| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void update_process_times(int user); extern void xtime_update(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family: read the current time in a multitude of ways, * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones wit * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Returns monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * struct ktime_timestanps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t raw; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the pointer to the * corresponding clocksource * @cycles: System counter value * @cs: Clocksource corresponding to system counter value. Used by * timekeeping code to verify comparibility of two cycle values */ struct system_counterval_t { u64 cycles; struct clocksource *cs; }; /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); #endif |
| 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 | #ifdef CONFIG_PREEMPTIRQ_TRACEPOINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM preemptirq #if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PREEMPTIRQ_H #include <linux/ktime.h> #include <linux/tracepoint.h> #include <linux/string.h> #include <asm/sections.h> DECLARE_EVENT_CLASS(preemptirq_template, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip), TP_STRUCT__entry( __field(s32, caller_offs) __field(s32, parent_offs) ), TP_fast_assign( __entry->caller_offs = (s32)(ip - (unsigned long)_stext); __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext); ), TP_printk("caller=%pS parent=%pS", (void *)((unsigned long)(_stext) + __entry->caller_offs), (void *)((unsigned long)(_stext) + __entry->parent_offs)) ); #ifdef CONFIG_TRACE_IRQFLAGS DEFINE_EVENT(preemptirq_template, irq_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, irq_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #endif #ifdef CONFIG_TRACE_PREEMPT_TOGGLE DEFINE_EVENT(preemptirq_template, preempt_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, preempt_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif #endif /* _TRACE_PREEMPTIRQ_H */ #include <trace/define_trace.h> #else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */ #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif |
| 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 | /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, Inc * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/kthread.h> #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/seq_file.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/time.h> #include <linux/time64.h> #include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> #include <linux/cgroup.h> #include <linux/wait.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* See "Frequency meter" comments, below. */ struct fmeter { int cnt; /* unprocessed events count */ int val; /* most recent output value */ time64_t time; /* clock (secs) when val computed */ spinlock_t lock; /* guards read or write of above */ }; struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ /* * On default hierarchy: * * The user-configured masks can only be changed by writing to * cpuset.cpus and cpuset.mems, and won't be limited by the * parent masks. * * The effective masks is the real masks that apply to the tasks * in the cpuset. They may be changed if the configured masks are * changed or hotplug happens. * * effective_mask == configured_mask & parent's effective_mask, * and if it ends up empty, it will inherit the parent's mask. * * * On legacy hierachy: * * The user-configured masks are always the same with effective masks. */ /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ cpumask_var_t effective_cpus; nodemask_t effective_mems; /* * CPUs allocated to child sub-partitions (default hierarchy only) * - CPUs granted by the parent = effective_cpus U subparts_cpus * - effective_cpus and subparts_cpus are mutually exclusive. * * effective_cpus contains only onlined CPUs, but subparts_cpus * may have offlined ones. */ cpumask_var_t subparts_cpus; /* * This is old Memory Nodes tasks took on. * * - top_cpuset.old_mems_allowed is initialized to mems_allowed. * - A new cpuset's old_mems_allowed is initialized when some * task is moved into it. * - old_mems_allowed is used in cpuset_migrate_mm() when we change * cpuset.mems_allowed and have tasks' nodemask updated, and * then old_mems_allowed is updated to mems_allowed. */ nodemask_t old_mems_allowed; struct fmeter fmeter; /* memory_pressure filter */ /* * Tasks are being attached to this cpuset. Used to prevent * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). */ int attach_in_progress; /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; /* number of CPUs in subparts_cpus */ int nr_subparts_cpus; /* partition root state */ int partition_root_state; /* * Default hierarchy only: * use_parent_ecpus - set if using parent's effective_cpus * child_ecpus_count - # of children with use_parent_ecpus set */ int use_parent_ecpus; int child_ecpus_count; /* * number of SCHED_DEADLINE tasks attached to this cpuset, so that we * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; int nr_migrate_dl_tasks; u64 sum_migrate_dl_bw; }; /* * Partition root states: * * 0 - not a partition root * * 1 - partition root * * -1 - invalid partition root * None of the cpus in cpus_allowed can be put into the parent's * subparts_cpus. In this case, the cpuset is not a real partition * root anymore. However, the CPU_EXCLUSIVE bit will still be set * and the cpuset can be restored back to a partition root if the * parent cpuset can give more CPUs back to this child cpuset. */ #define PRS_DISABLED 0 #define PRS_ENABLED 1 #define PRS_ERROR -1 /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cpuset, css) : NULL; } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) { return css_cs(cs->css.parent); } void inc_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks++; } void dec_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks--; } /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, CS_MEMORY_MIGRATE, CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, } cpuset_flagbits_t; /* convenient tests for these bits */ static inline bool is_cpuset_online(struct cpuset *cs) { return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); } static inline int is_mem_exclusive(const struct cpuset *cs) { return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); } static inline int is_mem_hardwall(const struct cpuset *cs) { return test_bit(CS_MEM_HARDWALL, &cs->flags); } static inline int is_sched_load_balance(const struct cpuset *cs) { return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } static inline int is_memory_migrate(const struct cpuset *cs) { return test_bit(CS_MEMORY_MIGRATE, &cs->flags); } static inline int is_spread_page(const struct cpuset *cs) { return test_bit(CS_SPREAD_PAGE, &cs->flags); } static inline int is_spread_slab(const struct cpuset *cs) { return test_bit(CS_SPREAD_SLAB, &cs->flags); } static inline int is_partition_root(const struct cpuset *cs) { return cs->partition_root_state > 0; } static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), .partition_root_state = PRS_ENABLED, }; /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ #define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ css_for_each_child((pos_css), &(parent_cs)->css) \ if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling * css_rightmost_descendant() to skip subtree. @root_cs is included in the * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this * comment. * * A task must hold both locks to modify cpusets. If a task holds * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it * is the only task able to also acquire callback_lock and be able to * modify cpusets. It can perform various checks on the cpuset structure * first, knowing nothing will change. It can also allocate memory while * just holding cpuset_mutex. While it is performing these checks, various * callback routines can briefly acquire callback_lock to query cpusets. * Once it is ready to make the changes, it takes callback_lock, blocking * everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock * from one of the callbacks into the cpuset code from within * __alloc_pages(). * * If a task is only holding callback_lock, then it has read-only * access to cpusets. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_file_read() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * * Accessing a task's cpuset should be done in accordance with the * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); void cpuset_lock(void) { mutex_lock(&cpuset_mutex); } void cpuset_unlock(void) { mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; /* * CPU / memory hotplug is handled asynchronously. */ static void cpuset_hotplug_workfn(struct work_struct *work); static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. * With v2 behavior, "cpus" and "mems" are always what the users have * requested and won't be changed by hotplug events. Only the effective * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /* * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) { while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* * The top cpuset doesn't have any online cpu as a * consequence of a race between cpuset_hotplug_work * and cpu hotplug notifier. But we know the top * cpuset's effective_cpus is on its way to be * identical to cpu_online_mask. */ cpumask_copy(pmask, cpu_online_mask); return; } } cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); } /* * update task's spread flag if cpuset's page/slab spread flag is set * * Call with callback_lock or cpuset_mutex held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) task_set_spread_page(tsk); else task_clear_spread_page(tsk); if (is_spread_slab(cs)) task_set_spread_slab(tsk); else task_clear_spread_slab(tsk); } /* * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } /** * alloc_cpumasks - allocate three cpumasks for cpuset * @cs: the cpuset that have cpumasks to be allocated. * @tmp: the tmpmasks structure pointer * Return: 0 if successful, -ENOMEM otherwise. * * Only one of the two input arguments should be non-NULL. */ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { cpumask_var_t *pmask1, *pmask2, *pmask3; if (cs) { pmask1 = &cs->cpus_allowed; pmask2 = &cs->effective_cpus; pmask3 = &cs->subparts_cpus; } else { pmask1 = &tmp->new_cpus; pmask2 = &tmp->addmask; pmask3 = &tmp->delmask; } if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) return -ENOMEM; if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) goto free_one; if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) goto free_two; return 0; free_two: free_cpumask_var(*pmask2); free_one: free_cpumask_var(*pmask1); return -ENOMEM; } /** * free_cpumasks - free cpumasks in a tmpmasks structure * @cs: the cpuset that have cpumasks to be free. * @tmp: the tmpmasks structure pointer */ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { if (cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->subparts_cpus); } if (tmp) { free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } } /** * alloc_trial_cpuset - allocate a trial cpuset * @cs: the cpuset that the trial cpuset duplicates */ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) { struct cpuset *trial; trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); if (!trial) return NULL; if (alloc_cpumasks(trial, NULL)) { kfree(trial); return NULL; } cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->effective_cpus, cs->effective_cpus); return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumasks(cs, NULL); kfree(cs); } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; rcu_read_lock(); /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; /* Remaining checks don't apply to root cpuset */ ret = 0; if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* On legacy hiearchy, we must be a subset of our parent cpuset. */ ret = -EACCES; if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } /* * Cpusets with tasks - existing or newly being attached - can't * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; if (!nodes_empty(cur->mems_allowed) && nodes_empty(trial->mems_allowed)) goto out; } /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && !cpuset_cpumask_can_shrink(cur->cpus_allowed, trial->cpus_allowed)) goto out; ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); } rcu_read_unlock(); } /* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ return static_key_count(&cpusets_enabled_key.key) + 1; } /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) * * Finding the best partition (set of domains): * The triple nested loops below over i, j, k scan over the * load balanced cpusets (using the array of cpuset pointers in * csa[]) looking for pairs of cpusets that have overlapping * cpus_allowed, but which don't have the same 'pn' partition * number and gives them in the same partition number. It keeps * looping on the 'restart' label until it can no longer find * any such pairs. * * The union of the cpus_allowed masks from the set of * all cpusets having the same 'pn' value then form the one * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (root_load_balance && !top_cpuset.nr_subparts_cpus) { ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) goto done; dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; rcu_read_lock(); if (root_load_balance) csa[csn++] = &top_cpuset; cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. * * If root is load-balancing, we can skip @cp if it * is a subset of the root's effective_cpus. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (root_load_balance && cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ if (!is_partition_root(cp)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; restart: /* Find the best partition (set of sched domains) */ for (i = 0; i < csn; i++) { struct cpuset *a = csa[i]; int apn = a->pn; for (j = 0; j < csn; j++) { struct cpuset *b = csa[j]; int bpn = b->pn; if (apn != bpn && cpusets_overlap(a, b)) { for (k = 0; k < csn; k++) { struct cpuset *c = csa[k]; if (c->pn == bpn) c->pn = apn; } ndoms--; /* one less element */ goto restart; } } } /* * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; int apn = a->pn; if (apn < 0) { /* Skip completed partitions */ continue; } dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; if (warnings) { pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", nslot, ndoms, csn, i, apn); warnings--; } continue; } cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); /* Done with this partition */ b->pn = -1; } } nslot++; } BUG_ON(nslot != ndoms); done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; if (cs->nr_deadline_tasks == 0) return; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); rcu_read_lock(); /* * Clear default root domain DL accounting, it will be computed again * if a task belongs to it. */ dl_clear_root_domain(&def_root_domain); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } static void partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes get_online_cpus(). */ static void rebuild_sched_domains_locked(void) { struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; struct cpuset *cs; int ndoms; lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset * is enough to detect racing CPU offlines. */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) return; /* * With subpartition CPUs, however, the effective CPUs of a partition * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ if (top_cpuset.nr_subparts_cpus) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_root(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!cpumask_subset(cs->effective_cpus, cpu_active_mask)) { rcu_read_unlock(); return; } } rcu_read_unlock(); } /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ void rebuild_sched_domains(void) { get_online_cpus(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); put_online_cpus(); } /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Percpu kthreads in top_cpuset are ignored */ if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; set_cpus_allowed_ptr(task, cs->effective_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * If the parent has subpartition CPUs, include them in the list of * allowable CPUs in computing the new effective_cpus mask. Since offlined * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask * to mask those out. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { if (parent->nr_subparts_cpus) { cpumask_or(new_cpus, parent->effective_cpus, parent->subparts_cpus); cpumask_and(new_cpus, new_cpus, cs->cpus_allowed); cpumask_and(new_cpus, new_cpus, cpu_active_mask); } else { cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus); } } /* * Commands for update_parent_subparts_cpumask */ enum subparts_cmd { partcmd_enable, /* Enable partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's subparts_cpus */ }; /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset * @cpuset: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0, 1 or an error code * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will * be put into parent's subparts_cpus and taken away from parent's * effective_cpus. The function will return 0 if all the CPUs listed in * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition * root back to a non-partition root. Any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back * into parent's effective_cpus. 0 should always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu * list is to be changed from cpus_allowed to newmask. Otherwise, * cpus_allowed is assumed to remain the same. The cpuset should either * be a partition root or an invalid partition root. The partition root * state may change if newmask is NULL and none of the requested CPUs can * be granted by the parent. The function will return 1 if changes to * parent's subparts_cpus and effective_cpus happen or 0 otherwise. * Error code should only be returned when newmask is non-NULL. * * The partcmd_enable and partcmd_disable commands are used by * update_prstate(). The partcmd_update command is used by * update_cpumasks_hier() with newmask NULL and update_cpumask() with * newmask set. * * The checking is more strict when enabling partition root than the * other two commands. * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be * permitted when checked by validate_change(). The validate_change() * function will also prevent any changes to the cpu list if it is not * a superset of children's cpu lists. */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ int new_prs; bool part_error = false; /* Partition error? */ lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_root(parent) || (newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cpuset->cpus_allowed))) return -EINVAL; /* * Enabling/disabling partition root is not allowed if there are * online children. */ if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css)) return -EBUSY; /* * Enabling partition root is not allowed if not all the CPUs * can be granted from parent's effective_cpus or at least one * CPU will be left after that. */ if ((cmd == partcmd_enable) && (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) return -EINVAL; /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* * partcmd_update with newmask: * * delmask = cpus_allowed & ~newmask & parent->subparts_cpus * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus */ cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus); cpumask_and(tmp->addmask, newmask, parent->effective_cpus); adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* * Return error if the new effective_cpus could become empty. */ if (adding && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) return -EINVAL; /* * As some of the CPUs in subparts_cpus might have * been offlined, we need to compute the real delmask * to confirm that. */ if (!cpumask_and(tmp->addmask, tmp->delmask, cpu_active_mask)) return -EINVAL; cpumask_copy(tmp->addmask, parent->effective_cpus); } } else { /* * partcmd_update w/o newmask: * * addmask = cpus_allowed & parent->effective_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. * So no deletion is needed. */ adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, parent->effective_cpus); part_error = cpumask_equal(tmp->addmask, parent->effective_cpus); } if (cmd == partcmd_update) { int prev_prs = cpuset->partition_root_state; /* * Check for possible transition between PRS_ENABLED * and PRS_ERROR. */ switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) new_prs = PRS_ENABLED; break; } /* * Set part_error if previously in invalid state. */ part_error = (prev_prs == PRS_ERROR); } if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */ if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ adding = false; deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } if (!adding && !deleting && (new_prs == cpuset->partition_root_state)) return 0; /* * Change the parent's subparts_cpus. * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (adding) { cpumask_or(parent->subparts_cpus, parent->subparts_cpus, tmp->addmask); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, tmp->addmask); } if (deleting) { cpumask_andnot(parent->subparts_cpus, parent->subparts_cpus, tmp->delmask); /* * Some of the CPUs in subparts_cpus might have been offlined. */ cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, tmp->delmask); } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); if (cpuset->partition_root_state != new_prs) cpuset->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); return cmd == partcmd_update; } /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * * When congifured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierachy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; int new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); compute_effective_cpumask(tmp->new_cpus, cp, parent); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; parent->child_ecpus_count++; } } else if (cp->use_parent_ecpus) { cp->use_parent_ecpus = false; WARN_ON_ONCE(!parent->child_ecpus_count); parent->child_ecpus_count--; } /* * Skip the whole subtree if the cpumask remains the same * and has no partition root state. */ if (!cp->partition_root_state && cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ new_prs = cp->partition_root_state; if ((cp != cs) && new_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an * invalid partition root, clear its state * and its CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); new_prs = PRS_DISABLED; /* * clear_bit() is an atomic operation and * readers aren't interested in the state * of CS_CPU_EXCLUSIVE anyway. So we can * just update the flag without holding * the callback_lock. */ clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); break; case PRS_ENABLED: if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) update_tasks_cpumask(parent); break; case PRS_ERROR: /* * When parent is invalid, it has to be too. */ new_prs = PRS_ERROR; break; } } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { /* * Make sure that effective_cpus & subparts_cpus * are mutually exclusive. * * In the unlikely event that effective_cpus * becomes empty. we clear cp->nr_subparts_cpus and * let its child partition roots to compete for * CPUs again. */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); if (cpumask_empty(cp->effective_cpus)) { cpumask_copy(cp->effective_cpus, tmp->new_cpus); cpumask_clear(cp->subparts_cpus); cp->nr_subparts_cpus = 0; } else if (!cpumask_subset(cp->subparts_cpus, tmp->new_cpus)) { cpumask_andnot(cp->subparts_cpus, cp->subparts_cpus, tmp->new_cpus); cp->nr_subparts_cpus = cpumask_weight(cp->subparts_cpus); } } if (new_prs != cp->partition_root_state) cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp); /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || is_partition_root(cp))) need_rebuild_sched_domains = true; rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); if (need_rebuild_sched_domains) rebuild_sched_domains_locked(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs) continue; if (!sibling->use_parent_ecpus) continue; if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; /* * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. */ if (!*buf) { cpumask_clear(trialcs->cpus_allowed); } else { retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) return retval; if (!cpumask_subset(trialcs->cpus_allowed, top_cpuset.cpus_allowed)) return -EINVAL; } /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; retval = validate_change(cs, trialcs); if (retval < 0) return retval; #ifdef CONFIG_CPUMASK_OFFSTACK /* * Use the cpumasks in trialcs for tmpmasks when they are pointers * to allocated cpumasks. */ tmp.addmask = trialcs->subparts_cpus; tmp.delmask = trialcs->effective_cpus; tmp.new_cpus = trialcs->cpus_allowed; #endif if (cs->partition_root_state) { /* Cpumask of a partition root cannot be empty */ if (cpumask_empty(trialcs->cpus_allowed)) return -EINVAL; if (update_parent_subparts_cpumask(cs, partcmd_update, trialcs->cpus_allowed, &tmp) < 0) return -EINVAL; } spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); /* * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); update_cpumasks_hier(cs, &tmp); if (cs->partition_root_state) { struct cpuset *parent = parent_cs(cs); /* * For partition root, update the cpumasks of sibling * cpusets if they use parent's effective_cpus. */ if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmp); } return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hiearchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; * it's read-only */ if (cs == &top_cpuset) { retval = -EACCES; goto done; } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have memory. */ if (!