql->adj_limit) - READ_ONCE(dql->num_queued); } /* Record number of completed objects and recalculate the limit. */ void dql_completed(struct dql *dql, unsigned int count); /* Reset dql state */ void dql_reset(struct dql *dql); /* Initialize dql state */ void dql_init(struct dql *dql, unsigned int hold_time); #endif /* _KERNEL_ */ #endif /* _LINUX_DQL_H */
1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGTABLE_H #define _LINUX_PGTABLE_H #include <linux/pfn.h> #include <asm/pgtable.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU #include <linux/mm_types.h> #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS #error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* * On almost all architectures and configurations, 0 can be used as the * upper ceiling to free_pgtables(): on many architectures it has the same * effect as using TASK_SIZE. However, there is one configuration which * must impose a more careful limit, to avoid freeing kernel pgtables. */ #ifndef USER_PGTABLES_CEILING #define USER_PGTABLES_CEILING 0UL #endif /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * * The pXx_index() functions return the index of the entry in the page * table page which would control the given virtual address * * As these functions may be used by the same code for different levels of * the page table folding, they are always available, regardless of * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 * because in such cases PTRS_PER_PxD equals 1. */ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } #define pmd_index pmd_index #endif #ifndef pud_index static inline unsigned long pud_index(unsigned long address) { return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); } #define pud_index pud_index #endif #ifndef pgd_index /* Must be a compile-time constant, so implement it as a macro */ #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); } #define pte_offset_kernel pte_offset_kernel #endif #if defined(CONFIG_HIGHPTE) #define pte_offset_map(dir, address) \ ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ pte_index((address))) #define pte_unmap(pte) kunmap_atomic((pte)) #else #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) #define pte_unmap(pte) ((void)(pte)) /* NOP */ #endif /* Find an entry in the second-level page table.. */ #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { return (pud_t *)p4d_page_vaddr(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) { return (pgd + pgd_index(address)); }; /* * a shortcut to get a pgd_t in a given mm */ #ifndef pgd_offset #define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) #endif /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ #ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) #endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a * pointer to the PMD entry in user or kernel page table or translate a virtual * address to the pointer in the PTE in the kernel page tables with simple * helpers. */ static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); } static inline pmd_t *pmd_off_k(unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); } static inline pte_t *virt_to_kpte(unsigned long vaddr) { pmd_t *pmd = pmd_off_k(vaddr); return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #endif #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #else static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { BUILD_BUG(); return 0; } static inline int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t pte = *ptep; int r = 1; if (!pte_young(pte)) r = 0; else set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); return r; } #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; int r = 1; if (!pmd_young(pmd)) r = 0; else set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); return r; } #else static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else /* * Despite relevant to THP only, this API is called from generic rmap code * under PageTransHuge(), hence needs a dummy implementation for !THP */ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = *ptep; pte_clear(mm, address, ptep); return pte; } #endif #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; pmd_clear(pmdp); return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t pud = *pudp; pud_clear(pudp); return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, int full) { return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); } #endif #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm, unsigned long address, pud_t *pudp, int full) { return pudp_huge_get_and_clear(mm, address, pudp); } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_t pte; pte = ptep_get_and_clear(mm, address, ptep); return pte; } #endif /* * If two threads concurrently fault at the same page, the thread that * won the race updates the PTE and its local TLB/Cache. The other thread * gives up, simply does nothing, and continues; on architectures where * software can update TLB, local TLB can be updated here to avoid next page * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ #ifndef __HAVE_ARCH_UPDATE_MMU_TLB static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { } #define __HAVE_ARCH_UPDATE_MMU_TLB #endif /* * Some architectures may be able to avoid expensive synchronization * primitives when modifications are made to PTE's which are already * not present, or in the process of an address space destruction. */ #ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL static inline void pte_clear_not_present_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_clear(mm, address, ptep); } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); #endif #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte = *ptep; set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); } #endif /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibilty of software setting this bit. It brings * out extra page fault penalty to track page access bit. For optimization page * access bit can be set during all page fault flow on these arches. * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ #ifndef pte_sw_mkyoung static inline pte_t pte_sw_mkyoung(pte_t pte) { return pte; } #define pte_sw_mkyoung pte_sw_mkyoung #endif #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif #ifndef pte_mk_savedwrite #define pte_mk_savedwrite pte_mkwrite #endif #ifndef pte_clear_savedwrite #define pte_clear_savedwrite pte_wrprotect #endif #ifndef pmd_savedwrite #define pmd_savedwrite pmd_write #endif #ifndef pmd_mk_savedwrite #define pmd_mk_savedwrite pmd_mkwrite #endif #ifndef pmd_clear_savedwrite #define pmd_clear_savedwrite pmd_wrprotect #endif #ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t old_pmd = *pmdp; set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); } #else static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t old_pud = *pudp; set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); } #else static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { BUILD_BUG(); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return *pmdp; } #define pmdp_collapse_flush pmdp_collapse_flush #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is an implementation of pmdp_establish() that is only suitable for an * architecture that doesn't have hardware dirty/accessed bits. In this case we * can't race with CPU which sets these bits and non-atomic aproach is fine. */ static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { pmd_t old_pmd = *pmdp; set_pmd_at(vma->vm_mm, address, pmdp, pmd); return old_pmd; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { return pte_val(pte_a) == pte_val(pte_b); } #endif #ifndef __HAVE_ARCH_PTE_UNUSED /* * Some architectures provide facilities to virtualization guests * so that they can flag allocated pages as unused. This allows the * host to transparently reclaim unused pages. This function returns * whether the pte's page is unused. */ static inline int pte_unused(pte_t pte) { return 0; } #endif #ifndef pte_access_permitted #define pte_access_permitted(pte, write) \ (pte_present(pte) && (!(write) || pte_write(pte))) #endif #ifndef pmd_access_permitted #define pmd_access_permitted(pmd, write) \ (pmd_present(pmd) && (!(write) || pmd_write(pmd))) #endif #ifndef pud_access_permitted #define pud_access_permitted(pud, write) \ (pud_present(pud) && (!(write) || pud_write(pud))) #endif #ifndef p4d_access_permitted #define p4d_access_permitted(p4d, write) \ (p4d_present(p4d) && (!(write) || p4d_write(p4d))) #endif #ifndef pgd_access_permitted #define pgd_access_permitted(pgd, write) \ (pgd_present(pgd) && (!(write) || pgd_write(pgd))) #endif #ifndef __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { return pmd_val(pmd_a) == pmd_val(pmd_b); } static inline int pud_same(pud_t pud_a, pud_t pud_b) { return pud_val(pud_a) == pud_val(pud_b); } #endif #ifndef __HAVE_ARCH_P4D_SAME static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) { return p4d_val(p4d_a) == p4d_val(p4d_b); } #endif #ifndef __HAVE_ARCH_PGD_SAME static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) { return pgd_val(pgd_a) == pgd_val(pgd_b); } #endif /* * Use set_p*_safe(), and elide TLB flushing, when confident that *no* * TLB flush will be required as a result of the "set". For example, use * in scenarios where it is known ahead of time that the routine is * setting non-present entries, or re-setting an existing entry to the * same value. Otherwise, use the typical "set" helpers and flush the * TLB. */ #define set_pte_safe(ptep, pte) \ ({ \ WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ set_pte(ptep, pte); \ }) #define set_pmd_safe(pmdp, pmd) \ ({ \ WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ set_pmd(pmdp, pmd); \ }) #define set_pud_safe(pudp, pud) \ ({ \ WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ set_pud(pudp, pud); \ }) #define set_p4d_safe(p4dp, p4d) \ ({ \ WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ set_p4d(p4dp, p4d); \ }) #define set_pgd_safe(pgdp, pgd) \ ({ \ WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ set_pgd(pgdp, pgd); \ }) #ifndef __HAVE_ARCH_DO_SWAP_PAGE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ static inline void arch_do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte) { } #endif #ifndef __HAVE_ARCH_UNMAP_ONE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_unmap_one() can save this * metadata on a swap-out of a page. */ static inline int arch_unmap_one(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t orig_pte) { return 0; } #endif /* * Allow architectures to preserve additional metadata associated with * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP static inline int arch_prepare_to_swap(struct page *page) { return 0; } #endif #ifndef __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { } static inline void arch_swap_invalidate_area(int type) { } #endif #ifndef __HAVE_ARCH_SWAP_RESTORE static inline void arch_swap_restore(swp_entry_t entry, struct page *page) { } #endif #ifndef __HAVE_ARCH_PGD_OFFSET_GATE #define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) #endif #ifndef __HAVE_ARCH_MOVE_PTE #define move_pte(pte, prot, old_addr, new_addr) (pte) #endif #ifndef pte_accessible # define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) #endif /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. */ #define pgd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #ifndef p4d_addr_end #define p4d_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pmd_addr_end #define pmd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif /* * When walking page tables, we usually want to skip any p?d_none entries; * and any p?d_bad entries - reporting the error before resetting to none. * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *); #else #define p4d_clear_bad(p4d) do { } while (0) #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *); #else #define pud_clear_bad(p4d) do { } while (0) #endif void pmd_clear_bad(pmd_t *); static inline int pgd_none_or_clear_bad(pgd_t *pgd) { if (pgd_none(*pgd)) return 1; if (unlikely(pgd_bad(*pgd))) { pgd_clear_bad(pgd); return 1; } return 0; } static inline int p4d_none_or_clear_bad(p4d_t *p4d) { if (p4d_none(*p4d)) return 1; if (unlikely(p4d_bad(*p4d))) { p4d_clear_bad(p4d); return 1; } return 0; } static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) return 1; if (unlikely(pud_bad(*pud))) { pud_clear_bad(pud); return 1; } return 0; } static inline int pmd_none_or_clear_bad(pmd_t *pmd) { if (pmd_none(*pmd)) return 1; if (unlikely(pmd_bad(*pmd))) { pmd_clear_bad(pmd); return 1; } return 0; } static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* * Get the current pte state, but zero it out to make it * non-present, preventing the hardware from asynchronously * updating it. */ return ptep_get_and_clear(vma->vm_mm, addr, ptep); } static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { /* * The pte is non-present, so there's no hardware state to * preserve. */ set_pte_at(vma->vm_mm, addr, ptep, pte); } #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION /* * Start a pte protection read-modify-write transaction, which * protects against asynchronous hardware modifications to the pte. * The intention is not to prevent the hardware from making pte * updates, but to prevent any updates it may make from being lost. * * This does not protect against other software modifications of the * pte; the appropriate pte lock must be held over the transation. * * Note that this interface is intended to be batchable, meaning that * ptep_modify_prot_commit may not actually update the pte, but merely * queue the update to be done at some later time. The update must be * actually committed before the pte lock is released, however. */ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return __ptep_modify_prot_start(vma, addr, ptep); } /* * Commit an update to a pte, leaving any hardware-controlled bits in * the PTE unmodified. */ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { __ptep_modify_prot_commit(vma, addr, ptep, pte); } #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ #endif /* CONFIG_MMU */ /* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. */ #ifndef pgprot_nx #define pgprot_nx(prot) (prot) #endif #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif #ifndef pgprot_writecombine #define pgprot_writecombine pgprot_noncached #endif #ifndef pgprot_writethrough #define pgprot_writethrough pgprot_noncached #endif #ifndef pgprot_device #define pgprot_device pgprot_noncached #endif #ifndef pgprot_mhp #define pgprot_mhp(prot) (prot) #endif #ifdef CONFIG_MMU #ifndef pgprot_modify #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) newprot = pgprot_noncached(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) newprot = pgprot_writecombine(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) newprot = pgprot_device(newprot); return newprot; } #endif #endif /* CONFIG_MMU */ #ifndef pgprot_encrypted #define pgprot_encrypted(prot) (prot) #endif #ifndef pgprot_decrypted #define pgprot_decrypted(prot) (prot) #endif /* * A facility to provide lazy MMU batching. This allows PTE updates and * page invalidations to be delayed until a call to leave lazy MMU mode * is issued. Some architectures may benefit from doing this, and it is * beneficial for both shadow and direct mode hypervisors, which may batch * the PTE updates which happen during this window. Note that using this * interface requires that read hazards be removed from the code. A read * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be * up to date. This mode can only be entered and left under the protection of * the page table locks for all page tables which may be modified. In the UP * case, this is required so that preemption is disabled, and in the SMP case, * it must synchronize the delayed page table writes properly on other CPUs. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE #define arch_enter_lazy_mmu_mode() do {} while (0) #define arch_leave_lazy_mmu_mode() do {} while (0) #define arch_flush_lazy_mmu_mode() do {} while (0) #endif /* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for * paravirtualized guests. By convention, only one of the batched * update (lazy) modes (CPU, MMU) should be active at any given time, * entry should never be nested, and entry and exits should always be * paired. This is for sanity of maintaining and reasoning about the * kernel code. In this case, the exit (end of the context switch) is * in architecture-specific code, and so doesn't need a generic * definition. */ #ifndef __HAVE_ARCH_START_CONTEXT_SWITCH #define arch_start_context_switch(prev) do {} while (0) #endif #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ static inline int pte_soft_dirty(pte_t pte) { return 0; } static inline int pmd_soft_dirty(pmd_t pmd) { return 0; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte; } static inline int pte_swp_soft_dirty(pte_t pte) { return 0; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #ifndef __HAVE_PFNMAP_TRACKING /* * Interfaces that can be used by architecture code to keep track of * memory type of pfn mappings specified by the remap_pfn_range, * vmf_insert_pfn. */ /* * track_pfn_remap is called when a _new_ pfn mapping is being established * by remap_pfn_range() for physical range indicated by pfn and size. */ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size) { return 0; } /* * track_pfn_insert is called when a _new_ single pfn is established * by vmf_insert_pfn(). */ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) { } /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). */ static inline int track_pfn_copy(struct vm_area_struct *vma) { return 0; } /* * untrack_pfn is called while unmapping a pfnmap for a region. * untrack can be called for a specific region indicated by pfn and size or * can be for the entire vma (in which case pfn, size are zero). */ static inline void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { } /* * untrack_pfn_moved is called while mremapping a pfnmap for a new region. */ static inline void untrack_pfn_moved(struct vm_area_struct *vma) { } #else extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); extern void untrack_pfn_moved(struct vm_area_struct *vma); #endif #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; unsigned long offset_from_zero_pfn = pfn - zero_pfn; return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); } #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) #else static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; return pfn == zero_pfn; } static inline unsigned long my_zero_pfn(unsigned long addr) { extern unsigned long zero_pfn; return zero_pfn; } #endif #ifdef CONFIG_MMU #ifndef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return 0; } #ifndef pmd_write static inline int pmd_write(pmd_t pmd) { BUG(); return 0; } #endif /* pmd_write */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef pud_write static inline int pud_write(pud_t pud) { BUG(); return 0; } #endif /* pud_write */ #if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { return 0; } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) static inline int pud_trans_huge(pud_t pud) { return 0; } #endif /* See pmd_none_or_trans_huge_or_clear_bad for discussion. */ static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) { pud_t pudval = READ_ONCE(*pud); if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) return 1; if (unlikely(pud_bad(pudval))) { pud_clear_bad(pud); return 1; } return 0; } /* See pmd_trans_unstable for discussion. */ static inline int pud_trans_unstable(pud_t *pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) return pud_none_or_trans_huge_or_dev_or_clear_bad(pud); #else return 0; #endif } #ifndef pmd_read_atomic static inline pmd_t pmd_read_atomic(pmd_t *pmdp) { /* * Depend on compiler for an atomic pmd read. NOTE: this is * only going to work, if the pmdval_t isn't larger than * an unsigned long. */ return *pmdp; } #endif #ifndef arch_needs_pgtable_deposit #define arch_needs_pgtable_deposit() (false) #endif /* * This function is meant to be used by sites walking pagetables with * the mmap_lock held in read mode to protect against MADV_DONTNEED and * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd * into a null pmd and the transhuge page fault can convert a null pmd * into an hugepmd or into a regular pmd (if the hugepage allocation * fails). While holding the mmap_lock in read mode the pmd becomes * stable and stops changing under us only if it's not null and not a * transhuge pmd. When those races occurs and this function makes a * difference vs the standard pmd_none_or_clear_bad, the result is * undefined so behaving like if the pmd was none is safe (because it * can return none anyway). The compiler level barrier() is critically * important to compute the two checks atomically on the same pmdval. * * For 32bit kernels with a 64bit large pmd_t this automatically takes * care of reading the pmd atomically to avoid SMP race conditions * against pmd_populate() when the mmap_lock is hold for reading by the * caller (a special atomic read not done by "gcc" as in the generic * version above, is also needed when THP is disabled because the page * fault can populate the pmd from under us). */ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) { pmd_t pmdval = pmd_read_atomic(pmd); /* * The barrier will stabilize the pmdval in a register or on * the stack so that it will stop changing under the code. * * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, * pmd_read_atomic is allowed to return a not atomic pmdval * (for example pointing to an hugepage that has never been * mapped in the pmd). The below checks will only care about * the low part of the pmd with 32bit PAE x86 anyway, with the * exception of pmd_none(). So the important thing is that if * the low part of the pmd is found null, the high part will * be also null or the pmd_none() check below would be * confused. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE barrier(); #endif /* * !pmd_present() checks for pmd migration entries * * The complete check uses is_pmd_migration_entry() in linux/swapops.h * But using that requires moving current function and pmd_trans_unstable() * to linux/swapops.h to resovle dependency, which is too much code move. * * !pmd_present() is equivalent to is_pmd_migration_entry() currently, * because !pmd_present() pages can only be under migration not swapped * out. * * pmd_none() is preseved for future condition checks on pmd migration * entries and not confusing with this function name, although it is * redundant with !pmd_present(). */ if (pmd_none(pmdval) || pmd_trans_huge(pmdval) || (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval))) return 1; if (unlikely(pmd_bad(pmdval))) { pmd_clear_bad(pmd); return 1; } return 0; } /* * This is a noop if Transparent Hugepage Support is not built into * the kernel. Otherwise it is equivalent to * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in * places that already verified the pmd is not none and they want to * walk ptes while holding the mmap sem in read mode (write mode don't * need this). If THP is not enabled, the pmd can't go away under the * code even if MADV_DONTNEED runs, but if THP is enabled we need to * run a pmd_trans_unstable before walking the ptes after * split_huge_pmd returns (because it may have run when the pmd become * null, but then a page fault can map in a THP and not a regular page). */ static inline int pmd_trans_unstable(pmd_t *pmd) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return pmd_none_or_trans_huge_or_clear_bad(pmd); #else return 0; #endif } #ifndef CONFIG_NUMA_BALANCING /* * Technically a PTE can be PROTNONE even when not doing NUMA balancing but * the only case the kernel cares is for NUMA balancing and is only ever set * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked * _PAGE_PROTNONE so by default, implement the helper as "always no". It * is the responsibility of the caller to distinguish between PROT_NONE * protections and NUMA hinting fault protections. */ static inline int pte_protnone(pte_t pte) { return 0; } static inline int pmd_protnone(pmd_t pmd) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); int p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int p4d_clear_huge(p4d_t *p4d) { return 0; } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int p4d_clear_huge(p4d_t *p4d) { return 0; } static inline int pud_clear_huge(pud_t *pud) { return 0; } static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) { return 0; } static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in * THP regime. Stock flush_tlb_range() typically has optimization to nuke the * entire TLB if flush span is greater than a threshold, which will * likely be true for a single huge page. Thus a single THP flush will * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #else #define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() #define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() #endif #endif struct file; int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot); #ifndef