*buf) { nodes_clear(trialcs->mems_allowed); } else { retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) { retval = -EINVAL; goto done; } } if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } retval = validate_change(cs, trialcs); if (retval < 0) goto done; spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); done: return retval; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP if (val < -1 || val >= sched_domain_level_max) return -EINVAL; #endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) rebuild_sched_domains_locked(); } return 0; } /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flag(cs, task); css_task_iter_end(&it); } /* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /* * update_prstate - update partititon_root_state * cs: the cpuset to update * new_prs: new partition root state * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; if (old_prs == new_prs) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL; if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; err = -EINVAL; if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed * cannot be NULL. */ if (cpumask_empty(cs->cpus_allowed)) goto out; err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); if (err) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, NULL, &tmpmask); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, NULL, &tmpmask); if (err) goto out; /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } update_tasks_cpumask(parent); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); rebuild_sched_domains_locked(); out: if (!err) { spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); } free_cpumasks(NULL, &tmpmask); return err; } /* * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: * fmeter_init() - initialize a frequency meter. * fmeter_markevent() - called each time the event happens. * fmeter_getrate() - returns the recent rate of such events. * fmeter_update() - internal routine used to update fmeter. * * A common data structure is passed to each of these routines, * which is used to keep track of the state required to manage the * frequency meter and its digital filter. * * The filter works on the number of events marked per unit time. * The filter is single-pole low-pass recursive (IIR). The time unit * is 1 second. Arithmetic is done using 32-bit integers scaled to * simulate 3 decimal digits of precision (multiplied by 1000). * * With an FM_COEF of 933, and a time base of 1 second, the filter * has a half-life of 10 seconds, meaning that if the events quit * happening, then the rate returned from the fmeter_getrate() * will be cut in half each 10 seconds, until it converges to zero. * * It is not worth doing a real infinitely recursive filter. If more * than FM_MAXTICKS ticks have elapsed since the last filter event, * just compute FM_MAXTICKS ticks worth, by which point the level * will be stable. * * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid * arithmetic overflow in the fmeter_update() routine. * * Given the simple 32 bit integer arithmetic used, this meter works * best for reporting rates between one per millisecond (msec) and * one per 32 (approx) seconds. At constant rates faster than one * per msec it maxes out at values just under 1,000,000. At constant * rates between one per msec, and one per second it will stabilize * to a value N*1000, where N is the rate of events per second. * At constant rates between one per second and one per 32 seconds, * it will be choppy, moving up on the seconds that have an event, * and then decaying until the next event. At rates slower than * about one in 32 seconds, it decays all the way back to zero between * each event. */ #define FM_COEF 933 /* coefficient for half-life of 10 secs */ #define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ #define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ #define FM_SCALE 1000 /* faux fixed point scale */ /* Initialize a frequency meter */ static void fmeter_init(struct fmeter *fmp) { fmp->cnt = 0; fmp->val = 0; fmp->time = 0; spin_lock_init(&fmp->lock); } /* Internal meter update - process cnt events and update value */ static void fmeter_update(struct fmeter *fmp) { time64_t now; u32 ticks; now = ktime_get_seconds(); ticks = now - fmp->time; if (ticks == 0) return; ticks = min(FM_MAXTICKS, ticks); while (ticks-- > 0) fmp->val = (FM_COEF * fmp->val) / FM_SCALE; fmp->time = now; fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; fmp->cnt = 0; } /* Process any previous ticks, then bump cnt by one (times scale). */ static void fmeter_markevent(struct fmeter *fmp) { spin_lock(&fmp->lock); fmeter_update(fmp); fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); spin_unlock(&fmp->lock); } /* Process any previous ticks, then return current value. */ static int fmeter_getrate(struct fmeter *fmp) { int val; spin_lock(&fmp->lock); fmeter_update(fmp); val = fmp->val; spin_unlock(&fmp->lock); return val; } static struct cpuset *cpuset_attach_old_cs; static void reset_migrate_dl_data(struct cpuset *cs) { cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; if (!is_in_v2_mode() && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; if (dl_task(task)) { cs->nr_migrate_dl_tasks++; cs->sum_migrate_dl_bw += task->dl.dl_bw; } } if (!cs->nr_migrate_dl_tasks) goto out_success; if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) { reset_migrate_dl_data(cs); ret = -EINVAL; goto out_unlock; } ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); if (ret) { reset_migrate_dl_data(cs); goto out_unlock; } } out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; ret = 0; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); if (cs->nr_migrate_dl_tasks) { int cpu = cpumask_any(cs->effective_cpus); dl_bw_free(cpu, cs->sum_migrate_dl_bw); reset_migrate_dl_data(cs); } mutex_unlock(&cpuset_mutex); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); /* prepare for attach */ if (cs == &top_cpuset) cpumask_copy(cpus_attach, cpu_possible_mask); else guarantee_online_cpus(cs, cpus_attach); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, task); } /* * Change mm for all threadgroup leaders. This is expensive and may * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); else mmput(mm); } } cs->old_mems_allowed = cpuset_attach_nodemask_to; if (cs->nr_migrate_dl_tasks) { cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; reset_migrate_dl_data(cs); } cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ typedef enum { FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_EFFECTIVE_CPULIST, FILE_EFFECTIVE_MEMLIST, FILE_SUBPARTS_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, FILE_SCHED_LOAD_BALANCE, FILE_PARTITION_ROOT, FILE_SCHED_RELAX_DOMAIN_LEVEL, FILE_MEMORY_PRESSURE_ENABLED, FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, } cpuset_filetype_t; static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = 0; get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; } switch (type) { case FILE_CPU_EXCLUSIVE: retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); break; case FILE_MEM_EXCLUSIVE: retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); break; case FILE_MEM_HARDWALL: retval = update_flag(CS_MEM_HARDWALL, cs, val); break; case FILE_SCHED_LOAD_BALANCE: retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); break; case FILE_MEMORY_MIGRATE: retval = update_flag(CS_MEMORY_MIGRATE, cs, val); break; case FILE_MEMORY_PRESSURE_ENABLED: cpuset_memory_pressure_enabled = !!val; break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); return retval; } static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: retval = update_relax_domain_level(cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); return retval; } /* * Common handling for a write to a "cpus" or "mems" file. */ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; buf = strstrip(buf); /* * CPU or memory hotunplug may leave @cs w/o any execution * resources, in which case the hotplug code asynchronously updates * configuration and transfers all tasks to the nearest ancestor * which can execute. * * As writes to "cpus" or "mems" may restore @cs's execution * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * * cpuset_hotplug_work calls back into cgroup core via * cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: return is_cpu_exclusive(cs); case FILE_MEM_EXCLUSIVE: return is_mem_exclusive(cs); case FILE_MEM_HARDWALL: return is_mem_hardwall(cs); case FILE_SCHED_LOAD_BALANCE: return is_sched_load_balance(cs); case FILE_MEMORY_MIGRATE: return is_memory_migrate(cs); case FILE_MEMORY_PRESSURE_ENABLED: return cpuset_memory_pressure_enabled; case FILE_MEMORY_PRESSURE: return fmeter_getrate(&cs->fmeter); case FILE_SPREAD_PAGE: return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: return cs->relax_domain_level; default: BUG(); } /* Unrechable but makes gcc happy */ return 0; } static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); switch (cs->partition_root_state) { case PRS_ENABLED: seq_puts(seq, "root\n"); break; case PRS_DISABLED: seq_puts(seq, "member\n"); break; case PRS_ERROR: seq_puts(seq, "root invalid\n"); break; } return 0; } static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); /* * Convert "root" to ENABLED, and convert "member" to DISABLED. */ if (!strcmp(buf, "root")) val = PRS_ENABLED; else if (!strcmp(buf, "member")) val = PRS_DISABLED; else return -EINVAL; css_get(&cs->css); get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); css_put(&cs->css); return retval ?: nbytes; } /* * for the common functions, 'private' gives the type of file */ static struct cftype legacy_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, }, { .name = "effective_cpus", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "effective_mems", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpu_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_CPU_EXCLUSIVE, }, { .name = "mem_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_EXCLUSIVE, }, { .name = "mem_hardwall", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_HARDWALL, }, { .name = "sched_load_balance", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SCHED_LOAD_BALANCE, }, { .name = "sched_relax_domain_level", .read_s64 = cpuset_read_s64, .write_s64 = cpuset_write_s64, .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, }, { .name = "memory_migrate", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_MIGRATE, }, { .name = "memory_pressure", .read_u64 = cpuset_read_u64, .private = FILE_MEMORY_PRESSURE, }, { .name = "memory_spread_page", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_PAGE, }, { .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, { .name = "memory_pressure_enabled", .flags = CFTYPE_ONLY_ON_ROOT, .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE_ENABLED, }, { } /* terminate */ }; /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = sched_partition_show, .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_DEBUG, }, { } /* terminate */ }; /* * cpuset_css_alloc - allocate a cpuset css * cgrp: control group that the new cpuset will be part of */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (alloc_cpumasks(cs, NULL)) { kfree(cs); return ERR_PTR(-ENOMEM); } set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); nodes_clear(cs->mems_allowed); nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup_subsys_state *pos_css; if (!parent) return 0; get_online_cpus(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is * set. This flag handling is implemented in cgroup core for * histrical reasons - the flag may be specified during mount. * * Currently, if any sibling cpusets have exclusive cpus or mem, we * refuse to clone the configuration - thereby refusing the task to * be entered, and as a result refusing the sys_unshare() or * clone() which initiated it. If this becomes a problem for some * users who wish to allow that scenario, then this could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. * * If the cpuset has the 'sched.partition' flag enabled, simulate * turning 'sched.partition" off. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); get_online_cpus(); mutex_lock(&cpuset_mutex); if (is_partition_root(cs)) update_prstate(cs, 0); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { if (task_css_is_root(task, cpuset_cgrp_id)) return; set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; } /* * If CPU and/or memory hotplug handlers, below, unplug any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { pr_err("cpuset: failed to transfer tasks out of empty cpuset "); pr_cont_cgroup_name(cs->css.cgroup); pr_cont("\n"); } } static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { bool is_empty; spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, * as the tasks will be migratecd to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) update_tasks_cpumask(cs); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into * cpuset. Should be done outside any lock. */ if (is_empty) remove_tasks_in_empty_cpuset(cs); mutex_lock(&cpuset_mutex); } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { if (cpumask_empty(new_cpus)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); if (mems_updated) update_tasks_nodemask(cs); } static bool force_rebuild; void cpuset_force_rebuild(void) { force_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { mutex_unlock(&cpuset_mutex); goto retry; } parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); if (cs->nr_subparts_cpus) /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. */ cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * In the unlikely event that a partition root has empty * effective_cpus or its parent becomes erroneous, we have to * transition it to the erroneous state. */ if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); spin_unlock_irq(&callback_lock); compute_effective_cpumask(&new_cpus, cs, parent); } /* * If the effective_cpus is empty because the child * partitions take away all the CPUs, we can keep * the current partition and let the child partitions * fight for available CPUs. */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; spin_unlock_irq(&callback_lock); } cpuset_force_rebuild(); } /* * On the other hand, an erroneous partition root may be transitioned * back to a regular one or a partition root with no CPU allocated * from the parent may change to erroneous. */ if (is_partition_root(parent) && ((cs->partition_root_state == PRS_ERROR) || !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild(); update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); mutex_unlock(&cpuset_mutex); } /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. */ static void cpuset_hotplug_workfn(struct work_struct *work) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subparts_cpus is populated, it is likely that the check below * will produce a false positive on cpus_updated when the cpu list * isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* * In the rare case that hotplug removes all the cpus in subparts_cpus, * we assumed that cpus are updated. */ if (!cpus_updated && top_cpuset.nr_subparts_cpus) cpus_updated = true; /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subparts_cpus & let the child partitions * fight for the CPUs again. */ if (top_cpuset.nr_subparts_cpus) { if (cpumask_subset(&new_cpus, top_cpuset.subparts_cpus)) { top_cpuset.nr_subparts_cpus = 0; cpumask_clear(top_cpuset.subparts_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, top_cpuset.subparts_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; rebuild_sched_domains(); } free_cpumasks(NULL, ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ schedule_work(&cpuset_hotplug_work); } void cpuset_wait_for_hotplug(void) { flush_work(&cpuset_hotplug_work); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } static struct notifier_block cpuset_track_online_nodes_nb = { .notifier_call = cpuset_track_online_nodes, .priority = 10, /* ??! */ }; /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the * tasks cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_cpus(task_cs(tsk), pmask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. **/ void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { rcu_read_lock(); do_set_cpus_allowed(tsk, is_in_v2_mode() ? task_cs(tsk)->cpus_allowed : cpu_possible_mask); rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /** * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * __alloc_pages() routine only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_mem_spread_node() - On which node to begin search for a file page * cpuset_slab_spread_node() - On which node to begin search for a slab page * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), * and if the memory allocation used cpuset_mem_spread_node() * to determine on which node to start looking, as it will for * certain page cache or slab cache pages such as used for file * system buffers and inode caches, then instead of starting on the * local node to look for a free page, rather spread the starting * node around the tasks mems_allowed nodes. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist passed to * __alloc_pages() will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) current->cpuset_slab_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special * cpuset file 'memory_pressure_enabled' in the root cpuset. */ int cpuset_memory_pressure_enabled __read_mostly; /** * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. * * This represents the rate at which some task in the cpuset * ran low on memory on all nodes it was allowed to use, and * had to enter the kernels page reclaim code in an effort to * create more free memory by tossing clean pages or swapping * or writing dirty pages. * * Display to user space in the per-cpuset read-only file * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. **/ void __cpuset_memory_pressure_bump(void) { rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET /* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; css = task_get_css(tsk, cpuset_cgrp_id); retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); css_put(css); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: kfree(buf); out: return retval; } #endif /* CONFIG_PROC_PID_CPUSET */ /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 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 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * hrtimers - High-resolution kernel timers * * Copyright(C) 2005, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005, Red Hat, Inc., Ingo Molnar * * data type definitions, declarations, prototypes * * Started by: Thomas Gleixner and Ingo Molnar */ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H #include <linux/hrtimer_defs.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/list.h> #include <linux/percpu.h> #include <linux/seqlock.h> #include <linux/timer.h> #include <linux/timerqueue.h> struct hrtimer_clock_base; struct hrtimer_cpu_base; /* * Mode arguments of xxx_hrtimer functions: * * HRTIMER_MODE_ABS - Time value is absolute * HRTIMER_MODE_REL - Time value is relative to now * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered * when starting the timer) * HRTIMER_MODE_SOFT - Timer callback function will be executed in * soft irq context * HRTIMER_MODE_HARD - Timer callback function will be executed in * hard irq context even on PREEMPT_RT. */ enum hrtimer_mode { HRTIMER_MODE_ABS = 0x00, HRTIMER_MODE_REL = 0x01, HRTIMER_MODE_PINNED = 0x02, HRTIMER_MODE_SOFT = 0x04, HRTIMER_MODE_HARD = 0x08, HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, }; /* * Return values for the callback function */ enum hrtimer_restart { HRTIMER_NORESTART, /* Timer is not restarted */ HRTIMER_RESTART, /* Timer must be restarted */ }; /* * Values to track state of the timer * * Possible states: * * 0x00 inactive * 0x01 enqueued into rbtree * * The callback state is not part of the timer->state because clearing it would * mean touching the timer after the callback, this makes it impossible to free * the timer from the callback function. * * Therefore we track the callback state in: * * timer->base->cpu_base->running == timer * * On SMP it is possible to have a "callback function running and enqueued" * status. It happens for example when a posix timer expired and the callback * queued a signal. Between dropping the lock which protects the posix timer * and reacquiring the base lock of the hrtimer, another CPU can deliver the * signal and rearm the timer. * * All state transitions are protected by cpu_base->lock. */ #define HRTIMER_STATE_INACTIVE 0x00 #define HRTIMER_STATE_ENQUEUED 0x01 /** * struct hrtimer - the basic hrtimer structure * @node: timerqueue node, which also manages node.expires, * the absolute expiry time in the hrtimers internal * representation. The time is related to the clock on * which the timer is based. Is setup by adding * slack to the _softexpires value. For non range timers * identical to _softexpires. * @_softexpires: the absolute earliest expiry time of the hrtimer. * The time which was given as expiry time when the timer * was armed. * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) * @is_rel: Set if the timer was armed relative * @is_soft: Set if hrtimer will be expired in soft interrupt context. * @is_hard: Set if hrtimer will be expired in hard interrupt context * even on RT. * * The hrtimer structure must be initialized by hrtimer_init() */ struct hrtimer { struct timerqueue_node node; ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; u8 state; u8 is_rel; u8 is_soft; u8 is_hard; }; /** * struct hrtimer_sleeper - simple sleeper structure * @timer: embedded timer structure * @task: task to wake up * * task is set to NULL, when the timer expires. */ struct hrtimer_sleeper { struct hrtimer timer; struct task_struct *task; }; #ifdef CONFIG_64BIT # define __hrtimer_clock_base_align ____cacheline_aligned #else # define __hrtimer_clock_base_align #endif /** * struct hrtimer_clock_base - the timer base for a specific clock * @cpu_base: per cpu clock base * @index: clock type index for per_cpu support when moving a * timer to a base on another cpu. * @clockid: clock id for per_cpu support * @seq: seqcount around __run_hrtimer * @running: pointer to the currently running hrtimer * @active: red black tree root node for the active timers * @get_time: function to retrieve the current time of the clock * @offset: offset of this clock to the monotonic base */ struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; unsigned int index; clockid_t clockid; seqcount_raw_spinlock_t seq; struct hrtimer *running; struct timerqueue_head active; ktime_t (*get_time)(void); ktime_t offset; } __hrtimer_clock_base_align; enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, HRTIMER_BASE_REALTIME, HRTIMER_BASE_BOOTTIME, HRTIMER_BASE_TAI, HRTIMER_BASE_MONOTONIC_SOFT, HRTIMER_BASE_REALTIME_SOFT, HRTIMER_BASE_BOOTTIME_SOFT, HRTIMER_BASE_TAI_SOFT, HRTIMER_MAX_CLOCK_BASES, }; /** * struct hrtimer_cpu_base - the per cpu clock bases * @lock: lock protecting the base and associated clock bases * and timers * @cpu: cpu number * @active_bases: Bitfield to mark bases with active timers * @clock_was_set_seq: Sequence counter of clock was set events * @hres_active: State of high resolution mode * @in_hrtirq: hrtimer_interrupt() is currently executing * @hang_detected: The last hrtimer interrupt detected a hang * @softirq_activated: displays, if the softirq is raised - update of softirq * related settings is not required then. * @nr_events: Total number of hrtimer interrupt events * @nr_retries: Total number of hrtimer interrupt retries * @nr_hangs: Total number of hrtimer interrupt hangs * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired * @online: CPU is online from an hrtimers point of view * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote * hrtimer enqueue; it is the total first expiry time (hard * and soft hrtimer are taken into account) * @next_timer: Pointer to the first expiring timer * @softirq_expires_next: Time to check, if soft queues needs also to be expired * @softirq_next_timer: Pointer to the first expiring softirq based timer * @clock_base: array of clock bases for this cpu * * Note: next_timer is just an optimization for __remove_hrtimer(). * Do not dereference the pointer because it is not reliable on * cross cpu removals. */ struct hrtimer_cpu_base { raw_spinlock_t lock; unsigned int cpu; unsigned int active_bases; unsigned int clock_was_set_seq; unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, softirq_activated : 1, online : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; unsigned short nr_hangs; unsigned int max_hang_time; #endif #ifdef CONFIG_PREEMPT_RT spinlock_t softirq_expiry_lock; atomic_t timer_waiters; #endif ktime_t expires_next; struct hrtimer *next_timer; ktime_t softirq_expires_next; struct hrtimer *softirq_next_timer; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; } ____cacheline_aligned; static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, u64 delta) { timer->_softexpires = time; timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { timer->node.expires = tv64; timer->_softexpires = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { return timer->node.expires; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { return timer->_softexpires; } static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) { return ktime_to_ns(timer->node.expires); } static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { return ktime_sub(timer->node.expires, timer->base->get_time()); } static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer) { return timer->base->get_time(); } static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? timer->base->cpu_base->hres_active : 0; } #ifdef CONFIG_HIGH_RES_TIMERS struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); extern unsigned int hrtimer_resolution; #else #define hrtimer_resolution (unsigned int)LOW_RES_NSEC #endif static inline ktime_t __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) { ktime_t rem = ktime_sub(timer->node.expires, now); /* * Adjust relative timers for the extra we added in * hrtimer_start_range_ns() to prevent short timeouts. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) rem -= hrtimer_resolution; return rem; } static inline ktime_t hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) { return __hrtimer_expires_remaining_adjusted(timer, timer->base->get_time()); } #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); #else static inline void timerfd_clock_was_set(void) { } #endif extern void hrtimers_resume(void); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); #ifdef CONFIG_PREEMPT_RT void hrtimer_cancel_wait_running(const struct hrtimer *timer); #else static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) { cpu_relax(); } #endif /* Exported timer functions: */ /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else static inline void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode) { hrtimer_init(timer, which_clock, mode); } static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { hrtimer_init_sleeper(sl, clock_id, mode); } static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif /* Basic timer operations: */ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 range_ns, const enum hrtimer_mode mode); /** * hrtimer_start - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { hrtimer_start_range_ns(timer, tim, 0, mode); } extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode) { u64 delta; ktime_t soft, hard; soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); hrtimer_start_range_ns(timer, soft, delta, mode); } void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode); static inline void hrtimer_restart(struct hrtimer *timer) { hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { return __hrtimer_get_remaining(timer, false); } extern u64 hrtimer_get_next_event(void); extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); /** * hrtimer_is_queued = check, whether the timer is on one of the queues * @timer: Timer to check * * Returns: True if the timer is queued, false otherwise * * The function can be used lockless, but it gives only a current snapshot. */ static inline bool hrtimer_is_queued(struct hrtimer *timer) { /* The READ_ONCE pairs with the update functions of timer->state */ return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* * Helper function to check, whether the timer is running the callback * function */ static inline int hrtimer_callback_running(struct hrtimer *timer) { return timer->base->running == timer; } /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); /** * hrtimer_forward_now - forward the timer expiry so it expires after now * @timer: hrtimer to forward * @interval: the interval to forward * * Forward the timer expiry so it will expire after the current time * of the hrtimer clock base. Returns the number of overruns. * * Can be safely called from the callback function of @timer. If * called from other contexts @timer must neither be enqueued nor * running the callback and the caller needs to take care of * serialization. * * Note: This only updates the timer expiry value and does not requeue * the timer. */ static inline u64 hrtimer_forward_now(struct hrtimer *timer, ktime_t interval) { return hrtimer_forward(timer, timer->base->get_time(), interval); } /* Precise sleep: */ extern int nanosleep_copyout(struct restart_block *, struct timespec64 *); extern long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid); extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode); extern int schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id); extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); /* Bootup initialization: */ extern void __init hrtimers_init(void); /* Show pending timers: */ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU int hrtimers_cpu_dying(unsigned int cpu); #else #define hrtimers_cpu_dying NULL #endif #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM io_uring #if !defined(_TRACE_IO_URING_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IO_URING_H #include <linux/tracepoint.h> struct io_wq_work; /** * io_uring_create - called after a new io_uring context was prepared * * @fd: corresponding file descriptor * @ctx: pointer to a ring context structure * @sq_entries: actual SQ size * @cq_entries: actual CQ size * @flags: SQ ring flags, provided to io_uring_setup(2) * * Allows to trace io_uring creation and provide pointer to a context, that can * be used later to find correlated events. */ TRACE_EVENT(io_uring_create, TP_PROTO(int fd, void *ctx, u32 sq_entries, u32 cq_entries, u32 flags), TP_ARGS(fd, ctx, sq_entries, cq_entries, flags), TP_STRUCT__entry ( __field( int, fd ) __field( void *, ctx ) __field( u32, sq_entries ) __field( u32, cq_entries ) __field( u32, flags ) ), TP_fast_assign( __entry->fd = fd; __entry->ctx = ctx; __entry->sq_entries = sq_entries; __entry->cq_entries = cq_entries; __entry->flags = flags; ), TP_printk("ring %p, fd %d sq size %d, cq size %d, flags %d", __entry->ctx, __entry->fd, __entry->sq_entries, __entry->cq_entries, __entry->flags) ); /** * io_uring_register - called after a buffer/file/eventfd was successfully * registered for a ring * * @ctx: pointer to a ring context structure * @opcode: describes which operation to perform * @nr_user_files: number of registered files * @nr_user_bufs: number of registered buffers * @cq_ev_fd: whether eventfs registered or not * @ret: return code * * Allows to trace fixed files/buffers/eventfds, that could be registered to * avoid an overhead of getting references to them for every operation. This * event, together with io_uring_file_get, can provide a full picture of how * much overhead one can reduce via fixing. */ TRACE_EVENT(io_uring_register, TP_PROTO(void *ctx, unsigned opcode, unsigned nr_files, unsigned nr_bufs, bool eventfd, long ret), TP_ARGS(ctx, opcode, nr_files, nr_bufs, eventfd, ret), TP_STRUCT__entry ( __field( void *, ctx ) __field( unsigned, opcode ) __field( unsigned, nr_files ) __field( unsigned, nr_bufs ) __field( bool, eventfd ) __field( long, ret ) ), TP_fast_assign( __entry->ctx = ctx; __entry->opcode = opcode; __entry->nr_files = nr_files; __entry->nr_bufs = nr_bufs; __entry->eventfd = eventfd; __entry->ret = ret; ), TP_printk("ring %p, opcode %d, nr_user_files %d, nr_user_bufs %d, " "eventfd %d, ret %ld", __entry->ctx, __entry->opcode, __entry->nr_files, __entry->nr_bufs, __entry->eventfd, __entry->ret) ); /** * io_uring_file_get - called before getting references to an SQE file * * @ctx: pointer to a ring context structure * @fd: SQE file descriptor * * Allows to trace out how often an SQE file reference is obtained, which can * help figuring out if it makes sense to use fixed files, or check that fixed * files are used correctly. */ TRACE_EVENT(io_uring_file_get, TP_PROTO(void *ctx, int fd), TP_ARGS(ctx, fd), TP_STRUCT__entry ( __field( void *, ctx ) __field( int, fd ) ), TP_fast_assign( __entry->ctx = ctx; __entry->fd = fd; ), TP_printk("ring %p, fd %d", __entry->ctx, __entry->fd) ); /** * io_uring_queue_async_work - called before submitting a new async work * * @ctx: pointer to a ring context structure * @hashed: type of workqueue, hashed or normal * @req: pointer to a submitted request * @work: pointer to a submitted io_wq_work * * Allows to trace asynchronous work submission. */ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, int rw, void * req, struct io_wq_work *work, unsigned int flags), TP_ARGS(ctx, rw, req, work, flags), TP_STRUCT__entry ( __field( void *, ctx ) __field( int, rw ) __field( void *, req ) __field( struct io_wq_work *, work ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->ctx = ctx; __entry->rw = rw; __entry->req = req; __entry->work = work; __entry->flags = flags; ), TP_printk("ring %p, request %p, flags %d, %s queue, work %p", __entry->ctx, __entry->req, __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); /** * io_uring_defer - called when an io_uring request is deferred * * @ctx: pointer to a ring context structure * @req: pointer to a deferred request * @user_data: user data associated with the request * * Allows to track deferred requests, to get an insight about what requests are * not started immediately. */ TRACE_EVENT(io_uring_defer, TP_PROTO(void *ctx, void *req, unsigned long long user_data), TP_ARGS(ctx, req, user_data), TP_STRUCT__entry ( __field( void *, ctx ) __field( void *, req ) __field( unsigned long long, data ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; __entry->data = user_data; ), TP_printk("ring %p, request %p user_data %llu", __entry->ctx, __entry->req, __entry->data) ); /** * io_uring_link - called before the io_uring request added into link_list of * another request * * @ctx: pointer to a ring context structure * @req: pointer to a linked request * @target_req: pointer to a previous request, that would contain @req * * Allows to track linked requests, to understand dependencies between requests * and how does it influence their execution flow. */ TRACE_EVENT(io_uring_link, TP_PROTO(void *ctx, void *req, void *target_req), TP_ARGS(ctx, req, target_req), TP_STRUCT__entry ( __field( void *, ctx ) __field( void *, req ) __field( void *, target_req ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; __entry->target_req = target_req; ), TP_printk("ring %p, request %p linked after %p", __entry->ctx, __entry->req, __entry->target_req) ); /** * io_uring_cqring_wait - called before start waiting for an available CQE * * @ctx: pointer to a ring context structure * @min_events: minimal number of events to wait for * * Allows to track waiting for CQE, so that we can e.g. troubleshoot * situations, when an application wants to wait for an event, that never * comes. */ TRACE_EVENT(io_uring_cqring_wait, TP_PROTO(void *ctx, int min_events), TP_ARGS(ctx, min_events), TP_STRUCT__entry ( __field( void *, ctx ) __field( int, min_events ) ), TP_fast_assign( __entry->ctx = ctx; __entry->min_events = min_events; ), TP_printk("ring %p, min_events %d", __entry->ctx, __entry->min_events) ); /** * io_uring_fail_link - called before failing a linked request * * @req: request, which links were cancelled * @link: cancelled link * * Allows to track linked requests cancellation, to see not only that some work * was cancelled, but also which request was the reason. */ TRACE_EVENT(io_uring_fail_link, TP_PROTO(void *req, void *link), TP_ARGS(req, link), TP_STRUCT__entry ( __field( void *, req ) __field( void *, link ) ), TP_fast_assign( __entry->req = req; __entry->link = link; ), TP_printk("request %p, link %p", __entry->req, __entry->link) ); /** * io_uring_complete - called when completing an SQE * * @ctx: pointer to a ring context structure * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags * */ TRACE_EVENT(io_uring_complete, TP_PROTO(void *ctx, u64 user_data, int res, unsigned cflags), TP_ARGS(ctx, user_data, res, cflags), TP_STRUCT__entry ( __field( void *, ctx ) __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) ), TP_fast_assign( __entry->ctx = ctx; __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; ), TP_printk("ring %p, user_data 0x%llx, result %d, cflags %x", __entry->ctx, (unsigned long long)__entry->user_data, __entry->res, __entry->cflags) ); /** * io_uring_submit_sqe - called before submitting one SQE * * @ctx: pointer to a ring context structure * @req: pointer to a submitted request * @opcode: opcode of request * @user_data: user data associated with the request * @flags request flags * @force_nonblock: whether a context blocking or not * @sq_thread: true if sq_thread has submitted this SQE * * Allows to track SQE submitting, to understand what was the source of it, SQ * thread or io_uring_enter call. */ TRACE_EVENT(io_uring_submit_sqe, TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, u32 flags, bool force_nonblock, bool sq_thread), TP_ARGS(ctx, req, opcode, user_data, flags, force_nonblock, sq_thread), TP_STRUCT__entry ( __field( void *, ctx ) __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) __field( u32, flags ) __field( bool, force_nonblock ) __field( bool, sq_thread ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; ), TP_printk("ring %p, req %p, op %d, data 0x%llx, flags %u, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, __entry->opcode, (unsigned long long)__entry->user_data, __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); /* * io_uring_poll_arm - called after arming a poll wait if successful * * @ctx: pointer to a ring context structure * @req: pointer to the armed request * @opcode: opcode of request * @user_data: user data associated with the request * @mask: request poll events mask * @events: registered events of interest * * Allows to track which fds are waiting for and what are the events of * interest. */ TRACE_EVENT(io_uring_poll_arm, TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, int mask, int events), TP_ARGS(ctx, req, opcode, user_data, mask, events), TP_STRUCT__entry ( __field( void *, ctx ) __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) __field( int, mask ) __field( int, events ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; __entry->mask = mask; __entry->events = events; ), TP_printk("ring %p, req %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", __entry->ctx, __entry->req, __entry->opcode, (unsigned long long) __entry->user_data, __entry->mask, __entry->events) ); TRACE_EVENT(io_uring_poll_wake, TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask), TP_ARGS(ctx, opcode, user_data, mask), TP_STRUCT__entry ( __field( void *, ctx ) __field( u8, opcode ) __field( u64, user_data ) __field( int, mask ) ), TP_fast_assign( __entry->ctx = ctx; __entry->opcode = opcode; __entry->user_data = user_data; __entry->mask = mask; ), TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x", __entry->ctx, __entry->opcode, (unsigned long long) __entry->user_data, __entry->mask) ); TRACE_EVENT(io_uring_task_add, TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask), TP_ARGS(ctx, opcode, user_data, mask), TP_STRUCT__entry ( __field( void *, ctx ) __field( u8, opcode ) __field( u64, user_data ) __field( int, mask ) ), TP_fast_assign( __entry->ctx = ctx; __entry->opcode = opcode; __entry->user_data = user_data; __entry->mask = mask; ), TP_printk("ring %p, op %d, data 0x%llx, mask %x", __entry->ctx, __entry->opcode, (unsigned long long) __entry->user_data, __entry->mask) ); /* * io_uring_task_run - called when task_work_run() executes the poll events * notification callbacks * * @ctx: pointer to a ring context structure * @req: pointer to the armed request * @opcode: opcode of request * @user_data: user data associated with the request * * Allows to track when notified poll events are processed */ TRACE_EVENT(io_uring_task_run, TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data), TP_ARGS(ctx, req, opcode, user_data), TP_STRUCT__entry ( __field( void *, ctx ) __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; ), TP_printk("ring %p, req %p, op %d, data 0x%llx", __entry->ctx, __entry->req, __entry->opcode, (unsigned long long) __entry->user_data) ); #endif /* _TRACE_IO_URING_H */ /* This part must be outside protection */ #include <trace/define_trace.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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memblock.h> #include <linux/mmdebug.h> #include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> #include <linux/vmalloc.h> #include "physaddr.h" #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } return x; } EXPORT_SYMBOL(__phys_addr); unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; if (y >= KERNEL_IMAGE_SIZE) return false; } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ if ((x > y) || !phys_addr_valid(x)) return false; } return pfn_valid(x >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #else #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); /* max_low_pfn is set early, but not _that_ early */ if (max_low_pfn) { VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); } return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) return false; if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #endif /* CONFIG_X86_64 */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/ima.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags, int *empty) { struct filename *result; char *kname; int len; result = audit_reusename(filename); if (result) return result; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { __putname(result); return ERR_PTR(len); } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) { const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; /* * size is chosen that way we to guarantee that * result->iname[0] is within the same object and that * kname can't be equal to result->iname, no matter what. */ result = kzalloc(size, GFP_KERNEL); if (unlikely(!result)) { __putname(kname); return ERR_PTR(-ENOMEM); } result->name = kname; len = strncpy_from_user(kname, filename, PATH_MAX); if (unlikely(len < 0)) { __putname(kname); kfree(result); return ERR_PTR(len); } if (unlikely(len == PATH_MAX)) { __putname(kname); kfree(result); return ERR_PTR(-ENAMETOOLONG); } } result->refcnt = 1; /* The empty path is special. */ if (unlikely(!len)) { if (empty) *empty = 1; if (!(flags & LOOKUP_EMPTY)) { putname(result); return ERR_PTR(-ENOENT); } } result->uptr = filename; result->aname = NULL; audit_getname(result); return result; } struct filename * getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } struct filename * getname_kernel(const char * filename) { struct filename *result; int len = strlen(filename) + 1; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { result->name = (char *)result->iname; } else if (len <= PATH_MAX) { const size_t size = offsetof(struct filename, iname[1]); struct filename *tmp; tmp = kmalloc(size, GFP_KERNEL); if (unlikely(!tmp)) { __putname(result); return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; result = tmp; } else { __putname(result); return ERR_PTR(-ENAMETOOLONG); } memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; result->refcnt = 1; audit_getname(result); return result; } void putname(struct filename *name) { BUG_ON(name->refcnt <= 0); if (--name->refcnt > 0) return; if (name->name != name->iname) { __putname(name->name); kfree(name); } else __putname(name); } static int check_acl(struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(inode, acl, mask); } acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * This does the basic UNIX permission checking. * * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit, * for RCU walking. */ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; /* Are we the owner? If so, ACL's don't matter */ if (likely(uid_eq(current_fsuid(), inode->i_uid))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { if (in_group_p(inode->i_gid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. */ int generic_permission(struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /* * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; if (unlikely(mask & MAY_WRITE)) { /* * Nobody gets write access to an immutable file. */ if (IS_IMMUTABLE(inode)) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EACCES; } retval = do_inode_permission(inode, mask); if (retval) return retval; retval = devcgroup_inode_permission(inode, mask); if (retval) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags; unsigned seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; unsigned root_seq; int dfd; kuid_t dir_uid; umode_t dir_mode; } __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->dfd = dfd; p->name = name; p->path.mnt = NULL; p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void terminate_walk(struct nameidata *nd) { drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->flags & LOOKUP_ROOT_GRABBED) { path_put(&nd->root); nd->flags &= ~LOOKUP_ROOT_GRABBED; } } else { nd->flags &= ~LOOKUP_RCU; rcu_read_unlock(); } nd->depth = 0; nd->path.mnt = NULL; nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; return false; } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* * For scoped-lookups (where nd->root has been zeroed), we need to * restart the whole lookup from scratch -- because set_root() is wrong * for these lookups (nd->dfd is the root, not the filesystem root). */ if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED)) return false; /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT)) return true; nd->flags |= LOOKUP_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); return false; } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * @seq: seq number to check @dentry against * Returns: true on success, false on failure * * Similar to to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) goto out2; if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: rcu_read_unlock(); return false; out_dput: rcu_read_unlock(); dput(dentry); return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->flags & LOOKUP_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (error) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->flags |= LOOKUP_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->flags |= LOOKUP_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } int sysctl_protected_symlinks __read_mostly = 0; int sysctl_protected_hardlinks __read_mostly = 0; int sysctl_protected_fifos __read_mostly; int sysctl_protected_regular __read_mostly; /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { if (!sysctl_protected_symlinks) return 0; /* Allowed if owner and follower match. */ if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * Returns 0 if successful, -ve on error. */ int may_linkat(struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @dir_mode: mode bits of directory * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; if (likely(dir_mode & 0002) || (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { const char *operation = S_ISFIFO(inode->i_mode) ? "sticky_create_fifo" : "sticky_create_regular"; audit_log_path_denied(AUDIT_ANOM_CREAT, operation); return -EACCES; } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, 0); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, struct inode **inode, unsigned *seqp) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (likely(!(flags & DCACHE_MANAGED_DENTRY))) return true; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->flags |= LOOKUP_JUMPED; *seqp = read_seqcount_begin(&dentry->d_seq); *inode = dentry->d_inode; /* * We don't need to re-check ->d_seq after this * ->d_inode read - there will be an RCU delay * between mount hash removal and ->mnt_root * becoming unpinned. */ flags = dentry->d_flags; if (read_seqretry(&mount_lock, nd->m_seq)) return false; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path, struct inode **inode, unsigned int *seqp) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = *seqp; if (unlikely(!*inode)) return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; path->dentry = dentry; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV)) ret = -EXDEV; else nd->flags |= LOOKUP_JUMPED; } if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } else { *inode = d_backing_inode(path->dentry); *seqp = 0; /* out of RCU mode, so the value doesn't matter */ } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. */ static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; struct inode *dir = base->d_inode; if (dentry) return dentry; /* Don't create child dentry for a dead directory. */ if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } return dentry; } static struct dentry *lookup_fast(struct nameidata *nd, struct inode **inode, unsigned *seqp) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the inode matches * the dentry name information from lookup. */ *inode = d_backing_inode(dentry); if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) return ERR_PTR(-ECHILD); /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. * * The memory barrier in read_seqcount_begin of child is * enough, we can use __read_seqcount_retry here. */ if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) return ERR_PTR(-ECHILD); *seqp = seq; status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); if (unlikely(status == -ECHILD)) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name, &wq); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD || !try_to_unlazy(nd)) return err; } return inode_permission(nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, unsigned seq, int flags) { struct saved *last; const char *res; int error = reserve_stack(nd, link, seq); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (!(nd->flags & LOOKUP_RCU)) { touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. */ static const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry, struct inode *inode, unsigned seq) { struct path path; int err = handle_mounts(nd, dentry, &path, &inode, &seq); if (err < 0) return ERR_PTR(err); if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (!(nd->flags & LOOKUP_RCU)) { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = seq; return NULL; } if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink above matches inode */ if (read_seqcount_retry(&path.dentry->d_seq, seq)) return ERR_PTR(-ECHILD); } else { if (path.mnt == nd->path.mnt) mntget(path.mnt); } return pick_link(nd, &path, inode, seq, flags); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; *inodep = parent->d_inode; *seqp = read_seqcount_begin(&parent->d_seq); if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq))) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); return NULL; } static struct dentry *follow_dotdot(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } *seqp = 0; *inodep = parent->d_inode; return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); dget(nd->path.dentry); return NULL; } static const char *handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; struct inode *inode; unsigned seq; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (error) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd, &inode, &seq); else parent = follow_dotdot(nd, &inode, &seq); if (IS_ERR(parent)) return ERR_CAST(parent); if (unlikely(!parent)) error = step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq); else error = step_into(nd, WALK_NOFOLLOW, parent, inode, seq); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))) return ERR_PTR(-EAGAIN); if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))) return ERR_PTR(-EAGAIN); } } return NULL; } static const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; struct inode *inode; unsigned seq; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return step_into(nd, flags, dentry, inode, seq); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * Calculate the length and hash of the path component, and * return the "hash_len" as the result. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long a = 0, b, x = 0, y = (unsigned long)salt; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; do { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); return hashlen_create(end_name_hash(hash), len); } #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); while (*name=='/') name++; if (!