CONFIG_X86_ESPFIX64 static inline void init_espfix_bsp(void) { } #endif extern void __init pgtable_cache_init(void); #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { return true; } static inline bool arch_has_pfn_modify_check(void) { return false; } #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ /* * Architecture PAGE_KERNEL_* fallbacks * * Some architectures don't define certain PAGE_KERNEL_* flags. This is either * because they really don't support them, or the port needs to be updated to * reflect the required functionality. Below are a set of relatively safe * fallbacks, as best effort, which we can count on in lieu of the architectures * not defining them on their own yet. */ #ifndef PAGE_KERNEL_RO # define PAGE_KERNEL_RO PAGE_KERNEL #endif #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif /* * Page Table Modification bits for pgtbl_mod_mask. * * These are used by the p?d_alloc_track*() set of functions an in the generic * vmalloc/ioremap code to track at which page-table levels entries have been * modified. Based on that the code can better decide when vmalloc and ioremap * mapping changes need to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 #define __PGTBL_PUD_MODIFIED 2 #define __PGTBL_PMD_MODIFIED 3 #define __PGTBL_PTE_MODIFIED 4 #define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) #define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) #define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) #define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) #define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) /* Page-Table Modification Mask */ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) #ifdef CONFIG_PHYS_ADDR_T_64BIT /* * ZSMALLOC needs to know the highest PFN on 32-bit architectures * with physical address space extension, but falls back to * BITS_PER_LONG otherwise. */ #error Missing MAX_POSSIBLE_PHYSMEM_BITS definition #else #define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif #endif #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 #else #define has_transparent_hugepage() 0 #endif #endif /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. */ #ifndef mm_p4d_folded #define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) #endif #ifndef mm_pud_folded #define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) #endif #ifndef mm_pmd_folded #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif #ifndef p4d_offset_lockless #define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) #endif #ifndef pud_offset_lockless #define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) #endif #ifndef pmd_offset_lockless #define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) #endif /* * p?d_leaf() - true if this entry is a final mapping to a physical address. * This differs from p?d_huge() by the fact that they are always available (if * the architecture supports large pages at the appropriate level) even * if CONFIG_HUGETLB_PAGE is not defined. * Only meaningful when called on a valid entry. */ #ifndef pgd_leaf #define pgd_leaf(x) 0 #endif #ifndef p4d_leaf #define p4d_leaf(x) 0 #endif #ifndef pud_leaf #define pud_leaf(x) 0 #endif #ifndef pmd_leaf #define pmd_leaf(x) 0 #endif #endif /* _LINUX_PGTABLE_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 // SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c Extended attribute handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com> Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fsnotify.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/posix_acl_xattr.h> #include <linux/uaccess.h> static const char * strcmp_prefix(const char *a, const char *a_prefix) { while (*a_prefix && *a == *a_prefix) { a++; a_prefix++; } return *a_prefix ? NULL : a; } /* * In order to implement different sets of xattr operations for each xattr * prefix, a filesystem should create a null-terminated array of struct * xattr_handler (one for each prefix) and hang a pointer to it off of the * s_xattr field of the superblock. */ #define for_each_xattr_handler(handlers, handler) \ if (handlers) \ for ((handler) = *(handlers)++; \ (handler) != NULL; \ (handler) = *(handlers)++) /* * Find the xattr_handler with the matching prefix. */ static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return ERR_PTR(-EIO); return ERR_PTR(-EOPNOTSUPP); } for_each_xattr_handler(handlers, handler) { const char *n; n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { if (!handler->prefix ^ !*n) { if (*n) continue; return ERR_PTR(-EINVAL); } *name = n; return handler; } } return ERR_PTR(-EOPNOTSUPP); } /* * Check permissions for extended attribute access. This is a bit complicated * because different namespaces have very different rules. */ static int xattr_permission(struct inode *inode, const char *name, int mask) { /* * We can never set or remove an extended attribute on a read-only * filesystem or on an immutable / append-only inode. */ if (mask & MAY_WRITE) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; /* * Updating an xattr will likely cause i_uid and i_gid * to be writen back improperly if their true value is * unknown to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EPERM; } /* * No restriction for security.* and system.* from the VFS. Decision * on these is left to the underlying filesystem / security module. */ if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return 0; /* * The trusted.* namespace can only be accessed by privileged users. */ if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { if (!capable(CAP_SYS_ADMIN)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; return 0; } /* * In the user.* namespace, only regular files and directories can have * extended attributes. For sticky directories, only the owner and * privileged users can write attributes. */ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && !inode_owner_or_capable(inode)) return -EPERM; } return inode_permission(inode, mask); } /* * Look for any handler that deals with the specified namespace. */ int xattr_supported_namespace(struct inode *inode, const char *prefix) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; size_t preflen; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return -EIO; return -EOPNOTSUPP; } preflen = strlen(prefix); for_each_xattr_handler(handlers, handler) { if (!strncmp(xattr_prefix(handler), prefix, preflen)) return 0; } return -EOPNOTSUPP; } EXPORT_SYMBOL(xattr_supported_namespace); int __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ return handler->set(handler, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); /** * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * * @dentry - object to perform setxattr on * @name - xattr name to set * @value - value to set @name to * @size - size of @value * @flags - flags to pass into filesystem operations * * returns the result of the internal setxattr or setsecurity operations. * * This function requires the caller to lock the inode's i_mutex before it * is executed. It also assumes that the caller will make the appropriate * permission checks. */ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { error = __vfs_setxattr(dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, size, flags); } } else { if (unlikely(is_bad_inode(inode))) return -EIO; } if (error == -EAGAIN) { error = -EOPNOTSUPP; if (issec) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; error = security_inode_setsecurity(inode, suffix, value, size, flags); if (!error) fsnotify_xattr(dentry); } } return error; } /** * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_setxattr_locked(struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_WRITE); if (error) return error; error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: return error; } EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int vfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t xattr_getsecurity(struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { len = security_inode_getsecurity(inode, name, &buffer, false); goto out_noalloc; } len = security_inode_getsecurity(inode, name, &buffer, true); if (len < 0) return len; if (size < len) { len = -ERANGE; goto out; } memcpy(value, buffer, len); out: kfree(buffer); out_noalloc: return len; } /* * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr * * Allocate memory, if not already allocated, or re-allocate correct size, * before retrieving the extended attribute. * * Returns the result of alloc, if failed, or the getxattr operation. */ ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; error = xattr_permission(inode, name, MAY_READ); if (error) return error; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; error = handler->get(handler, dentry, inode, name, NULL, 0); if (error < 0) return error; if (!value || (error > xattr_size)) { value = krealloc(*xattr_value, error + 1, flags); if (!value) return -ENOMEM; memset(value, 0, error + 1); } error = handler->get(handler, dentry, inode, name, value, error); *xattr_value = value; return error; } ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size); } EXPORT_SYMBOL(__vfs_getxattr); ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_READ); if (error) return error; error = security_inode_getxattr(dentry, name); if (error) return error; if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; int ret = xattr_getsecurity(inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ if (ret == -EOPNOTSUPP) goto nolsm; return ret; } nolsm: return __vfs_getxattr(dentry, inode, name, value, size); } EXPORT_SYMBOL_GPL(vfs_getxattr); ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { struct inode *inode = d_inode(dentry); ssize_t error; error = security_inode_listxattr(dentry); if (error) return error; if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); if (size && error > size) error = -ERANGE; } return error; } EXPORT_SYMBOL_GPL(vfs_listxattr); int __vfs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; return handler->set(handler, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); /** * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_removexattr_locked(struct dentry *dentry, const char *name, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_WRITE); if (error) return error; error = security_inode_removexattr(dentry, name); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_removexattr(dentry, name); if (!error) { fsnotify_xattr(dentry); evm_inode_post_removexattr(dentry, name); } out: return error; } EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int vfs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); /* * Extended attribute SET operations */ static long setxattr(struct dentry *d, const char __user *name, const void __user *value, size_t size, int flags) { int error; void *kvalue = NULL; char kname[XATTR_NAME_MAX + 1]; if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; if (size) { if (size > XATTR_SIZE_MAX) return -E2BIG; kvalue = kvmalloc(size, GFP_KERNEL); if (!kvalue) return -ENOMEM; if (copy_from_user(kvalue, value, size)) { error = -EFAULT; goto out; } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { error = cap_convert_nscap(d, &kvalue, size); if (error < 0) goto out; size = error; } } error = vfs_setxattr(d, kname, kvalue, size, flags); out: kvfree(kvalue); return error; } static int path_setxattr(const char __user *pathname, const char __user *name, const void __user *value, size_t size, int flags, unsigned int lookup_flags) { struct path path; int error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = setxattr(path.dentry, name, value, size, flags); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE5(setxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW); } SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattr(pathname, name, value, size, flags, 0); } SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { struct fd f = fdget(fd); int error = -EBADF; if (!f.file) return error; audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { error = setxattr(f.file->f_path.dentry, name, value, size, flags); mnt_drop_write_file(f.file); } fdput(f); return error; } /* * Extended attribute GET operations */ static ssize_t getxattr(struct dentry *d, const char __user *name, void __user *value, size_t size) { ssize_t error; void *kvalue = NULL; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; if (size) { if (size > XATTR_SIZE_MAX) size = XATTR_SIZE_MAX; kvalue = kvzalloc(size, GFP_KERNEL); if (!kvalue) return -ENOMEM; } error = vfs_getxattr(d, kname, kvalue, size); if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_to_user(kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(kvalue); return error; } static ssize_t path_getxattr(const char __user *pathname, const char __user *name, void __user *value, size_t size, unsigned int lookup_flags) { struct path path; ssize_t error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = getxattr(path.dentry, name, value, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(getxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW); } SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattr(pathname, name, value, size, 0); } SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { struct fd f = fdget(fd); ssize_t error = -EBADF; if (!f.file) return error; audit_file(f.file); error = getxattr(f.file->f_path.dentry, name, value, size); fdput(f); return error; } /* * Extended attribute LIST operations */ static ssize_t listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kvmalloc(size, GFP_KERNEL); if (!klist) return -ENOMEM; } error = vfs_listxattr(d, klist, size); if (error > 0) { if (size && copy_to_user(list, klist, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { /* The file system tried to returned a list bigger than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(klist); return error; } static ssize_t path_listxattr(const char __user *pathname, char __user *list, size_t size, unsigned int lookup_flags) { struct path path; ssize_t error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = listxattr(path.dentry, list, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattr(pathname, list, size, LOOKUP_FOLLOW); } SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattr(pathname, list, size, 0); } SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { struct fd f = fdget(fd); ssize_t error = -EBADF; if (!f.file) return error; audit_file(f.file); error = listxattr(f.file->f_path.dentry, list, size); fdput(f); return error; } /* * Extended attribute REMOVE operations */ static long removexattr(struct dentry *d, const char __user *name) { int error; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; return vfs_removexattr(d, kname); } static int path_removexattr(const char __user *pathname, const char __user *name, unsigned int lookup_flags) { struct path path; int error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = removexattr(path.dentry, name); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(removexattr, const char __user *, pathname, const char __user *, name) { return path_removexattr(pathname, name, LOOKUP_FOLLOW); } SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, const char __user *, name) { return path_removexattr(pathname, name, 0); } SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { struct fd f = fdget(fd); int error = -EBADF; if (!f.file) return error; audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { error = removexattr(f.file->f_path.dentry, name); mnt_drop_write_file(f.file); } fdput(f); return error; } /* * Combine the results of the list() operation from every xattr_handler in the * list. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr; unsigned int size = 0; if (!buffer) { for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; size += strlen(handler->name) + 1; } } else { char *buf = buffer; size_t len; for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; len = strlen(handler->name); if (len + 1 > buffer_size) return -ERANGE; memcpy(buf, handler->name, len + 1); buf += len + 1; buffer_size -= len + 1; } size = buf - buffer; } return size; } EXPORT_SYMBOL(generic_listxattr); /** * xattr_full_name - Compute full attribute name from suffix * * @handler: handler of the xattr_handler operation * @name: name passed to the xattr_handler operation * * The get and set xattr handler operations are called with the remainder of * the attribute name after skipping the handler's prefix: for example, "foo" * is passed to the get operation of a handler with prefix "user." to get * attribute "user.foo". The full name is still "there" in the name though. * * Note: the list xattr handler operation when called from the vfs is passed a * NULL name; some file systems use this operation internally, with varying * semantics. */ const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } EXPORT_SYMBOL(xattr_full_name); /* * Allocate new xattr and copy in the value; but leave the name to callers. */ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) { struct simple_xattr *new_xattr; size_t len; /* wrap around? */ len = sizeof(*new_xattr) + size; if (len < sizeof(*new_xattr)) return NULL; new_xattr = kvmalloc(len, GFP_KERNEL); if (!new_xattr) return NULL; new_xattr->size = size; memcpy(new_xattr->value, value, size); return new_xattr; } /* * xattr GET operation for in-memory/pseudo filesystems */ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size) { struct simple_xattr *xattr; int ret = -ENODATA; spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { if (strcmp(name, xattr->name)) continue; ret = xattr->size; if (buffer) { if (size < xattr->size) ret = -ERANGE; else memcpy(buffer, xattr->value, xattr->size); } break; } spin_unlock(&xattrs->lock); return ret; } /** * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems * @xattrs: target simple_xattr list * @name: name of the extended attribute * @value: value of the xattr. If %NULL, will remove the attribute. * @size: size of the new xattr * @flags: %XATTR_{CREATE|REPLACE} * @removed_size: returns size of the removed xattr, -1 if none removed * * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; * otherwise, fails with -ENODATA. * * Returns 0 on success, -errno on failure. */ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size) { struct simple_xattr *xattr; struct simple_xattr *new_xattr = NULL; int err = 0; if (removed_size) *removed_size = -1; /* value == NULL means remove */ if (value) { new_xattr = simple_xattr_alloc(value, size); if (!new_xattr) return -ENOMEM; new_xattr->name = kstrdup(name, GFP_KERNEL); if (!new_xattr->name) { kvfree(new_xattr); return -ENOMEM; } } spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { if (!strcmp(name, xattr->name)) { if (flags & XATTR_CREATE) { xattr = new_xattr; err = -EEXIST; } else if (new_xattr) { list_replace(&xattr->list, &new_xattr->list); if (removed_size) *removed_size = xattr->size; } else { list_del(&xattr->list); if (removed_size) *removed_size = xattr->size; } goto out; } } if (flags & XATTR_REPLACE) { xattr = new_xattr; err = -ENODATA; } else { list_add(&new_xattr->list, &xattrs->head); xattr = NULL; } out: spin_unlock(&xattrs->lock); if (xattr) { kfree(xattr->name); kvfree(xattr); } return err; } static bool xattr_is_trusted(const char *name) { return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } static int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) { size_t len = strlen(name) + 1; if (*buffer) { if (*remaining_size < len) return -ERANGE; memcpy(*buffer, name, len); *buffer += len; } *remaining_size -= len; return 0; } /* * xattr LIST operation for in-memory/pseudo filesystems */ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (IS_POSIXACL(inode)) { if (inode->i_acl) { err = xattr_list_one(&buffer, &remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(&buffer, &remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } } #endif spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; } spin_unlock(&xattrs->lock); return err ? err : size - remaining_size; } /* * Adds an extended attribute to the list */ void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr) { spin_lock(&xattrs->lock); list_add(&new_xattr->list, &xattrs->head); spin_unlock(&xattrs->lock); }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 // SPDX-License-Identifier: GPL-2.0 /* File: fs/ext4/acl.h (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #include <linux/posix_acl_xattr.h> #define EXT4_ACL_VERSION 0x0001 typedef struct { __le16 e_tag; __le16 e_perm; __le32 e_id; } ext4_acl_entry; typedef struct { __le16 e_tag; __le16 e_perm; } ext4_acl_entry_short; typedef struct { __le32 a_version; } ext4_acl_header; static inline size_t ext4_acl_size(int count) { if (count <= 4) { return sizeof(ext4_acl_header) + count * sizeof(ext4_acl_entry_short); } else { return sizeof(ext4_acl_header) + 4 * sizeof(ext4_acl_entry_short) + (count - 4) * sizeof(ext4_acl_entry); } } static inline int ext4_acl_count(size_t size) { ssize_t s; size -= sizeof(ext4_acl_header); s = size - 4 * sizeof(ext4_acl_entry_short); if (s < 0) { if (size % sizeof(ext4_acl_entry_short)) return -1; return size / sizeof(ext4_acl_entry_short); } else { if (s % sizeof(ext4_acl_entry)) return -1; return s / sizeof(ext4_acl_entry) + 4; } } #ifdef CONFIG_EXT4_FS_POSIX_ACL /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type); int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); #else /* CONFIG_EXT4_FS_POSIX_ACL */ #include <linux/sched.h> #define ext4_get_acl NULL #define ext4_set_acl NULL static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_GENERIC_NETLINK_H #define __NET_GENERIC_NETLINK_H #include <linux/genetlink.h> #include <net/netlink.h> #include <net/net_namespace.h> #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family */ struct genl_multicast_group { char name[GENL_NAMSIZ]; }; struct genl_ops; struct genl_info; /** * struct genl_family - generic netlink family * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version * @maxattr: maximum number of attributes supported * @policy: netlink policy * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them * @parallel_ops: operations can be called in parallel and aren't * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family */ struct genl_family { int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; unsigned int mcgrp_offset; /* private */ u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; u8 n_small_ops; u8 n_mcgrps; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; const struct genl_small_ops *small_ops; const struct genl_multicast_group *mcgrps; struct module *module; }; /** * struct genl_info - receiving information * @snd_seq: sending sequence number * @snd_portid: netlink portid of sender * @nlhdr: netlink message header * @genlhdr: generic netlink message header * @userhdr: user specific header * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers * @extack: extended ACK report struct */ struct genl_info { u32 snd_seq; u32 snd_portid; struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; void * userhdr; struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; struct netlink_ext_ack *extack; }; static inline struct net *genl_info_net(struct genl_info *info) { return read_pnet(&info->_net); } static inline void genl_info_net_set(struct genl_info *info, struct net *net) { write_pnet(&info->_net, net); } #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), GENL_DONT_VALIDATE_DUMP_STRICT = BIT(2), }; /** * struct genl_small_ops - generic netlink operations (small version) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @dumpit: callback for dumpers * * This is a cut-down version of struct genl_ops for users who don't need * most of the ancillary infra and want to save space. */ struct genl_small_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags * @maxattr: maximum number of attributes supported * @policy: netlink policy (takes precedence over family policy) * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps */ struct genl_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); const struct nla_policy *policy; unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage * @ops: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { const struct genl_family *family; struct genl_ops op; struct nlattr **attrs; }; static inline const struct genl_dumpit_info * genl_dumpit_info(struct netlink_callback *cb) { return cb->data; } int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd); /** * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() * * Returns pointer to netlink header. */ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) { return (struct nlmsghdr *)((char *)user_hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_parse_deprecated - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * genlmsg_parse - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * genl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @user_hdr: user header as returned from genlmsg_put() * * Cf. nl_dump_check_consistent(), this just provides a wrapper to make it * simpler to use with generic netlink. */ static inline void