*name) return 0; /* At this point we know we have a real path component. */ for(;;) { const char *link; u64 hash_len; int type; err = may_lookup(nd); if (err) return err; hash_len = hash_name(nd->path.dentry, name); type = LAST_NORM; if (name[0] == '.') switch (hashlen_len(hash_len)) { case 2: if (name[1] == '.') { type = LAST_DOTDOT; nd->flags |= LOOKUP_JUMPED; } break; case 1: type = LAST_DOT; } if (likely(type == LAST_NORM)) { struct dentry *parent = nd->path.dentry; nd->flags &= ~LOOKUP_JUMPED; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { struct qstr this = { { .hash_len = hash_len }, .name = name }; err = parent->d_op->d_hash(parent, &this); if (err < 0) return err; hash_len = this.hash_len; name = this.name; } } nd->last.hash_len = hash_len; nd->last.name = name; nd->last_type = type; name += hashlen_len(hash_len); if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (!depth) { nd->dir_uid = nd->inode->i_uid; nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->name->name; /* LOOKUP_CACHED requires RCU, ask caller to retry */ if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) return ERR_PTR(-EAGAIN); if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); nd->flags = flags | LOOKUP_JUMPED; nd->depth = 0; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ struct fd f = fdget_raw(nd->dfd); struct dentry *dentry; if (!f.file) return ERR_PTR(-EBADF); dentry = f.file->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) { fdput(f); return ERR_PTR(-ENOTDIR); } nd->path = f.file->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } fdput(f); } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (flags & LOOKUP_IS_SCOPED) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq)); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); if (unlikely(root)) { nd.root = *root; flags |= LOOKUP_ROOT; } set_nameidata(&nd, dfd, name); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); putname(name); return retval; } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } static struct filename *filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { int retval; struct nameidata nd; if (IS_ERR(name)) return name; set_nameidata(&nd, dfd, name); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } else { putname(name); name = ERR_PTR(retval); } restore_nameidata(); return name; } /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { struct filename *filename; struct dentry *d; struct qstr last; int type; filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path, &last, &type); if (IS_ERR(filename)) return ERR_CAST(filename); if (unlikely(type != LAST_NORM)) { path_put(path); putname(filename); return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); d = __lookup_hash(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); } putname(filename); return d; } int kern_path(const char *name, unsigned int flags, struct path *path) { return filename_lookup(AT_FDCWD, getname_kernel(name), flags, path, NULL); } EXPORT_SYMBOL(kern_path); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { struct path root = {.mnt = mnt, .dentry = dentry}; /* the first argument of filename_lookup() is ignored with root */ return filename_lookup(AT_FDCWD, getname_kernel(name), flags , path, &root); } EXPORT_SYMBOL(vfs_path_lookup); static int lookup_one_len_common(const char *name, struct dentry *base, int len, struct qstr *this) { this->name = name; this->len = len; this->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (unlikely(name[0] == '.')) { if (len < 2 || (len == 2 && name[1] == '.')) return -EACCES; } while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, this); if (err < 0) return err; } return inode_permission(base->d_inode, MAY_EXEC); } /** * try_lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) { struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); return lookup_dcache(&this, base, 0); } EXPORT_SYMBOL(try_lookup_one_len); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { struct dentry *dentry; struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0); return dentry ? dentry : __lookup_slow(&this, base, 0); } EXPORT_SYMBOL(lookup_one_len); /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { struct qstr this; int err; struct dentry *ret; err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); ret = lookup_dcache(&this, base, 0); if (!ret) ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_len_unlocked); /* * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_one_len_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { struct dentry *ret = lookup_one_len_unlocked(name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_positive_unlocked); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; struct qstr this = QSTR_INIT("pts", 3); if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; dput(parent); follow_down(path); return 0; } #endif int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { return filename_lookup(dfd, getname_flags(name, flags, empty), flags, path, NULL); } EXPORT_SYMBOL(user_path_at_empty); int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ static inline int may_create(struct inode *dir, struct dentry *child) { struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; s_user_ns = dir->i_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; return inode_permission(dir, MAY_WRITE | MAY_EXEC); } /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { struct dentry *p; if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } p = d_ancestor(p1, p2); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return p; } EXPORT_SYMBOL(lock_rename); void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } EXPORT_SYMBOL(unlock_rename); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * Umask stripping depends on whether or not the filesystem supports POSIX * ACLs. If the filesystem doesn't support it umask stripping is done directly * in here. If the filesystem does support POSIX ACLs umask stripping is * deferred until the filesystem calls posix_acl_create(). * * Returns: mode */ static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir)) mode &= ~current_umask(); return mode; } /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Note that it's currently valid for @type to be 0 if a directory is created. * Filesystems raise that flag individually and we need to check whether each * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a * non-zero type. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { mode = mode_strip_sgid(dir, mode); mode = mode_strip_umask(dir, mode); /* * Apply the vfs mandated allowed permission mask and set the type of * file to be created before we call into the filesystem. */ mode &= (mask_perms & ~S_IFMT); mode |= (type & S_IFMT); return mode; } int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode = vfs_prepare_mode(dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; error = dir->i_op->create(dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create(dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; } error = inode_permission(inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(inode)) return -EPERM; return 0; } static int handle_truncate(struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; /* * Refuse to truncate files with mandatory locks held on them. */ error = locks_verify_locked(filp); if (!error) error = security_path_truncate(path); if (!error) { error = do_truncate(path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; s_user_ns = dir->dentry->d_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; int error; if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; error = dir->i_op->atomic_open(dir, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { if (unlikely(dentry != file->f_path.dentry)) { dput(dentry); dentry = dget(file->f_path.dentry); } } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { if (file->f_path.dentry) { dput(dentry); dentry = file->f_path.dentry; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } } if (error) { dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) return dentry; } if (d_in_lookup(dentry)) break; error = d_revalidate(dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ return dentry; } /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; mode = vfs_prepare_mode(dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(&nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { dentry = atomic_open(nd, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error); return dentry; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } return dentry; out_dput: dput(dentry); return ERR_PTR(error); } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; unsigned seq; struct inode *inode; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ if (unlikely(nd->last.name[nd->last.len])) return ERR_PTR(-EISDIR); } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be * dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write); if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED)) fsnotify_create(dir->d_inode, dentry); if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry, inode, seq); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(nd->dir_mode, nd->dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(&nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; int error; /* we want directory to be writable */ error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; mode = vfs_prepare_mode(dir, mode, mode, mode); error = dir->i_op->tmpfile(dir, child, mode); if (error) goto out_err; error = -ENOENT; inode = child->d_inode; if (unlikely(!inode)) goto out_err; if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } ima_post_create_tmpfile(inode); return child; out_err: dput(child); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_tmpfile); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct dentry *child; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); error = PTR_ERR(child); if (IS_ERR(child)) goto out2; dput(path.dentry); path.dentry = child; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; error = finish_open(file, child, NULL); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; set_nameidata(&nd, dfd, pathname); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; struct filename *filename; int flags = op->lookup_flags | LOOKUP_ROOT; nd.root.mnt = mnt; nd.root.dentry = dentry; if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); filename = getname_kernel(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); putname(filename); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; int type; int err2; int error; bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); /* * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any * other flags passed in are ignored! */ lookup_flags &= LOOKUP_REVAL; name = filename_parentat(dfd, name, lookup_flags, path, &last, &type); if (IS_ERR(name)) return ERR_CAST(name); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* * Do the final lookup. */ lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path->dentry, lookup_flags); if (IS_ERR(dentry)) goto unlock; error = -EEXIST; if (d_is_positive(dentry)) goto fail; /* * Special case - lookup gave negative, but... we had foo/bar/ * From the vfs_mknod() POV we just have a negative dentry - * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ if (unlikely(!is_dir && last.name[last.len])) { error = -ENOENT; goto fail; } if (unlikely(err2)) { error = err2; goto fail; } putname(name); return dentry; fail: dput(dentry); dentry = ERR_PTR(error); unlock: inode_unlock(path->dentry->d_inode); if (!err2) mnt_drop_write(path->mnt); out: path_put(path); putname(name); return dentry; } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname_kernel(pathname), path, lookup_flags); } EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) { dput(dentry); inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname(pathname), path, lookup_flags); } EXPORT_SYMBOL(user_path_create); int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create(dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; mode = vfs_prepare_mode(dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = dir->i_op->mknod(dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } static long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) return error; retry: dentry = user_path_create(dfd, filename, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mknod(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(path.dentry->d_inode,dentry,mode,true); if (!error) ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); break; } out: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { return do_mknodat(dfd, filename, mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { return do_mknodat(AT_FDCWD, filename, mode, dev); } int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error = may_create(dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) return error; if (!dir->i_op->mkdir) return -EPERM; mode = vfs_prepare_mode(dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; if (max_links && dir->i_nlink >= max_links) return -EMLINK; error = dir->i_op->mkdir(dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkdir); static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: dentry = user_path_create(dfd, pathname, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) error = vfs_mkdir(path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { return do_mkdirat(dfd, pathname, mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { return do_mkdirat(AT_FDCWD, pathname, mode); } int vfs_rmdir(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 1); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); long do_rmdir(int dfd, struct filename *name) { int error = 0; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; goto exit1; case LAST_DOT: error = -EINVAL; goto exit1; case LAST_ROOT: error = -EBUSY; goto exit1; } error = mnt_want_write(path.mnt); if (error) goto exit1; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit2; if (!dentry->d_inode) { error = -ENOENT; goto exit3; } error = security_path_rmdir(&path, dentry); if (error) goto exit3; error = vfs_rmdir(path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } putname(name); return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { return do_rmdir(AT_FDCWD, getname(pathname)); } /** * vfs_unlink - unlink a filesystem object * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_mutex. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete(dir, dentry, 0); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(target, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { fsnotify_unlink(dir, dentry); } else if (!error) { fsnotify_link_count(target); d_delete_notify(dir, dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_mutex. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ long do_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; struct inode *inode = NULL; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); error = -EISDIR; if (type != LAST_NORM) goto exit1; error = mnt_want_write(path.mnt); if (error) goto exit1; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ if (last.name[last.len]) goto slashes; inode = dentry->d_inode; if (d_is_negative(dentry)) goto slashes; ihold(inode); error = security_path_unlink(&path, dentry); if (error) goto exit2; error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); exit2: dput(dentry); } inode_unlock(path.dentry->d_inode); if (inode) iput(inode); /* truncate the inode here */ inode = NULL; if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; inode = NULL; goto retry; } putname(name); return error; slashes: if (d_is_negative(dentry)) error = -ENOENT; else if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; goto exit2; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; if (flag & AT_REMOVEDIR) return do_rmdir(dfd, getname(pathname)); return do_unlinkat(dfd, getname(pathname)); } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { return do_unlinkat(AT_FDCWD, getname(pathname)); } int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->symlink) return -EPERM; error = security_inode_symlink(dir, dentry, oldname); if (error) return error; error = dir->i_op->symlink(dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); static long do_symlinkat(const char __user *oldname, int newdfd, const char __user *newname) { int error; struct filename *from; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; from = getname(oldname); if (IS_ERR(from)) return PTR_ERR(from); retry: dentry = user_path_create(newdfd, newname, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putname; error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out_putname: putname(from); return error; } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_symlinkat(oldname, newdfd, newname); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { return do_symlinkat(oldname, AT_FDCWD, newname); } /** * vfs_link - create a new link * @old_dentry: object to be linked * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_mutex * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; int error; if (!inode) return -ENOENT; error = may_create(dir, new_dentry); if (error) return error; if (dir->i_sb != inode->i_sb) return -EXDEV; /* * A link to an append-only or immutable file cannot be created. */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; /* * Updating the link count 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; if (!dir->i_op->link) return -EPERM; if (S_ISDIR(inode->i_mode)) return -EPERM; error = security_inode_link(old_dentry, dir, new_dentry); if (error) return error; inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { error = try_break_deleg(inode, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } if (!error && (inode->i_state & I_LINKABLE)) { spin_lock(&inode->i_lock); inode->i_state &= ~I_LINKABLE; spin_unlock(&inode->i_lock); } inode_unlock(inode); if (!error) fsnotify_link(dir, inode, new_dentry); return error; } EXPORT_SYMBOL(vfs_link); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ static int do_linkat(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, int flags) { struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; int how = 0; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; /* * To use null names we require CAP_DAC_READ_SEARCH * This ensures that not everyone will be able to create * handlink using the passed filedescriptor. */ if (flags & AT_EMPTY_PATH) { if (!capable(CAP_DAC_READ_SEARCH)) return -ENOENT; how = LOOKUP_EMPTY; } if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: error = user_path_at(olddfd, oldname, how, &old_path); if (error) return error; new_dentry = user_path_create(newdfd, newname, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; error = may_linkat(&old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); goto retry; } } if (retry_estale(error, how)) { path_put(&old_path); how |= LOOKUP_REVAL; goto retry; } out: path_put(&old_path); return error; } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { return do_linkat(olddfd, oldname, newdfd, newname, flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } /** * vfs_rename - rename a filesystem object * @old_dir: parent of source * @old_dentry: source * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, struct inode **delegated_inode, unsigned int flags) { int error; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; error = may_delete(old_dir, old_dentry, is_dir); if (error) return error; if (!target) { error = may_create(new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) error = may_delete(new_dir, new_dentry, is_dir); else error = may_delete(new_dir, new_dentry, new_is_dir); } if (error) return error; if (!old_dir->i_op->rename) return -EPERM; /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { if (is_dir) { error = inode_permission(source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { error = inode_permission(target, MAY_WRITE); if (error) return error; } } error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) return error; take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* * Lock children. * The source subdirectory needs to be locked on cross-directory * rename or cross-directory exchange since its parent changes. * The target subdirectory needs to be locked on cross-directory * exchange due to parent change and on any rename due to becoming * a victim. * Non-directories need locking in all cases (for NFS reasons); * they get locked after any subdirectories (in inode address order). * * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ lock_old_subdir = new_dir != old_dir; lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); if (is_dir) { if (lock_old_subdir) inode_lock_nested(source, I_MUTEX_CHILD); if (target && (!new_is_dir || lock_new_subdir)) inode_lock(target); } else if (new_is_dir) { if (lock_new_subdir) inode_lock_nested(target, I_MUTEX_CHILD); inode_lock(source); } else { lock_two_nondirectories(source, target); } error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) goto out; if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && old_dir->i_nlink >= max_links) goto out; } if (!is_dir) { error = try_break_deleg(source, delegated_inode); if (error) goto out; } if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; if (!(flags & RENAME_EXCHANGE) && target) { if (is_dir) { shrink_dcache_parent(new_dentry); target->i_flags |= S_DEAD; } dont_mount(new_dentry); detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE)) d_move(old_dentry, new_dentry); else d_exchange(old_dentry, new_dentry); } out: if (!is_dir || lock_old_subdir) inode_unlock(source); if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } release_dentry_name_snapshot(&old_name); return error; } EXPORT_SYMBOL(vfs_rename); int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) goto put_both; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) goto put_both; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: from = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); if (IS_ERR(from)) { error = PTR_ERR(from); goto put_new; } to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, &new_type); if (IS_ERR(to)) { error = PTR_ERR(to); goto exit1; } error = -EXDEV; if (old_path.mnt != new_path.mnt) goto exit2; error = -EBUSY; if (old_type != LAST_NORM) goto exit2; if (flags & RENAME_NOREPLACE) error = -EEXIST; if (new_type != LAST_NORM) goto exit2; error = mnt_want_write(old_path.mnt); if (error) goto exit2; retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; /* source must exist */ error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; error = -EEXIST; if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) goto exit5; if (flags & RENAME_EXCHANGE) { error = -ENOENT; if (d_is_negative(new_dentry)) goto exit5; if (!d_is_dir(new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) goto exit5; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) goto exit5; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) goto exit5; } /* source should not be ancestor of target */ error = -EINVAL; if (old_dentry == trap) goto exit5; /* target should not be an ancestor of source */ if (!(flags & RENAME_EXCHANGE)) error = -ENOTEMPTY; if (new_dentry == trap) goto exit5; error = security_path_rename(&old_path, old_dentry, &new_path, new_dentry, flags); if (error) goto exit5; error = vfs_rename(old_path.dentry->d_inode, old_dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode, flags); exit5: dput(new_dentry); exit4: dput(old_dentry); exit3: unlock_rename(new_path.dentry, old_path.dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(old_path.mnt); exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); exit1: path_put(&old_path); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } put_both: if (!IS_ERR(from)) putname(from); put_new: if (!IS_ERR(to)) putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0); } int readlink_copy(char __user *buffer, int buflen, const char *link) { int len = PTR_ERR(link); if (IS_ERR(link)) goto out; len = strlen(link); if (len > (unsigned) buflen) len = buflen; if (copy_to_user(buffer, link, len)) len = -EFAULT; out: return len; } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); DEFINE_DELAYED_CALL(done); const char *link; int res; if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); if (!d_is_symlink(dentry)) return -EINVAL; spin_lock(&inode->i_lock); inode->i_opflags |= IOP_DEFAULT_READLINK; spin_unlock(&inode->i_lock); } link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link); do_delayed_call(&done); return res; } EXPORT_SYMBOL(vfs_readlink); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { const char *res = ERR_PTR(-EINVAL); struct inode *inode = d_inode(dentry); if (d_is_symlink(dentry)) { res = ERR_PTR(security_inode_readlink(dentry)); if (!res) res = inode->i_op->get_link(dentry, inode, done); } return res; } EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { char *kaddr; struct page *page; struct address_space *mapping = inode->i_mapping; if (!dentry) { page = find_get_page(mapping, 0); if (!page) return ERR_PTR(-ECHILD); if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } } else { page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) return (char*)page; } set_delayed_call(callback, page_put_link, page); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); kaddr = page_address(page); nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } EXPORT_SYMBOL(page_get_link); void page_put_link(void *arg) { put_page(arg); } EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { DEFINE_DELAYED_CALL(done); int res = readlink_copy(buffer, buflen, page_get_link(dentry, d_inode(dentry), &done)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(page_readlink); /* * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS */ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; unsigned int flags = 0; if (nofs) flags |= AOP_FLAG_NOFS; retry: err = pagecache_write_begin(NULL, mapping, 0, len-1, flags, &page, &fsdata); if (err) goto fail; memcpy(page_address(page), symname, len-1); err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); if (err < 0) goto fail; if (err < len-1) goto retry; mark_inode_dirty(inode); return 0; fail: return err; } EXPORT_SYMBOL(__page_symlink); int page_symlink(struct inode *inode, const char *symname, int len) { return __page_symlink(inode, symname, len, !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG #define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->close_on_exec); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *__fcheck_files(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) { fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); } return NULL; } static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return __fcheck_files(files, fd); } /* * Check whether the specified fd has an open file. */ #define fcheck(fd) fcheck_files(current->files, fd) struct task_struct; struct files_struct *get_files_struct(struct task_struct *); void put_files_struct(struct files_struct *fs); void reset_files_struct(struct files_struct *); int unshare_files(struct files_struct **); struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags); extern void __fd_install(struct files_struct *files, unsigned int fd, struct file *file); extern int __close_fd(struct files_struct *files, unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern int close_fd_get_file(unsigned int fd, struct file **res); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_H #define _LINUX_WAIT_H /* * Linux wait queue related types and methods */ #include <linux/list.h> #include <linux/stddef.h> #include <linux/spinlock.h> #include <asm/current.h> #include <uapi/linux/wait.h> typedef struct wait_queue_entry wait_queue_entry_t; typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_BOOKMARK 0x04 #define WQ_FLAG_CUSTOM 0x08 #define WQ_FLAG_DONE 0x10 /* * A single wait-queue entry structure: */ struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; struct list_head entry; }; struct wait_queue_head { spinlock_t lock; struct list_head head; }; typedef struct wait_queue_head wait_queue_head_t; struct task_struct; /* * Macros for declaration and initialisaton of the datatypes */ #define __WAITQUEUE_INITIALIZER(name, tsk) { \ .private = tsk, \ .func = default_wake_function, \ .entry = { NULL, NULL } } #define DECLARE_WAITQUEUE(name, tsk) \ struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = { &(name).head, &(name).head } } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); #define init_waitqueue_head(wq_head) \ do { \ static struct lock_class_key __key; \ \ __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { wq_entry->flags = 0; wq_entry->private = p; wq_entry->func = default_wake_function; } static inline void init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { wq_entry->flags = 0; wq_entry->private = NULL; wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like:: * * CPU0 - waker CPU1 - waiter * * for (;;) { * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (waitqueue_active(wq_head)) if (@cond) * wake_up(wq_head); break; * schedule(); * } * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll * observe an empty wait list while the waiter might not observe @cond. * * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ static inline int waitqueue_active(struct wait_queue_head *wq_head) { return !list_empty(&wq_head->head); } /** * wq_has_single_sleeper - check if there is only one sleeper * @wq_head: wait queue head * * Returns true of wq_head has only one sleeper on the list. * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) { return list_is_singular(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier should be paired with one on the * waiting side. */ smp_mb(); return waitqueue_active(wq_head); } extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add(&wq_entry->entry, &wq_head->head); } /* * Used for wake-one threads: */ static inline void __add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq_head, wq_entry); } static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void __add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_del(&wq_entry->entry); } void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, unsigned int mode, void *key, wait_queue_entry_t *bookmark); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) #define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE) /* * Wakeup macros to be used to report events to the targets. */ #define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m)) #define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m)) #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, poll_to_key(m)) #define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) /** * wake_up_pollfree - signal that a polled waitqueue is going away * @wq_head: the wait queue head * * In the very rare cases where a ->poll() implementation uses a waitqueue whose * lifetime is tied to a task rather than to the 'struct file' being polled, * this function must be called before the waitqueue is freed so that * non-blocking polls (e.g. epoll) are notified that the queue is going away. * * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. */ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) { /* * For performance reasons, we don't always take the queue lock here. * Therefore, we might race with someone removing the last entry from * the queue, and proceed while they still hold the queue lock. * However, rcu_read_lock() is required to be held in such cases, so we * can safely proceed with an RCU-delayed free. */ if (waitqueue_active(wq_head)) __wake_up_pollfree(wq_head); } #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ if (__cond && !__ret) \ __ret = 1; \ __cond || !__ret; \ }) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ state == TASK_INTERRUPTIBLE || state == TASK_KILLABLE) \ extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret * variable when used from the wait_event_*() macros. * * This is so that both can use the ___wait_cond_timeout() construct * to wrap the condition. * * The type inconsistency of the wait_event_*() __ret variable is also * on purpose; we use long where we can return timeout values and int * otherwise. */ #define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_entry __wq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ }) #define __wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_event(wq_head, condition); \ } while (0) #define __io_wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ #define io_wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __io_wait_event(wq_head, condition); \ } while (0) #define __wait_event_freezable(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ freezable_schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_freezable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable(wq_head, condition); \ __ret; \ }) #define __wait_event_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = freezable_schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ #define wait_event_freezable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ #define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_interruptible(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible(wq_head, condition); \ __ret; \ }) #define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ #define wait_event_interruptible_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_interruptible_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ ({ \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \ } \ \ __ret = ___wait_event(wq_head, condition, state, 0, 0, \ if (!__t.task) { \ __ret = -ETIME; \ break; \ } \ schedule()); \ \ hrtimer_cancel(&__t.timer); \ destroy_hrtimer_on_stack(&__t.timer); \ __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ #define wait_event_hrtimeout(wq_head, condition, timeout) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ #define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ ({ \ long __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq, condition, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define __wait_event_interruptible_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) #define wait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_killable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) #define wait_event_killable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_freezable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ freezable_schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable_exclusive(wq, condition); \ __ret; \ }) /** * wait_event_idle - wait for a condition without contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \ } while (0) /** * wait_event_idle_exclusive - wait for a condition with contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle_exclusive(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \ } while (0) #define __wait_event_idle_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 1, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\ __ret; \ }) extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); #define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ __ret = fn(&(wq), &__wait); \ if (__ret) \ break; \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ __ret; \ }) /** * wait_event_interruptible_locked - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** * wait_event_killable - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_killable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable(wq_head, condition); \ __ret; \ }) #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a kill signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a kill signal. * * Only kill signals interrupt this process. */ #define wait_event_killable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_killable_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_lock_irq_cmd - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ #define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** * wait_event_lock_irq - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ #define wait_event_lock_irq(wq_head, condition, lock) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) #define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock, cmd); \ __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock,); \ __ret; \ }) #define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ #define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_FUNC(name, function) \ struct wait_queue_entry name = { \ .private = current, \ .func = function, \ .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) #define init_wait(wait) \ do { \ (wait)->private = current; \ (wait)->func = autoremove_wake_function; \ INIT_LIST_HEAD(&(wait)->entry); \ (wait)->flags = 0; \ } while (0) bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg); #endif /* _LINUX_WAIT_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> #include <linux/gfp.h> #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key); #define percpu_counter_init(fbc, value, gfp) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init(fbc, value, gfp, &__key); \ }) void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { fbc->count = amount; return 0; } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { preempt_disable(); fbc->count += amount; preempt_enable(); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } static inline void percpu_counter_sync(struct percpu_counter *fbc) { } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H #include <asm/processor.h> #if defined(__KERNEL__) && !defined(__ASSEMBLY__) #include <asm/asm.h> #include <linux/bitops.h> #include <asm/alternative.h> enum cpuid_leafs { CPUID_1_EDX = 0, CPUID_8000_0001_EDX, CPUID_8086_0001_EDX, CPUID_LNX_1, CPUID_1_ECX, CPUID_C000_0001_EDX, CPUID_8000_0001_ECX, CPUID_LNX_2, CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, CPUID_LNX_4, CPUID_7_1_EAX, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, CPUID_LNX_5, NR_CPUID_WORDS, }; #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] #else #define X86_CAP_FMT "%d:%d" #define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31) #endif /* * In order to save room, we index into this array by doing * X86_BUG_<name> - NCAPINTS*32. */ extern const char * const x86_bug_flags[NBUGINTS*32]; #define test_cpu_cap(c, bit) \ arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) /* * There are 32 bits/features in each mask word. The high bits * (selected with (bit>>5) give us the word number and the low 5 * bits give us the bit/feature number inside the word. * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can * see if it is set in the mask word. */ #define CHECK_BIT_IN_MASK_WORD(maskname, word, bit) \ (((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word )) /* * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all * header macros which use NCAPINTS need to be changed. The duplicated macro * use causes the compiler to issue errors for all headers so that all usage * sites can be corrected. */ #define REQUIRED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 1, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 2, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 3, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 4, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 5, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 6, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 7, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 8, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 9, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 1, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 2, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 3, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 4, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 5, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 6, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 7, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 8, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 9, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, \ (unsigned long __percpu *)&cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel * infrastructure to be used. It may *not* directly test the CPU * itself. Use the cpu_has() family if you want true runtime * testing of CPU features, like in hypervisor code where you are * supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) extern void setup_clear_cpu_cap(unsigned int bit); extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_cap(bit) do { \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) #if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) /* * Workaround for the sake of BPF compilation which utilizes kernel * headers, but clang does not support ASM GOTO and fails the build. */ #ifndef __BPF_TRACING__ #warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments" #endif #define static_cpu_has(bit) boot_cpu_has(bit) #else /* * Static testing of CPU features. Used the same as boot_cpu_has(). It * statically patches the target code for additional performance. Use * static_cpu_has() only in fast paths, where every cycle counts. Which * means that the boot_cpu_has() variant is already fast enough for the * majority of cases and you should stick to using it as it is generally * only two instructions: a RIP-relative MOV and a TEST. */ static __always_inline bool _static_cpu_has(u16 bit) { asm_volatile_goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".section .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum],%[cap_byte]\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".previous\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; t_no: return false; } #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) #endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) #define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) #define cpu_have_feature boot_cpu_has #define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ #endif /* _ASM_X86_CPUFEATURE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 | /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/processor.h> static inline int phys_addr_valid(resource_size_t addr) { #ifdef CONFIG_PHYS_ADDR_T_64BIT return !(addr >> boot_cpu_data.x86_phys_bits); #else return 1; #endif } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { /* * Those arches which don't have hw access flag feature need to * implement their own helper. By default, "true" means pagefault * will be hit on old pte. */ return true; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { if (current->rss_stat.count[i]) { add_mm_counter(mm, i, current->rss_stat.count[i]); current->rss_stat.count[i] = 0; } } current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { struct task_struct *task = current; if (likely(task->mm == mm)) task->rss_stat.count[member] += val; else add_mm_counter(mm, member, val); } #define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) #define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) /* sync counter once per 64 page faults */ #define TASK_RSS_EVENTS_THRESH (64) static void check_sync_rss_stat(struct task_struct *task) { if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) static void check_sync_rss_stat(struct task_struct *task) { } #endif /* SPLIT_RSS_COUNTING */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); pmd_populate(mm, pmd, new); new = NULL; } spin_unlock(ptl); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; if (current->mm == mm) sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The disadvantage is that pages are refcounted * (which can be slower and simply not an option for some PFNMAP users). The * advantage is that we don't have to follow the strict linearity rule of * PFNMAP mappings in order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* * There is no pmd_special() but there may be special pmds, e.g. * in a direct-access (dax) mapping, so let's just replicate the * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #endif /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return entry.val; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = device_private_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ get_page(page); rss[mm_counter(page)]++; page_dup_rmap(page, false); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_write_device_private_entry(entry) && is_cow_mapping(vm_flags)) { make_device_private_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page if necessary. * * NOTE! The usual case is that this doesn't need to do * anything, and can just return a positive value. That * will let the caller know that it can just increase * the page refcount and re-use the pte the traditional * way. * * But _if_ we need to copy it because it needs to be * pinned in the parent (and the child should get its own * copy rather than just a reference to the same page), * we'll do that here and return zero to let the caller * know we're done. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; if (!is_cow_mapping(src_vma->vm_flags)) return 1; /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy * the page immediately so that we'll always guarantee * the pinned page won't be randomly replaced in the * future. * * The page pinning checks are just "has this mm ever * seen pinning", along with the (inexact) check of * the page count. That might give false positives for * for pinning, but it will work correctly. */ if (likely(!atomic_read(&src_mm->has_pinned))) return 1; if (likely(!page_maybe_dma_pinned(page))) return 1; /* * The vma->anon_vma of the child process may be NULL * because the entire vma does not contain anonymous pages. * A BUG will occur when the copy_present_page() passes * a copy of a non-anonymous page of that vma to the * page_add_new_anon_rmap() to set up new anonymous rmap. * Return 1 if the page is not an anonymous page. */ if (!PageAnon(page)) return 1; new_page = *prealloc; if (!new_page) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); page_add_new_anon_rmap(new_page, dst_vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, *src_pte)) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } /* * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page * is required to copy this pte. */ static inline int copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc) { struct mm_struct *src_mm = src_vma->vm_mm; unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, pte, page); if (retval <= 0) return retval; get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; } /* * If it's a COW mapping, write protect it both * in the parent and the child */ if (is_cow_mapping(vm_flags) && pte_write(pte)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } /* * If it's a shared mapping, mark it clean in * the child */ if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static inline struct page * page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr) { struct page *new_page; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); if (!new_page) return NULL; if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } cgroup_throttle_swaprate(new_page, GFP_KERNEL); return new_page; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct page *prealloc = NULL; again: progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } if (unlikely(!pte_present(*src_pte))) { entry.val = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (entry.val) break; progress += 8; continue; } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. */ if (unlikely(ret == -EAGAIN)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ put_page(prealloc); prealloc = NULL; } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (entry.val) { if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret) { WARN_ON_ONCE(ret != -EAGAIN); prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; /* We've captured and resolved the error. Reset, try again. */ ret = 0; } if (addr != end) goto again; out: if (unlikely(prealloc)) put_page(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; /* * Don't copy ptes where a page fault will fill them correctly. * Fork becomes much lighter when there are big shared or private * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && !src_vma->anon_vma) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ mmap_assert_write_locked(src_mm); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; /* Or, we zap COWed pages only if the caller wants to */ return !details->check_mapping; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { struct page *page; page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping && details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; addr += PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry)) { struct page *page = device_private_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping != page_rmapping(page)) continue; } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; page_remove_rmap(page, false); put_page(page); continue; } if (!non_swap_entry(entry)) { /* Genuine swap entry, hence a private anon page */ if (!should_zap_cows(details)) continue; rss[MM_SWAPENTS]--; } else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); if (details && details->check_mapping && details->check_mapping != page_rmapping(page)) continue; rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; tlb_flush_mmu(tlb); } if (addr != end) { cond_resched(); goto again; } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } else if (details && details->single_page && PageTransCompound(details->single_page) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is * none or trans huge it can change under us. This is * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); next: cond_resched(); } while (pmd++, addr = next, addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) unmap_single_vma(&tlb, vma, start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, start, range.end); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, address, range.end); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static int validate_page_before_insert(struct page *page) { if (PageAnon(page) || PageSlab(page) || page_has_type(page)) return -EINVAL; flush_dcache_page(page); return 0; } static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); return 0; } /* * This is the old fallback for page remapping. * * For historical reasons, it only allows reserved pages. Only * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); if (err) return err; return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. Arch *must* define pte_index. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } #endif /* ifdef pte_index */ /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { #ifdef pte_index const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); if (err) break; } *num = pgcount - idx; return err; #endif /* ifdef pte_index */ } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } entry = pte_mkyoung(*pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * See vmf_insert_mixed_prot() for a discussion of the implication of using * a value of @pgprot different from that of @vma->vm_page_prot. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot, bool mkwrite) { int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } /** * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and * encryption bits different than those of @vma->vm_page_prot, because * the caching- or encryption mode may not be known at mmap() time. * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot) { return __vm_insert_mixed(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_mixed_prot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; unsigned long remap_pfn = pfn; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } err = track_pfn_remap(vma, &prot, remap_pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) break; } while (pgd++, addr = next, addr != end); if (err) untrack_pfn(vma, remap_pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte; int err = 0; spinlock_t *ptl; if (create) { pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(*pte)) { err = fn(pte++, addr, data); if (err) break; } } while (addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_huge(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (create || !pmd_none_or_clear_bad(pmd)) { err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (create || !pud_none_or_clear_bad(pud)) { err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (create || !p4d_none_or_clear_bad(p4d)) { err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (!create && pgd_none_or_clear_bad(pgd)) continue; err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spinlock_t *ptl = pte_lockptr(mm, pmd); spin_lock(ptl); same = pte_same(*page_table, orig_pte); spin_unlock(ptl); } #endif pte_unmap(page_table); return same; } static inline bool cow_user_page(struct page *dst, struct page *src, struct vm_fault *vmf) { bool ret; void *kaddr; void __user *uaddr; bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { copy_user_highpage(dst, src, addr, vma); return true; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_atomic(dst); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache(vma, addr, vmf->pte); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (locked) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = true; pte_unlock: if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) { vm_fault_t ret; struct page *page = vmf->page; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { lock_page(page); if (!page->mapping) { unlock_page(page); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_PAGE(!PageLocked(page), page); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = set_page_dirty(page); VM_BUG_ON_PAGE(PageAnon(page), page); /* * Take a local copy of the address_space - page.mapping may be zeroed * by truncate after unlock_page(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = page_rmapping(page); unlock_page(page); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_RETRY; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * Handle the case of a page which we actually need to copy to a new page. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) goto oom; if (!cow_user_page(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. */ put_page(new_page); if (old_page) put_page(old_page); return 0; } } if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry. This will avoid a race condition * seen in the presence of one thread doing SMC and another * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * page_remove_rmap with the ptp_clear_flush above. * Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in page_remove_rmap. * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) put_page(new_page); pte_unmap_unlock(vmf->pte, vmf->ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above ptep_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); unlock_page(old_page); } put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); return VM_FAULT_OOM; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); return VM_FAULT_WRITE; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } tmp = finish_mkwrite_fault(vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { unlock_page(vmf->page); put_page(vmf->page); return tmp; } } else { wp_page_reuse(vmf); lock_page(vmf->page); } ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); return ret; } /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary * COW. * * We also mark the page dirty at this point even though the page will * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } /* * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ if (PageAnon(vmf->page)) { struct page *page = vmf->page; /* PageKsm() doesn't necessarily raise the page refcount */ if (PageKsm(page) || page_count(page) != 1) goto copy; if (!trylock_page(page)) goto copy; if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { unlock_page(page); goto copy; } /* * Ok, we've got the only map reference, and the only * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ unlock_page(page); wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } copy: /* * Ok, we need to copy. Oh, well.. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = details->first_index; if (zba < vba) zba = vba; zea = details->last_index; if (zea > vea) zea = vea; unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_page() - Unmap single page from processes. * @page: The locked page to be unmapped. * * Unmap this page from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a page, it may find that * the page has been remapped again: and then uses unmap_mapping_page() * to unmap it finally. */ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); details.check_mapping = mapping; details.first_index = page->index; details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; details.check_mapping = even_cows ? NULL : mapping; details.first_index = start; details.last_index = start + nr - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_private_entry(entry)) { vmf->page = device_private_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { struct swap_info_struct *si = swp_swap_info(entry); if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (page) { int err; __SetPageLocked(page); __SetPageSwapBacked(page); set_page_private(page, entry.val); /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); if (err) { ret = VM_FAULT_OOM; goto out_page; } shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(page, shadow); lru_cache_add(page); swap_readpage(page, true); } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = page; } if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not * release the swapcache from under us. The page pin, and pte_same * test below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not changed. */ if (unlikely((!PageSwapCache(page) || page_private(page) != entry.val)) && swapcache) goto out_page; page = ksm_might_need_to_copy(page, vma, vmf->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* * The page isn't present yet, go ahead with the fault. * * Be careful about the sequence of operations here. * To get its accounting right, reuse_swap_page() must be called * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. */ inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) { pte = pte_mkuffd_wp(pte); pte = pte_wrprotect(pte); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); vmf->orig_pte = pte; /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); } swap_free(entry); if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ unlock_page(swapcache); put_page(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); out_release: put_page(page); if (page != swapcache && swapcache) { unlock_page(swapcache); put_page(swapcache); } return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* See the comment in pte_alloc_one_map() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!page) goto oom; if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_cache(vma, vmf->address, vmf->pte); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: put_page(page); goto unlock; oom_free_page: put_page(page); oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; if (unlikely(PageHWPoison(vmf->page))) { struct page *page = vmf->page; vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(page)) unmap_mapping_pages(page_mapping(page), page->index, 1, false); /* Retry if a clean page was removed from the cache. */ if (invalidate_inode_page(page)) poisonret = VM_FAULT_NOPAGE; unlock_page(page); } put_page(page); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf->page); else VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); return ret; } /* * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. * If we check pmd_trans_unstable() first we will trip the bad_pmd() check * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. */ static int pmd_devmap_trans_unstable(pmd_t *pmd) { return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); } static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (!pmd_none(*vmf->pmd)) goto map_pte; if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { spin_unlock(vmf->ptl); goto map_pte; } mm_inc_nr_ptes(vma->vm_mm); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); spin_unlock(vmf->ptl); vmf->prealloc_pte = NULL; } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; } map_pte: /* * If a huge pmd materialized under us just retry later. Use * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge * under us and then back to pmd_none, as a result of MADV_DONTNEED * running immediately after a huge pmd fault in a different thread of * this mm, in turn leading to a misleading pmd_trans_huge() retval. * All we have to ensure is that it is a regular pmd that we can walk * with pte_offset_map() and we can do that through an atomic read in * C, which is what pmd_trans_unstable() provides. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; /* * At this point we know that our vmf->pmd points to a page of ptes * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() * for the duration of the fault. If a racing MADV_DONTNEED runs and * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still * be valid and we will re-check to make sure the vmf->pte isn't * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); return 0; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) return ret; page = compound_head(page); if (compound_order(page) != HPAGE_PMD_ORDER) return ret; /* * Archs like ppc64 need additonal space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); page_add_file_rmap(page, true); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { BUILD_BUG(); return 0; } #endif /** * alloc_set_pte - setup new PTE entry for given page and add reverse page * mapping. If needed, the function allocates page table or use pre-allocated. * * @vmf: fault environment * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on * return. * * Target users are page handler itself and implementations of * vm_ops->map_pages. * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; pte_t entry; vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (!vmf->pte) { ret = pte_alloc_one_map(vmf); if (ret) return ret; } /* Re-check under ptl */ if (unlikely(!pte_none(*vmf->pte))) { update_mmu_tlb(vma, vmf->address, vmf->pte); return VM_FAULT_NOPAGE; } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, vmf->address, vmf->pte); return 0; } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct page *page; vm_fault_t ret = 0; /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vmf->vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vmf->vma->vm_flags & VM_SHARED)) ret = check_stable_address_space(vmf->vma->vm_mm); if (!ret) ret = alloc_set_pte(vmf, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_bytes __read_mostly = rounddown_pow_of_two(65536); #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_bytes; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; if (val > PAGE_SIZE) fault_around_bytes = rounddown_pow_of_two(val); else fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function is called with the page table lock taken. In the split ptlock * case the page table lock only protects only those entries which belong to * the page table corresponding to the fault address. * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * * fault_around_bytes defines how many bytes we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_bytes rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { unsigned long address = vmf->address, nr_pages, mask; pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; vm_fault_t ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; vmf->address = max(address & mask, vmf->vma->vm_start); off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* * end_pgoff is either the end of the page table, the end of * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) goto out; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); /* Huge page is mapped? Page fault is solved */ if (pmd_trans_huge(*vmf->pmd)) { ret = VM_FAULT_NOPAGE; goto out; } /* ->map_pages() haven't done anything useful. Cold page cache? */ if (!vmf->pte) goto out; /* check if the page fault is solved */ vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); if (!pte_none(*vmf->pte)) ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); out: vmf->address = address; vmf->pte = NULL; return ret; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { ret = do_fault_around(vmf); if (ret) return ret; } ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); unlock_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) put_page(vmf->page); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!vmf->cow_page) return VM_FAULT_OOM; if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); __SetPageUptodate(vmf->cow_page); ret |= finish_fault(vmf); unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: put_page(vmf->cow_page); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { unlock_page(vmf->page); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { unlock_page(vmf->page); put_page(vmf->page); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { /* * If we find a migration pmd entry or a none pmd entry, which * should never happen, return SIGBUS */ if (unlikely(!pmd_present(*vmf->pmd))) ret = VM_FAULT_SIGBUS; else { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(*vmf->pte))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(page, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; bool migrated = false; pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. */ vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; } /* * Make it present again, Depending on how arch implementes non * accessible ptes, some can allow access by kernel mode. */ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); if (!page) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* TODO: handle PTE-mapped THP */ if (PageCompound(page)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!pte_write(pte)) flags |= TNF_NO_GROUP; /* * Flag if the page is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); pte_unmap_unlock(vmf->pte, vmf->ptl); if (target_nid == NUMA_NO_NODE) { put_page(page); goto out; } /* Migrate to the requested node */ migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; } else flags |= TNF_MIGRATE_FAIL; out: if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) { if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf, orig_pmd); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) return VM_FAULT_FALLBACK; if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; } else { /* See comment in pte_alloc_one_map() */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge * pmd from under us anymore at this point because we hold the * mmap_lock read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; /* * some architectures can have larger ptes than wordsize, * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic * accesses. The code below just needs a consistent view * for the ifs and we later double check anyway with the * ptl lock held. So here a barrier will do. */ barrier(); if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(*vmf->pte, entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(vmf); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* NUMA case for anonymous PUDs would go here */ if (dirty && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pmd_t orig_pmd = *vmf.pmd; barrier(); if (unlikely(is_swap_pmd(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); if (is_pmd_migration_entry(orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); if (dirty && !pmd_write(orig_pmd)) { ret = wp_huge_pmd(&vmf, orig_pmd); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf, orig_pmd); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accountings * * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accountings. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* * We don't do accounting for some specific faults: * * - Unsuccessful faults (e.g. when the address wasn't valid). That * includes arch_vma_access_permitted() failing before reaching here. * So this is not a "this many hardware page faults" counter. We * should use the hw profiling for that. * * - Incomplete faults (VM_FAULT_RETRY). They will only be counted * once they're completed. */ if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; __set_current_state(TASK_RUNNING); count_vm_event(PGFAULT); count_memcg_event_mm(vma->vm_mm, PGFAULT); /* do counter updates before entering really critical section. */ check_sync_rss_stat(current); if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) return VM_FAULT_SIGSEGV; /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } mm_account_fault(regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ p4d_free(mm, new); else pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) goto out; pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); if (pmd_huge(*pmd)) { if (!pmdpp) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PMD_MASK, (address & PMD_MASK) + PMD_SIZE); mmu_notifier_invalidate_range_start(range); } *ptlp = pmd_lock(mm, pmd); if (pmd_huge(*pmd)) { *pmdpp = pmd; return 0; } spin_unlock(*ptlp); if (range) mmu_notifier_invalidate_range_end(range); } if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PAGE_MASK, (address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(range); } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; *ptepp = ptep; return 0; unlock: pte_unmap_unlock(ptep, *ptlp); if (range) mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } /** * follow_pte - look up PTE at a user virtual address * @mm: the mm_struct of the target address space * @address: user virtual address * @ptepp: location to store found PTE * @ptlp: location to store the lock for the PTE * * On a successful return, the pointer to the PTE is stored in @ptepp; * the corresponding lock is taken and its location is stored in @ptlp. * The contents of the PTE are only stable until @ptlp is released; * any further use, if any, must be protected against invalidation * with MMU notifiers. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read. * * KVM uses this function. While it is arguably less bad than ``follow_pfn``, * it is not a good general-purpose API. * * Return: zero on success, -ve otherwise. */ int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); } EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping * @address: user virtual address * @pfn: location to store found PFN * * Only IO mappings and raw PFN mappings are allowed. * * This function does not allow the caller to read the permissions * of the PTE. Do not use it. * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn) { int ret = -EINVAL; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) return ret; ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); if (ret) return ret; *pfn = pte_pfn(*ptep); pte_unmap_unlock(ptep, ptl); return 0; } EXPORT_SYMBOL(follow_pfn); #ifdef CONFIG_HAVE_IOREMAP_PROT int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys) { int ret = -EINVAL; pte_t *ptep, pte; spinlock_t *ptl; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) goto out; pte = *ptep; /* Never return PFNs of anon folios in COW mappings. */ if (vm_normal_page(vma, address, pte)) goto unlock; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; *prot = pgprot_val(pte_pgprot(pte)); *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: return ret; } int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; int offset = addr & (PAGE_SIZE-1); if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); iounmap(maddr); return len; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. If non-NULL, use the * given task for page fault accounting. */ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; void *maddr; struct page *page = NULL; ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT break; #else /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, len, write); if (ret <= 0) break; bytes = ret; #endif } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } kunmap(page); put_page(page); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = find_vma(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; char *buf = (char *)__get_free_page(GFP_NOWAIT); if (buf) { char *p; p = file_path(f, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; printk("%s%s[%lx+%lx]", prefix, kbasename(p), vma->vm_start, vma->vm_end - vma->vm_start); free_page((unsigned long)buf); } } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { /* * Some code (nfs/sunrpc) uses socket ops on kernel memory while * holding the mmap_lock, this is safe because kernel memory doesn't * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ if (uaccess_kernel()) return; if (pagefault_disabled()) return; __might_sleep(file, line, 0); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline void process_huge_page( unsigned long addr_hint, unsigned int pages_per_huge_page, void (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l; unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= pages_per_huge_page) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } else { /* If target subpage in second half of huge page */ base = pages_per_huge_page - 2 * (pages_per_huge_page - n); l = pages_per_huge_page - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); cond_resched(); process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); } } static void clear_gigantic_page(struct page *page, unsigned long addr, unsigned int pages_per_huge_page) { int i; struct page *p = page; might_sleep(); for (i = 0; i < pages_per_huge_page; i++, p = mem_map_next(p, page, i)) { cond_resched(); clear_user_highpage(p, addr + i * PAGE_SIZE); } } static void clear_subpage(unsigned long addr, int idx, void *arg) { struct page *page = arg; clear_user_highpage(page + idx, addr); } void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } static void copy_user_gigantic_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { int i; struct page *dst_base = dst; struct page *src_base = src; for (i = 0; i < pages_per_huge_page; ) { cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); i++; dst = mem_map_next(dst, dst_base, i); src = mem_map_next(src, src_base, i); } } struct copy_subpage_arg { struct page *dst; struct page *src; struct vm_area_struct *vma; }; static void copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, addr, copy_arg->vma); } void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { copy_user_gigantic_page(dst, src, addr, vma, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault) { void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; struct page *subpage = dst_page; for (i = 0; i < pages_per_huge_page; i++, subpage = mem_map_next(subpage, dst_page, i)) { if (allow_pagefault) page_kaddr = kmap(subpage); else page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, (const void __user *)(src + i * PAGE_SIZE), PAGE_SIZE); if (allow_pagefault) kunmap(subpage); else kunmap_atomic(page_kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct page *page) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; page->ptl = ptl; return true; } void ptlock_free(struct page *page) { kmem_cache_free(page_ptl_cachep, page->ptl); } #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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/rcupdate.h> struct workqueue_struct; struct work_struct; typedef void (*work_func_t)(struct work_struct *work); void delayed_work_timer_fn(struct timer_list *t); /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif /* * The last color is no color used for works which don't * participate in workqueue flushing. */ WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, WORK_NO_COLOR = WORK_NR_COLORS, /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. * This makes pwqs aligned to 256 bytes and allows 15 workqueue * flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, /* * When a work item is off queue, its high bits point to the last * pool it was on. Cap at 31 bits and use the highest number to * indicate that no pool is associated. */ WORK_OFFQ_FLAG_BITS = 1, WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 24, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct work_struct { atomic_long_t data; struct list_head entry; work_func_t func; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs */ cpumask_var_t cpumask; /** * @no_numa: disable NUMA affinity * * Unlike other fields, ``no_numa`` isn't a property of a worker_pool. It * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus * doesn't participate in pool hash calculations or equality comparisons. */ bool no_numa; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK(_work, _func, _onstack) \ do { \ static struct lock_class_key __key; \ \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK(_work, _func, _onstack) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __init_timer(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __init_timer_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum { WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * excute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; /* unbound wq's aren't per-cpu, scale max_active according to #cpus */ #define WQ_UNBOUND_MAX_ACTIVE \ max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) /* * System-wide workqueues which are always present. * * system_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * * system_unbound_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * remaining args: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed * information on WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args...: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_workqueue_state(void); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_wq, work); } /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * * Think twice before calling this function! It's very easy to get into * trouble if you don't take great care. Either of the following situations * will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. * * Your code is running in the context of a work routine. * * They will be detected by lockdep when they occur, but the first might not * occur very often. It depends on what work items are on the workqueue and * what locks they need, which you have no control over. * * In most situations flushing the entire workqueue is overkill; you merely * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. */ static inline void flush_scheduled_work(void) { flush_workqueue(system_wq); } /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu(int cpu, long (*fn)(void *), void *arg); long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /** * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses * this_cpu_add which is irq-safe by definition. Hence there is no need muck * with irq state before calling this one */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; preempt_disable(); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock_irqrestore(&fbc->lock, flags); } else { this_cpu_add(*fbc->counters, amount); } preempt_enable(); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { unsigned long flags __maybe_unused; raw_spin_lock_init(&fbc->lock); lockdep_set_class(&fbc->lock, key); fbc->count = amount; fbc->counters = alloc_percpu_gfp(s32, gfp); if (!fbc->counters) return -ENOMEM; debug_percpu_counter_activate(fbc); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc->list); spin_lock_irqsave(&percpu_counters_lock, flags); list_add(&fbc->list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init); void percpu_counter_destroy(struct percpu_counter *fbc) { unsigned long flags __maybe_unused; if (!fbc->counters) return; debug_percpu_counter_deactivate(fbc); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); list_del(&fbc->list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc->counters); fbc->counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H #include <linux/compiler.h> #include <asm/percpu.h> #ifndef __ASSEMBLY__ struct task_struct; DECLARE_PER_CPU(struct task_struct *, current_task); static __always_inline struct task_struct *get_current(void) { return this_cpu_read_stable(current_task); } #define current get_current() #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CURRENT_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> #include <linux/types.