genl_dump_check_consistent(struct netlink_callback *cb, void *user_hdr) { nl_dump_check_consistent(cb, genlmsg_nlhdr(user_hdr)); } /** * genlmsg_put_reply - Add generic netlink header to a reply message * @skb: socket buffer holding the message * @info: receiver info * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, const struct genl_family *family, int flags, u8 cmd) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, flags, cmd); } /** * genlmsg_end - Finalize a generic netlink message * @skb: socket buffer the message is stored in * @hdr: user specific header */ static inline void genlmsg_end(struct sk_buff *skb, void *hdr) { nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_cancel - Cancel construction of a generic netlink message * @skb: socket buffer the message is stored in * @hdr: generic netlink message header */ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { if (hdr) nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_multicast_netns - multicast a netlink message to a specific netns * @family: the generic netlink family * @net: the net namespace * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return nlmsg_multicast(net->genl_sock, skb, portid, group, flags); } /** * genlmsg_multicast - multicast a netlink message to the default netns * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return genlmsg_multicast_netns(family, &init_net, skb, portid, group, flags); } /** * genlmsg_multicast_allns - multicast a netlink message to all net namespaces * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags); /** * genlmsg_unicast - unicast a netlink message * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 portid) { return nlmsg_unicast(net->genl_sock, skb, portid); } /** * genlmsg_reply - reply to a request * @skb: netlink message to be sent back * @info: receiver information */ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) { return genlmsg_unicast(genl_info_net(info), skb, info->snd_portid); } /** * gennlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) { return ((unsigned char *) gnlh + GENL_HDRLEN); } /** * genlmsg_len - length of message payload * @gnlh: genetlink message header */ static inline int genlmsg_len(const struct genlmsghdr *gnlh) { struct nlmsghdr *nlh = (struct nlmsghdr *)((unsigned char *)gnlh - NLMSG_HDRLEN); return (nlh->nlmsg_len - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_msg_size - length of genetlink message not including padding * @payload: length of message payload */ static inline int genlmsg_msg_size(int payload) { return GENL_HDRLEN + payload; } /** * genlmsg_total_size - length of genetlink message including padding * @payload: length of message payload */ static inline int genlmsg_total_size(int payload) { return NLMSG_ALIGN(genlmsg_msg_size(payload)); } /** * genlmsg_new - Allocate a new generic netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. */ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) { return nlmsg_new(genlmsg_total_size(payload), flags); } /** * genl_set_err - report error to genetlink broadcast listeners * @family: the generic netlink family * @net: the network namespace to report the error to * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * (this is the offset of the multicast group in the groups array) * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ static inline int genl_set_err(const struct genl_family *family, struct net *net, u32 portid, u32 group, int code) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_set_err(net->genl_sock, portid, group, code); } static inline int genl_has_listeners(const struct genl_family *family, struct net *net, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_has_listeners(net->genl_sock, group); } #endif /* __NET_GENERIC_NETLINK_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_64_H #define _ASM_X86_UACCESS_64_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/lockdep.h> #include <linux/kasan-checks.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> /* * Copy To/From Userspace */ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long copy_user_enhanced_fast_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_unrolled(void *to, const void *from, unsigned len); static __always_inline __must_check unsigned long copy_user_generic(void *to, const void *from, unsigned len) { unsigned ret; /* * If CPU has ERMS feature, use copy_user_enhanced_fast_string. * Otherwise, if CPU has rep_good feature, use copy_user_generic_string. * Otherwise, use copy_user_generic_unrolled. */ alternative_call_2(copy_user_generic_unrolled, copy_user_generic_string, X86_FEATURE_REP_GOOD, copy_user_enhanced_fast_string, X86_FEATURE_ERMS, ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from), "=d" (len)), "1" (to), "2" (from), "3" (len) : "memory", "rcx", "r8", "r9", "r10", "r11"); return ret; } static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); } static __always_inline __must_check unsigned long raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { return copy_user_generic((__force void *)dst, src, size); } static __always_inline __must_check unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size) { return copy_user_generic((__force void *)dst, (__force void *)src, size); } extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size); extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len); static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_nocache(dst, src, size, 0); } static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } #endif /* _ASM_X86_UACCESS_64_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2018 Christoph Hellwig. * * DMA operations that map physical memory directly without using an IOMMU. */ #ifndef _KERNEL_DMA_DIRECT_H #define _KERNEL_DMA_DIRECT_H #include <linux/dma-direct.h> int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); bool dma_direct_can_mmap(struct device *dev); int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); size_t dma_direct_max_mapping_size(struct device *dev); #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_SWIOTLB) void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir); #else static inline void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { } #endif #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \ defined(CONFIG_SWIOTLB) void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs); void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir); #else static inline void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs) { } static inline void dma_direct_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { } #endif static inline void dma_direct_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { phys_addr_t paddr = dma_to_phys(dev, addr); if (unlikely(is_swiotlb_buffer(paddr))) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(paddr, size, dir); } static inline void dma_direct_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { phys_addr_t paddr = dma_to_phys(dev, addr); if (!dev_is_dma_coherent(dev)) { arch_sync_dma_for_cpu(paddr, size, dir); arch_sync_dma_for_cpu_all(); } if (unlikely(is_swiotlb_buffer(paddr))) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); if (dir == DMA_FROM_DEVICE) arch_dma_mark_clean(paddr, size); } static inline dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); if (unlikely(swiotlb_force == SWIOTLB_FORCE)) return swiotlb_map(dev, phys, size, dir, attrs); if (unlikely(!dma_capable(dev, dma_addr, size, true))) { if (swiotlb_force != SWIOTLB_NO_FORCE) return swiotlb_map(dev, phys, size, dir, attrs); dev_WARN_ONCE(dev, 1, "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); return DMA_MAPPING_ERROR; } if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) arch_sync_dma_for_device(phys, size, dir); return dma_addr; } static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { phys_addr_t phys = dma_to_phys(dev, addr); if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(phys))) swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs); } #endif /* _KERNEL_DMA_DIRECT_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr ) __field( void *, location ) __field( unsigned short, protocol ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->protocol = ntohs(skb->protocol); ), TP_printk("skbaddr=%p protocol=%u location=%p", __entry->skbaddr, __entry->protocol, __entry->location) ); TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) ), TP_fast_assign( __entry->skbaddr = skb; ), TP_printk("skbaddr=%p", __entry->skbaddr) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H #include <linux/threads.h> #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count) {} static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} static inline void paravirt_release_pte(unsigned long pfn) {} static inline void paravirt_release_pmd(unsigned long pfn) {} static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif /* * Flags to use when allocating a user page table page. */ extern gfp_t __userpte_alloc_gfp; #ifdef CONFIG_PAGE_TABLE_ISOLATION /* * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 * in a pointer to swap between the two 4k halves. */ #define PGD_ALLOCATION_ORDER 1 #else #define PGD_ALLOCATION_ORDER 0 #endif /* * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); extern pgtable_t pte_alloc_one(struct mm_struct *); extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, unsigned long address) { ___pte_free_tlb(tlb, pte); } static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate_kernel_safe(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { unsigned long pfn = page_to_pfn(pte); paravirt_alloc_pte(mm, pfn); set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } #define pmd_pgtable(pmd) pmd_page(pmd) #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { ___pmd_free_tlb(tlb, pmd); } #ifdef CONFIG_X86_PAE extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); #else /* !CONFIG_X86_PAE */ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); } #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { ___pud_free_tlb(tlb, pud); } #if CONFIG_PGTABLE_LEVELS > 4 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; return (p4d_t *)get_zeroed_page(gfp); } static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { if (!pgtable_l5_enabled()) return; BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); free_page((unsigned long)p4d); } extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { if (pgtable_l5_enabled()) ___p4d_free_tlb(tlb, p4d); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_H */
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old, prev = old; \ CODE \ old.lock_count = cmpxchg64_relaxed(&lockref->lock_count, \ old.lock_count, \ new.lock_count); \ if (likely(old.lock_count == prev.lock_count)) { \ SUCCESS; \ } \ if (!--retry) \ break; \ cpu_relax(); \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ int lockref_get_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_not_zero - Decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count would become zero */ int lockref_put_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count--; if (old.count <= 1) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 1) { lockref->count--; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_put_not_zero); /** * lockref_get_or_lock - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero * and we got the lock instead. */ int lockref_get_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; if (old.count <= 0) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 0) return 0; lockref->count++; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_get_or_lock); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return an error. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ int lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return 0; lockref->count--; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ int lockref_get_not_dead(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count < 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count >= 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead);
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLY__ #include <asm/nospec-branch.h> /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __section(".cpuidle.text") /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern __always_inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : "=rm" (flags) : /* no input */ : "memory"); return flags; } extern inline void native_restore_fl(unsigned long flags); extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ :"g" (flags) :"memory", "cc"); } static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static __always_inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static inline __cpuidle void native_safe_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } #endif #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline unsigned long arch_local_save_flags(void) { return native_save_fl(); } static __always_inline void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); } static __always_inline void arch_local_irq_enable(void) { native_irq_enable(); } /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static inline __cpuidle void halt(void) { native_halt(); } /* * For spinlocks, etc: */ static __always_inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(x) pushfq; popq %rax #endif #define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; #define USERGS_SYSRET32 \ swapgs; \ sysretl #else #define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static __always_inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } #else #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV #else #define SWAPGS swapgs #endif #endif #endif /* !__ASSEMBLY__ */ #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(bitlock); } /* * Return true if it was acquired */ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(bitlock); return 1; } /* * bit-based spin_unlock() */ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Supervisor Mode Access Prevention support * * Copyright (C) 2012 Intel Corporation * Author: H. Peter Anvin <hpa@linux.intel.com> */ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H #include <asm/nops.h> #include <asm/cpufeatures.h> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" #define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ #include <asm/alternative-asm.h> #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #else /* __ASSEMBLY__ */ #include <asm/alternative.h> #ifdef CONFIG_X86_SMAP static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_CLAC, X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_STAC, X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) { unsigned long flags; asm volatile ("# smap_save\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "pushf; pop %0; " __ASM_CLAC "\n\t" "1:" : "=rm" (flags) : : "memory", "cc"); return flags; } static __always_inline void smap_restore(unsigned long flags) { asm volatile ("# smap_restore\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "push %0; popf\n\t" "1:" : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ static inline void clac(void) { } static inline void stac(void) { } static inline unsigned long smap_save(void) { return 0; } static inline void smap_restore(unsigned long flags) { } #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */
1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/bitmap.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) */ #include <linux/buffer_head.h> #include "ext4.h" unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { return numchars * BITS_PER_BYTE - memweight(bitmap, numchars); } int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) { hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi); provided |= (hi << 16); } else calculated &= 0xFFFF; return provided == calculated; } void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh, int sz) { __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16); } int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh) { __u32 hi; __u32 provided, calculated; struct ext4_sb_info *sbi = EXT4_SB(sb); int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; if (!ext4_has_metadata_csum(sb)) return 1; provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) { hi = le16_to_cpu(gdp->bg_block_bitmap_csum_hi); provided |= (hi << 16); } else calculated &= 0xFFFF; if (provided == calculated) return 1; return 0; } void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *gdp, struct buffer_head *bh) { int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8; __u32 csum; struct ext4_sb_info *sbi = EXT4_SB(sb); if (!ext4_has_metadata_csum(sb)) return; csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16); }