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* * All weight knobs on the default hierarhcy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ #define CGROUP_WEIGHT_MIN 1 #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 /* walk only threadgroup leaders */ #define CSS_TASK_ITER_PROCS (1U << 0) /* walk all threaded css_sets in the domain */ #define CSS_TASK_ITER_THREADED (1U << 1) /* internal flags */ #define CSS_TASK_ITER_SKIPPED (1U << 16) /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; struct list_head *tcset_pos; struct list_head *tcset_head; struct list_head *task_pos; struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) \ extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; #include <linux/cgroup_subsys.h> #undef SUBSYS /** * cgroup_subsys_enabled - fast test on whether a subsys is enabled * @ss: subsystem in question */ #define cgroup_subsys_enabled(ss) \ static_branch_likely(&ss ## _enabled_key) /** * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy * @ss: subsystem in question */ #define cgroup_subsys_on_dfl(ss) \ static_branch_likely(&ss ## _on_dfl_key) bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); extern int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); void cgroup_exit(struct task_struct *p); void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p); int cgroup_init_early(void); int cgroup_init(void); int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v); /* * Iteration helpers and macros. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor * @parent: css whose children to walk * * Walk @parent's children. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_child(pos, parent) \ for ((pos) = css_next_child(NULL, (parent)); (pos); \ (pos) = css_next_child((pos), (parent))) /** * css_for_each_descendant_pre - pre-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * * Walk @root's descendants. @root is included in the iteration and the * first node to be visited. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * For example, the following guarantees that a descendant can't escape * state updates of its ancestors. * * my_online(@css) * { * Lock @css's parent and @css; * Inherit state from the parent; * Unlock both. * } * * my_update_state(@css) * { * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; * if (@pos == @css) * Update @css's state; * else * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } * * As long as the inheriting step, including checking the parent state, is * enclosed inside @pos locking, double-locking the parent isn't necessary * while inheriting. The state update to the parent is guaranteed to be * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. * * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_descendant_pre(pos, css) \ for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ (pos) = css_next_descendant_pre((pos), (css))) /** * css_for_each_descendant_post - post-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. @root is included in the iteration and the last * node to be visited. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * Note that the walk visibility guarantee example described in pre-order * walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple * processes. * * On the v2 hierarchy, there may be tasks from multiple processes and they * may not share the source or destination csses. * * On traditional hierarchies, when there are multiple tasks in @tset, if a * task of a process is in @tset, all tasks of the process are in @tset. * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ #define cgroup_taskset_for_each(task, dst_css, tset) \ for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ (task); \ (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ #define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ (leader); \ (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else /* * Inline functions. */ static inline u64 cgroup_id(struct cgroup *cgrp) { return cgrp->kn->id; } /** * css_get - obtain a reference on the specified css * @css: target css * * The caller must already have a reference. */ static inline void css_get(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) percpu_ref_get(&css->refcnt); } /** * css_get_many - obtain references on the specified css * @css: target css * @n: number of references to get * * The caller must already have a reference. */ static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n) { if (!(css->flags & CSS_NO_REF)) percpu_ref_get_many(&css->refcnt, n); } /** * css_tryget - try to obtain a reference on the specified css * @css: target css * * Obtain a reference on @css unless it already has reached zero and is * being released. This function doesn't care whether @css is on or * offline. The caller naturally needs to ensure that @css is accessible * but doesn't have to be holding a reference on it - IOW, RCU protected * access is good enough for this function. Returns %true if a reference * count was successfully obtained; %false otherwise. */ static inline bool css_tryget(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget(&css->refcnt); return true; } /** * css_tryget_online - try to obtain a reference on the specified css if online * @css: target css * * Obtain a reference on @css if it's online. The caller naturally needs * to ensure that @css is accessible but doesn't have to be holding a * reference on it - IOW, RCU protected access is good enough for this * function. Returns %true if a reference count was successfully obtained; * %false otherwise. */ static inline bool css_tryget_online(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget_live(&css->refcnt); return true; } /** * css_is_dying - test whether the specified css is dying * @css: target css * * Test whether @css is in the process of offlining or already offline. In * most cases, ->css_online() and ->css_offline() callbacks should be * enough; however, the actual offline operations are RCU delayed and this * test returns %true also when @css is scheduled to be offlined. * * This is useful, for example, when the use case requires synchronous * behavior with respect to cgroup removal. cgroup removal schedules css * offlining but the css can seem alive while the operation is being * delayed. If the delay affects user visible semantics, this test can be * used to resolve the situation. */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); } /** * css_put - put a css reference * @css: target css * * Put a reference obtained via css_get() and css_tryget_online(). */ static inline void css_put(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) percpu_ref_put(&css->refcnt); } /** * css_put_many - put css references * @css: target css * @n: number of references to put * * Put references obtained via css_get() and css_tryget_online(). */ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) { if (!(css->flags & CSS_NO_REF)) percpu_ref_put_many(&css->refcnt, n); } static inline void cgroup_get(struct cgroup *cgrp) { css_get(&cgrp->self); } static inline bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); } static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); } /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for * @__c: extra condition expression to be passed to rcu_dereference_check() * * A task's css_set is RCU protected, initialized and exited while holding * task_lock(), and can only be modified while holding both cgroup_mutex * and task_lock() while the task is alive. This macro verifies that the * caller is inside proper critical section and returns @task's css_set. * * The caller can also specify additional allowed conditions via @__c, such * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ rcu_dereference((task)->cgroups) #endif /** * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() * * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ #define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** * task_css_set - obtain a task's css_set * @task: the task to obtain css_set for * * See task_css_set_check(). */ static inline struct css_set *task_css_set(struct task_struct *task) { return task_css_set_check(task, false); } /** * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * See task_css_check(). */ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, false); } /** * task_get_css - find and get the css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) { struct cgroup_subsys_state *css; rcu_read_lock(); while (true) { css = task_css(task, subsys_id); /* * Can't use css_tryget_online() here. A task which has * PF_EXITING set may stay associated with an offline css. * If such task calls this function, css_tryget_online() * will keep failing. */ if (likely(css_tryget(css))) break; cpu_relax(); } rcu_read_unlock(); return css; } /** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID * * Test whether @task belongs to the root css on the specified subsystem. * May be invoked in any context. */ static inline bool task_css_is_root(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, true) == init_css_set.subsys[subsys_id]; } static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { return task_css(task, subsys_id)->cgroup; } static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) { return task_css_set(task)->dfl_cgrp; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ static inline bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); } /** * cgroup_ancestor - find ancestor of cgroup * @cgrp: cgroup to find ancestor of * @ancestor_level: level of ancestor to find starting from root * * Find ancestor of cgroup at specified level starting from root if it exists * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at * @ancestor_level. * * This function is safe to call as long as @cgrp is accessible. */ static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { if (cgrp->level < ancestor_level) return NULL; while (cgrp && cgrp->level > ancestor_level) cgrp = cgroup_parent(cgrp); return cgrp; } /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested * @ancestor: possible ancestor of @task's cgroup * * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. * It follows all the same rules as cgroup_is_descendant, and only applies * to the default hierarchy. */ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { struct css_set *cset = task_css_set(task); return cgroup_is_descendant(cset->dfl_cgrp, ancestor); } /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ static inline struct cftype *of_cft(struct kernfs_open_file *of) { return of->kn->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); /* cft/css accessors for cftype->seq_*() operations */ static inline struct cftype *seq_cft(struct seq_file *seq) { return of_cft(seq->private); } static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) { return of_css(seq->private); } /* * Name / path handling functions. All are thin wrappers around the kernfs * counterparts and can be called under any context. */ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_name(cgrp->kn, buf, buflen); } static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_path(cgrp->kn, buf, buflen); } static inline void pr_cont_cgroup_name(struct cgroup *cgrp) { pr_cont_kernfs_name(cgrp->kn); } static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { pr_cont_kernfs_path(cgrp->kn); } static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return &cgrp->psi; } static inline void cgroup_init_kthreadd(void) { /* * kthreadd is inherited by all kthreads, keep it in the root so * that the new kthreads are guaranteed to stay in the root until * initialization is finished. */ current->no_cgroup_migration = 1; } static inline void cgroup_kthread_ready(void) { /* * This kthread finished initialization. The creator should have * set PF_NO_SETAFFINITY if this kthread should stay in the root. */ current->no_cgroup_migration = 0; } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} static inline int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_exit(struct task_struct *p) {} static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { return NULL; } static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return NULL; } static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS /* * cgroup scalable recursive statistics. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); /* * Basic resource stats. */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} static inline void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) {} #endif void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec); void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec); static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) { struct cgroup *cgrp; cpuacct_charge(task, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); } static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup *cgrp; cpuacct_account_field(task, index, delta_exec); rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) {} static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) {} #endif /* CONFIG_CGROUPS */ /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA #if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) extern spinlock_t cgroup_sk_update_lock; #endif void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { #if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) unsigned long v; /* * @skcd->val is 64bit but the following is safe on 32bit too as we * just need the lower ulong to be written and read atomically. */ v = READ_ONCE(skcd->val); if (v & 3) return &cgrp_dfl_root.cgrp; return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; #else return (struct cgroup *)(unsigned long)skcd->val; #endif } #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ struct cgroup_namespace { refcount_t count; struct ns_common ns; struct user_namespace *user_ns; struct ucounts *ucounts; struct css_set *root_cset; }; extern struct cgroup_namespace init_cgroup_ns; #ifdef CONFIG_CGROUPS void free_cgroup_ns(struct cgroup_namespace *ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns); int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); #else /* !CONFIG_CGROUPS */ static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } static inline struct cgroup_namespace * copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { return old_ns; } #endif /* !CONFIG_CGROUPS */ static inline void get_cgroup_ns(struct cgroup_namespace *ns) { if (ns) refcount_inc(&ns->count); } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { if (ns && refcount_dec_and_test(&ns->count)) free_cgroup_ns(ns); } #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); void cgroup_leave_frozen(bool always_leave); void cgroup_update_frozen(struct cgroup *cgrp); void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); static inline bool cgroup_task_freeze(struct task_struct *task) { bool ret; if (task->flags & PF_KTHREAD) return false; rcu_read_lock(); ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags); rcu_read_unlock(); return ret; } static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; } #else /* !CONFIG_CGROUPS */ static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } static inline bool cgroup_task_freeze(struct task_struct *task) { return false; } static inline bool cgroup_task_frozen(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUP_BPF static inline void cgroup_bpf_get(struct cgroup *cgrp) { percpu_ref_get(&cgrp->bpf.refcnt); } static inline void cgroup_bpf_put(struct cgroup *cgrp) { percpu_ref_put(&cgrp->bpf.refcnt); } #else /* CONFIG_CGROUP_BPF */ static inline void cgroup_bpf_get(struct cgroup *cgrp) {} static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ #endif /* _LINUX_CGROUP_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/processor.h> #include <linux/cpumask.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) #define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) #define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } #endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * * RCU read-side critical sections are forbidden in the inner idle loop, * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU * will happily ignore any such read-side critical sections. However, * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument * (in this example, calling the do_something_with_RCU() function), * and then tell RCU to go back to ignoring this CPU. It is permissible * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is * on the order of a million or so, even on 32-bit systems). It is * not legal to block within RCU_NONIDLE(), nor is it permissible to * transfer control either into or out of RCU_NONIDLE()'s statement. */ #define RCU_NONIDLE(a) \ do { \ rcu_irq_enter_irqson(); \ do { a; } while (0); \ rcu_irq_exit_irqson(); \ } while (0) /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU # define rcu_tasks_trace_qs(t) \ do { \ if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ smp_store_release(&(t)->trc_reader_checked, true); \ smp_mb(); /* Readers partitioned by store. */ \ } \ } while (0) # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs((t)); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as * is the case in the context of the RCU callback that is freeing up * the data, or after a synchronize_rcu() returns. This can be useful * when tearing down multi-linked structures after a grace period * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In most situations, rcu_read_unlock() is immune from deadlock. * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() * is responsible for deboosting, which it does via rt_mutex_unlock(). * Unfortunately, this function acquires the scheduler's runqueue and * priority-inheritance spinlocks. This means that deadlock could result * if the caller of rcu_read_unlock() already holds one of these locks or * any lock that is ever acquired while holding them. * * That said, RCU readers are never priority boosted unless they were * preempted. Therefore, one way to avoid deadlock is to make sure * that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with one of * rt_mutex_unlock()'s locks held. Such preemption can be avoided in * a number of ways, for example, by invoking preempt_disable() before * critical section's outermost rcu_read_lock(). * * Given that the set of locks acquired by rt_mutex_unlock() might change * at any time, a somewhat more future-proofed approach is to make sure * that that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with irqs disabled. * This approach relies on the fact that rt_mutex_unlock() currently only * acquires irq-disabled locks. * * The second of these two approaches is best in most situations, * however, the first approach can also be useful, at least to those * developers willing to keep abreast of the set of locks acquired by * rt_mutex_unlock(). * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent of rcu_read_lock(), but disables preemption. * Read-side critical sections can also be introduced by anything else * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ #define __kvfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in __kvfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * Note that the allowable offset might decrease in the future, for example, * to allow something like kmem_cache_free_rcu(). * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) /** * kvfree_rcu() - kvfree an object after a grace period. * * This macro consists of one or two arguments and it is * based on whether an object is head-less or not. If it * has a head then a semantic stays the same as it used * to be before: * * kvfree_rcu(ptr, rhf); * * where @ptr is a pointer to kvfree(), @rhf is the name * of the rcu_head structure within the type of @ptr. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kvfree_rcu(ptr); * * where @ptr is a pointer to kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME #define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; #endif /* __LINUX_RCUPDATE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_INVALID, }; extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_getcwd(void); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_getcwd(void) { if (unlikely(audit_context())) __audit_getcwd(); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(unsigned int response) { if (!audit_dummy_context()) __audit_fanotify(response); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_getcwd(void) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(unsigned int response) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> struct file; extern void fput(struct file *); extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { if (fput_needed) fput(file); } struct fd { struct file *file; unsigned int flags; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 static inline void fdput(struct fd fd) { if (fd.flags & FDPUT_FPUT) fput(fd.file); } extern struct file *fget(unsigned int fd); extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); extern unsigned long __fdget_pos(unsigned int fd); extern void __f_unlock_pos(struct file *); static inline struct fd __to_fd(unsigned long v) { return (struct fd){(struct file *)(v & ~3),v & 3}; } static inline struct fd fdget(unsigned int fd) { return __to_fd(__fdget(fd)); } static inline struct fd fdget_raw(unsigned int fd) { return __to_fd(__fdget_raw(fd)); } static inline struct fd fdget_pos(int fd) { return __to_fd(__fdget_pos(fd)); } static inline void fdput_pos(struct fd f) { if (f.flags & FDPUT_POS_UNLOCK) __f_unlock_pos(f.file); fdput(f); } extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; return __receive_fd(-1, file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { return __receive_fd(-1, file, NULL, o_flags); } static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) { return __receive_fd(fd, file, NULL, o_flags); } extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; #endif /* __LINUX_FILE_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE 5 #ifdef CONFIG_X86_64 # define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC #else # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t" "2:\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } #else /* __ASSEMBLY__ */ .macro STATIC_JUMP_IF_TRUE target, key, def .Lstatic_jump_\@: .if \def /* Equivalent to "jmp.d32 \target" */ .byte 0xe9 .long \target - .Lstatic_jump_after_\@ .Lstatic_jump_after_\@: .else .byte STATIC_KEY_INIT_NOP .endif .pushsection __jump_table, "aw" _ASM_ALIGN .long .Lstatic_jump_\@ - ., \target - . _ASM_PTR \key - . .popsection .endm .macro STATIC_JUMP_IF_FALSE target, key, def .Lstatic_jump_\@: .if \def .byte STATIC_KEY_INIT_NOP .else /* Equivalent to "jmp.d32 \target" */ .byte 0xe9 .long \target - .Lstatic_jump_after_\@ .Lstatic_jump_after_\@: .endif .pushsection __jump_table, "aw" _ASM_ALIGN .long .Lstatic_jump_\@ - ., \target - . _ASM_PTR \key + 1 - . .popsection .endm #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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } /** * instrument_atomic_read - instrument atomic read access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); } /** * instrument_atomic_write - instrument atomic write access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); } /** * instrument_copy_from_user - instrument writes of copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } #endif /* _LINUX_INSTRUMENTED_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_H #define _ASM_X86_UACCESS_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/extable.h> /* * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. */ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) { /* * If we have used "sizeof()" for the size, * we know it won't overflow the limit (but * it might overflow the 'addr', so it's * important to subtract the size from the * limit, not add it to the address). */ if (__builtin_constant_p(size)) return unlikely(addr > limit - size); /* Arbitrary sizes? Be careful about overflow */ addr += size; if (unlikely(addr < size)) return true; return unlikely(addr > limit); } #define __range_not_ok(addr, size, limit) \ ({ \ __chk_user_ptr(addr); \ __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ }) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline bool pagefault_disabled(void); # define WARN_ON_IN_IRQ() \ WARN_ON_ONCE(!in_task() && !pagefault_disabled()) #else # define WARN_ON_IN_IRQ() #endif /** * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check * @size: Size of block to check * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Checks if a pointer to a block of memory in user space is valid. * * Note that, depending on architecture, this function probably just * checks that the pointer is in the user space range - after calling * this function, memory access functions may still return -EFAULT. * * Return: true (nonzero) if the memory block may be valid, false (zero) * if it is definitely invalid. */ #define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ likely(!__range_not_ok(addr, size, TASK_SIZE_MAX)); \ }) extern int __get_user_1(void); extern int __get_user_2(void); extern int __get_user_4(void); extern int __get_user_8(void); extern int __get_user_nocheck_1(void); extern int __get_user_nocheck_2(void); extern int __get_user_nocheck_4(void); extern int __get_user_nocheck_8(void); extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() #define __uaccess_begin_nospec() \ ({ \ stac(); \ barrier_nospec(); \ }) /* * This is the smallest unsigned integer type that can fit a value * (up to 'long long') */ #define __inttype(x) __typeof__( \ __typefits(x,char, \ __typefits(x,short, \ __typefits(x,int, \ __typefits(x,long,0ULL))))) #define __typefits(x,type,not) \ __builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not) /* * This is used for both get_user() and __get_user() to expand to * the proper special function call that has odd calling conventions * due to returning both a value and an error, and that depends on * the size of the pointer passed in. * * Careful: we have to cast the result to the type of the pointer * for sign reasons. * * The use of _ASM_DX as the register specifier is a bit of a * simplification, as gcc only cares about it as the starting point * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits * (%ecx being the next register in gcc's x86 register sequence), and * %rdx on 64 bits. * * Clang/LLVM cares about the size of the register, but still wants * the base register for something that ends up being a pair. */ #define do_get_user_call(fn,x,ptr) \ ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ asm volatile("call __" #fn "_%P4" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ }) /** * get_user - Get a simple variable from user space. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); }) /** * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr) #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ asm_volatile_goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ _ASM_EXTABLE_UA(2b, %l2) \ : : "A" (x), "r" (addr) \ : : label) #else #define __put_user_goto_u64(x, ptr, label) \ __put_user_goto(x, ptr, "q", "er", label) #endif extern void __put_user_bad(void); /* * Strange magic calling convention: pointer in %ecx, * value in %eax(:%edx), return value in %ecx. clobbers %rbx */ extern void __put_user_1(void); extern void __put_user_2(void); extern void __put_user_4(void); extern void __put_user_8(void); extern void __put_user_nocheck_1(void); extern void __put_user_nocheck_2(void); extern void __put_user_nocheck_4(void); extern void __put_user_nocheck_8(void); /* * ptr must be evaluated and assigned to the temporary __ptr_pu before * the assignment of x to __val_pu, to avoid any function calls * involved in the ptr expression (possibly implicitly generated due * to KASAN) from clobbering %ax. */ #define do_put_user_call(fn,x,ptr) \ ({ \ int __ret_pu; \ void __user *__ptr_pu; \ register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ __chk_user_ptr(ptr); \ __ptr_pu = (ptr); \ __val_pu = (x); \ asm volatile("call __" #fn "_%P[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ "r" (__val_pu), \ [size] "i" (sizeof(*(ptr))) \ :"ebx"); \ __builtin_expect(__ret_pu, 0); \ }) /** * put_user - Write a simple value into user space. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Return: zero on success, or -EFAULT on error. */ #define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); }) /** * __put_user - Write a simple value into user space, with less checking. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. */ #define __put_user(x, ptr) do_put_user_call(put_user_nocheck,x,ptr) #define __put_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __put_user_goto(x, ptr, "b", "iq", label); \ break; \ case 2: \ __put_user_goto(x, ptr, "w", "ir", label); \ break; \ case 4: \ __put_user_goto(x, ptr, "l", "ir", label); \ break; \ case 8: \ __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, label) do { \ unsigned int __gu_low, __gu_high; \ const unsigned int __user *__gu_ptr; \ __gu_ptr = (const void __user *)(ptr); \ __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ } while (0) #else #define __get_user_asm_u64(x, ptr, label) \ __get_user_asm(x, ptr, "q", "=r", label) #endif #define __get_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: { \ unsigned char x_u8__; \ __get_user_asm(x_u8__, ptr, "b", "=q", label); \ (x) = x_u8__; \ break; \ } \ case 2: \ __get_user_asm(x, ptr, "w", "=r", label); \ break; \ case 4: \ __get_user_asm(x, ptr, "l", "=r", label); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, label); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ : [umem] "m" (__m(addr)) \ : : label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ asm volatile("\n" \ "1: movl %[lowbits],%%eax\n" \ "2: movl %[highbits],%%edx\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: mov %[efault],%[errout]\n" \ " xorl %%eax,%%eax\n" \ " xorl %%edx,%%edx\n" \ " jmp 3b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 4b) \ _ASM_EXTABLE_UA(2b, 4b) \ : [errout] "=r" (retval), \ [output] "=&A"(x) \ : [lowbits] "m" (__m(__ptr)), \ [highbits] "m" __m(((u32 __user *)(__ptr)) + 1), \ [efault] "i" (-EFAULT), "0" (retval)); \ }) #else #define __get_user_asm_u64(x, ptr, retval) \ __get_user_asm(x, ptr, retval, "q", "=r") #endif #define __get_user_size(x, ptr, size, retval) \ do { \ unsigned char x_u8__; \ \ retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __get_user_asm(x_u8__, ptr, retval, "b", "=q"); \ (x) = x_u8__; \ break; \ case 2: \ __get_user_asm(x, ptr, retval, "w", "=r"); \ break; \ case 4: \ __get_user_asm(x, ptr, retval, "l", "=r"); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, retval); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, itype, ltype) \ asm volatile("\n" \ "1: mov"itype" %[umem],%[output]\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %[efault],%[errout]\n" \ " xorl %k[output],%k[output]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : [errout] "=r" (err), \ [output] ltype(x) \ : [umem] "m" (__m(addr)), \ [efault] "i" (-EFAULT), "0" (err)) #endif // CONFIG_CC_ASM_GOTO_OUTPUT #ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #endif // CONFIG_X86_32 #else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ int __err = 0; \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ CC_SET(z) \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[errout]) \ : CC_OUT(z) (success), \ [errout] "+r" (__err), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 /* * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses * both ESI and EDI for the memory operand, compilation will fail if the error * is an input+output as there will be no register available for input. */ #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ int __result; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ "mov $0, %%ecx\n\t" \ "setz %%cl\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ : [result]"=c" (__result), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory", "cc"); \ if (unlikely(__result < 0)) \ goto label; \ if (unlikely(!__result)) \ *_old = __old; \ likely(__result); }) #endif // CONFIG_X86_32 #endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) /* * Tell gcc we read from memory instead of writing: this is because * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ : : label) extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); #define copy_mc_to_kernel copy_mc_to_kernel unsigned long __must_check copy_mc_to_user(void __user *to, const void *from, unsigned len); #endif /* * movsl can be slow when source and dest are not both 8-byte aligned */ #ifdef CONFIG_X86_INTEL_USERCOPY extern struct movsl_mask { int mask; } ____cacheline_aligned_in_smp movsl_mask; #endif #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> #endif /* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; __uaccess_begin_nospec(); return 1; } #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() #define user_access_save() smap_save() #define user_access_restore(x) smap_restore(x) #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), err_label); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT extern void __try_cmpxchg_user_wrong_size(void); #ifndef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) #endif /* * Force the pointer to u<size> to match the size expected by the asm helper. * clang/LLVM compiles all cases and only discards the unused paths after * processing errors, which breaks i386 if the pointer is an 8-byte value. */ #define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ bool __ret; \ __chk_user_ptr(_ptr); \ switch (sizeof(*(_ptr))) { \ case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ (__force u8 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ (__force u16 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ (__force u32 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ (_nval), _label); \ break; \ default: __try_cmpxchg_user_wrong_size(); \ } \ __ret; }) /* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ #define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ int __ret = -EFAULT; \ __uaccess_begin_nospec(); \ __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ _label: \ __uaccess_end(); \ __ret; \ }) /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. */ #define unsafe_copy_loop(dst, src, len, type, label) \ while (len >= sizeof(type)) { \ unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } #define unsafe_copy_to_user(_dst,_src,_len,label) \ do { \ char __user *__ucu_dst = (_dst); \ const char *__ucu_src = (_src); \ size_t __ucu_len = (_len); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) #define HAVE_GET_KERNEL_NOFAULT #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), err_label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ int __kr_err; \ \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __put_kernel_nofault(dst, src, type, err_label) \ __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ sizeof(type), err_label) #endif /* _ASM_X86_UACCESS_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 | // SPDX-License-Identifier: GPL-2.0 /* * preemptoff and irqoff tracepoints * * Copyright (C) Joel Fernandes (Google) <joel@joelfernandes.org> */ #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include "trace.h" #define CREATE_TRACE_POINTS #include <trace/events/preemptirq.h> #ifdef CONFIG_TRACE_IRQFLAGS /* Per-cpu variable to prevent redundant calls when IRQs already off */ static DEFINE_PER_CPU(int, tracing_irq_cpu); /* * Like trace_hardirqs_on() but without the lockdep invocation. This is * used in the low level entry code where the ordering vs. RCU is important * and lockdep uses a staged approach which splits the lockdep hardirq * tracking into a RCU on and a RCU off section. */ void trace_hardirqs_on_prepare(void) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } } EXPORT_SYMBOL(trace_hardirqs_on_prepare); NOKPROBE_SYMBOL(trace_hardirqs_on_prepare); void trace_hardirqs_on(void) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } lockdep_hardirqs_on_prepare(CALLER_ADDR0); lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); NOKPROBE_SYMBOL(trace_hardirqs_on); /* * Like trace_hardirqs_off() but without the lockdep invocation. This is * used in the low level entry code where the ordering vs. RCU is important * and lockdep uses a staged approach which splits the lockdep hardirq * tracking into a RCU on and a RCU off section. */ void trace_hardirqs_off_finish(void) { if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); if (!in_nmi()) trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off_finish); NOKPROBE_SYMBOL(trace_hardirqs_off_finish); void trace_hardirqs_off(void) { lockdep_hardirqs_off(CALLER_ADDR0); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off); NOKPROBE_SYMBOL(trace_hardirqs_off); __visible void trace_hardirqs_on_caller(unsigned long caller_addr) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); tracer_hardirqs_on(CALLER_ADDR0, caller_addr); this_cpu_write(tracing_irq_cpu, 0); } lockdep_hardirqs_on_prepare(caller_addr); lockdep_hardirqs_on(caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { lockdep_hardirqs_off(caller_addr); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_TRACE_IRQFLAGS */ #ifdef CONFIG_TRACE_PREEMPT_TOGGLE void trace_preempt_on(unsigned long a0, unsigned long a1) { if (!in_nmi()) trace_preempt_enable_rcuidle(a0, a1); tracer_preempt_on(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { if (!in_nmi()) trace_preempt_disable_rcuidle(a0, a1); tracer_preempt_off(a0, a1); } #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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* overloaded: * - notify group_exit_task when ->count is equal to notify_count * - everyone except group_exit_task is stopped during signal delivery * of fatal signals, group_exit_task processes the signal. */ int notify_count; struct task_struct *group_exit_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ #define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { return (sig->flags & SIGNAL_GROUP_EXIT) || (sig->group_exit_task != NULL); } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *task, sigset_t *mask, kernel_siginfo_t *info); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(task, &task->blocked, &__info); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); schedule(); } #ifdef __ARCH_SI_TRAPNO # define ___ARCH_SI_TRAPNO(_a1) , _a1 #else # define ___ARCH_SI_TRAPNO(_a1) #endif #ifdef __ia64__ # define ___ARCH_SI_IA64(_a1, _a2, _a3) , _a1, _a2, _a3 #else # define ___ARCH_SI_IA64(_a1, _a2, _a3) #endif int force_sig_fault_to_task(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)); int send_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int signal_pending(struct task_struct *p) { /* * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same * behavior in terms of ensuring that we break out of wait loops * so that notify signal callbacks can be processed. */ if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) return 1; return task_sigpending(p); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(long state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending_and_wake(struct task_struct *t); extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool resume) { signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { signal_wake_up_state(t, resume ? __TASK_TRACED : 0); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Careful: do_each_thread/while_each_thread is a double loop so * 'break' will not work as expected - use goto instead. */ #define do_each_thread(g, t) \ for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } static inline struct task_struct *next_thread(const struct task_struct *p) { return list_entry_rcu(p->thread_group.next, struct task_struct, thread_group); } static inline int thread_group_empty(struct task_struct *p) { return list_empty(&p->thread_group); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern bool thread_group_exited(struct pid *pid); extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) { struct sighand_struct *ret; ret = __lock_task_sighand(task, flags); (void)__cond_lock(&task->sighand->siglock, ret); return ret; } static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() do { } while (0) #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } #ifndef arch_spin_lock_flags #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #endif static inline void do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock) { __acquire(lock); arch_spin_lock_flags(&lock->raw_lock, *flags); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) \ __cond_lock(lock, _raw_spin_trylock_bh(lock)) #define raw_spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define raw_spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) /* Include rwlock functions */ #include <linux/rwlock.h> /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } #define spin_trylock_irqsave(lock, flags) \ ({ \ raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); #endif /* __LINUX_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/thread_info.h> DECLARE_PER_CPU(int, __preempt_count); /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) /* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ static __always_inline int preempt_count(void) { return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { int old, new; do { old = raw_cpu_read_4(__preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old); } /* * must be macros to avoid header recursion hell */ #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* * We fold the NEED_RESCHED bit into the preempt count such that * preempt_enable() can decrement and test for needing to reschedule with a * single instruction. * * We invert the actual bit, so that when the decrement hits 0 we know we both * need to resched (the bit is cleared) and can resched (no preempt count). */ static __always_inline void set_preempt_need_resched(void) { raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* * The various preempt_count add/sub methods */ static __always_inline void __preempt_count_add(int val) { raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { raw_cpu_add_4(__preempt_count, -val); } /* * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule * a decrement which hits zero means we have no preempt_count and should * reschedule. */ static __always_inline bool __preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule_thunk(void); # define __preempt_schedule() \ asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); # define __preempt_schedule_notrace() \ asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/ima.h> #include <linux/dnotify.h> #include <linux/compat.h> #include "internal.h" int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ ret = notify_change(dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { struct inode *inode; long error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = mnt_want_write(path->mnt); if (error) goto out; error = inode_permission(inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = locks_verify_truncate(inode, NULL, length); if (!error) error = security_path_truncate(path); if (!error) error = do_truncate(path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); out: return error; } EXPORT_SYMBOL_GPL(vfs_truncate); long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (!error) { error = vfs_truncate(&path, length); path_put(&path); } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return do_sys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return do_sys_truncate(path, length); } #endif long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; struct fd f; int error; error = -EINVAL; if (length < 0) goto out; error = -EBADF; f = fdget(fd); if (!f.file) goto out; /* explicitly opened as large or we are on 64-bit box */ if (f.file->f_flags & O_LARGEFILE) small = 0; dentry = f.file->f_path.dentry; inode = dentry->d_inode; error = -EINVAL; if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE)) goto out_putf; error = -EINVAL; /* Cannot ftruncate over 2^31 bytes without large file support */ if (small && length > MAX_NON_LFS) goto out_putf; error = -EPERM; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(f.file))) goto out_putf; sb_start_write(inode->i_sb); error = locks_verify_truncate(inode, f.file, length); if (!error) error = security_path_truncate(&f.file->f_path); if (!error) error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length) { return do_sys_ftruncate(fd, length, 1); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length) { return do_sys_ftruncate(fd, length, 1); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return do_sys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return do_sys_ftruncate(fd, length, 0); } #endif /* BITS_PER_LONG == 32 */ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret; if (offset < 0 || len <= 0) return -EINVAL; /* Return error if mode is not supported */ if (mode & ~FALLOC_FL_SUPPORTED_MASK) return -EOPNOTSUPP; /* Punch hole and zero range are mutually exclusive */ if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; /* Punch hole must have keep size set */ if ((mode & FALLOC_FL_PUNCH_HOLE) && !(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* Collapse range should only be used exclusively. */ if ((mode & FALLOC_FL_COLLAPSE_RANGE) && (mode & ~FALLOC_FL_COLLAPSE_RANGE)) return -EINVAL; /* Insert range should only be used exclusively. */ if ((mode & FALLOC_FL_INSERT_RANGE) && (mode & ~FALLOC_FL_INSERT_RANGE)) return -EINVAL; /* Unshare range should only be used with allocate mode. */ if ((mode & FALLOC_FL_UNSHARE_RANGE) && (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * We can only allow pure fallocate on append only files */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wrap through zero too */ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fallocate(f.file, mode, offset, len); fdput(f); } return error; } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. */ static const struct cred *access_override_creds(void) { const struct cred *old_cred; struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-RCY. */ override_cred->non_rcu = 1; old_cred = override_creds(override_cred); /* override_cred() gets its own ref */ put_cred(override_cred); return old_cred; } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (!(flags & AT_EACCESS)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } retry: res = user_path_at(dfd, filename, lookup_flags, &path); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path)) goto out_path_release; } res = inode_permission(inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; /* * This is a rare case where using __mnt_is_readonly() * is OK without a mnt_want/drop_write() pair. Since * no actual write to the fs is performed here, we do * not need to telegraph to that to anyone. * * By doing this, we accept that this access is * inherently racy and know that the fs may change * state before we even see this result. */ if (__mnt_is_readonly(path.mnt)) res = -EROFS; out_path_release: path_put(&path); if (retry_estale(res, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: if (old_cred) revert_creds(old_cred); return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { return do_faccessat(dfd, filename, mode, 0); } SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, int, flags) { return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return do_faccessat(AT_FDCWD, filename, mode, 0); } SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; set_fs_pwd(current->fs, &path); dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); int error; error = -EBADF; if (!f.file) goto out; error = -ENOTDIR; if (!d_can_lookup(f.file->f_path.dentry)) goto out_putf; error = inode_permission(file_inode(f.file), MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (error) goto dput_and_out; set_fs_root(current->fs, &path); error = 0; dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; struct iattr newattrs; int error; error = mnt_want_write(path->mnt); if (error) return error; retry_deleg: inode_lock(inode); error = security_path_chmod(path, mode); if (error) goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path->mnt); return error; } int vfs_fchmod(struct file *file, umode_t mode) { audit_file(file); return chmod_common(&file->f_path, mode); } SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { struct fd f = fdget(fd); int err = -EBADF; if (f.file) { err = vfs_fchmod(f.file, mode); fdput(f); } return err; } static int do_fchmodat(int dfd, const char __user *filename, umode_t mode) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (!error) { error = chmod_common(&path, mode); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) { return do_fchmodat(dfd, filename, mode); } SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { return do_fchmodat(AT_FDCWD, filename, mode); } int chown_common(const struct path *path, uid_t user, gid_t group) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; struct iattr newattrs; kuid_t uid; kgid_t gid; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); retry_deleg: newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { if (!uid_valid(uid)) return -EINVAL; newattrs.ia_valid |= ATTR_UID; newattrs.ia_uid = uid; } if (group != (gid_t) -1) { if (!gid_valid(gid)) return -EINVAL; newattrs.ia_valid |= ATTR_GID; newattrs.ia_gid = gid; } inode_lock(inode); if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(inode); error = security_path_chown(path, uid, gid); if (!error) error = notify_change(path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag) { struct path path; int error = -EINVAL; int lookup_flags; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) goto out; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = mnt_want_write(path.mnt); if (error) goto out_release; error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { return do_fchownat(dfd, filename, user, group, flag); } SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, AT_SYMLINK_NOFOLLOW); } int vfs_fchown(struct file *file, uid_t user, gid_t group) { int error; error = mnt_want_write_file(file); if (error) return error; audit_file(file); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); return error; } int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fchown(f.file, user, group); fdput(f); } return error; } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { return ksys_fchown(fd, user, group); } static int do_dentry_open(struct file *f, struct inode *inode, int (*open)(struct inode *, struct file *)) { static const struct file_operations empty_fops = {}; int error; path_get(&f->f_path); f->f_inode = inode; f->f_mapping = inode->i_mapping; f->f_wb_err = filemap_sample_wb_err(f->f_mapping); f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH | FMODE_OPENED; f->f_op = &empty_fops; return 0; } if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) goto cleanup_file; error = __mnt_want_write(f->f_path.mnt); if (unlikely(error)) { put_write_access(inode); goto cleanup_file; } f->f_mode |= FMODE_WRITER; } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } error = security_file_open(f); if (error) goto cleanup_all; error = break_lease(locks_inode(f), f->f_flags); if (error) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (!open) open = f->f_op->open; if (open) { error = open(inode, f); if (error) goto cleanup_all; } f->f_mode |= FMODE_OPENED; if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(inode); if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; f->f_write_hint = WRITE_LIFE_NOT_SET; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); /* NB: we're sure to have correct a_ops only after f_op->open */ if (f->f_flags & O_DIRECT) { if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO) return -EINVAL; } /* * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ if ((f->f_mode & FMODE_WRITE) && filemap_nr_thps(inode->i_mapping)) truncate_pagecache(inode, 0); return 0; cleanup_all: if (WARN_ON_ONCE(error > 0)) error = -EINVAL; fops_put(f->f_op); if (f->f_mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(f->f_path.mnt); } cleanup_file: path_put(&f->f_path); f->f_path.mnt = NULL; f->f_path.dentry = NULL; f->f_inode = NULL; return error; } /** * finish_open - finish opening a file * @file: file pointer * @dentry: pointer to dentry * @open: open callback * @opened: state of open * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. * * NB: the dentry reference is _not_ consumed. If, for example, the dentry is * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry; return do_dentry_open(file, d_backing_inode(dentry), open); } EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer * @dentry: dentry or NULL (as returned from ->lookup()) * * This can be used to set the result of a successful lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * * Returns "0" which must be the return value of ->atomic_open() after having * called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { file->f_path.dentry = dentry; return 0; } EXPORT_SYMBOL(finish_no_open); char *file_path(struct file *filp, char *buf, int buflen) { return d_path(&filp->f_path, buf, buflen); } EXPORT_SYMBOL(file_path); /** * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized * @cred: credentials to use */ int vfs_open(const struct path *path, struct file *file) { file->f_path = *path; return do_dentry_open(file, d_backing_inode(path->dentry), NULL); } struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; struct file *f; validate_creds(cred); /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(dentry_open); struct file *open_with_fake_path(const struct path *path, int flags, struct inode *inode, const struct cred *cred) { struct file *f = alloc_empty_file_noaccount(flags, cred); if (!IS_ERR(f)) { int error; f->f_path = *path; error = do_dentry_open(f, inode, NULL); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(open_with_fake_path); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) inline struct open_how build_open_how(int flags, umode_t mode) { struct open_how how = { .flags = flags & VALID_OPEN_FLAGS, .mode = mode & S_IALLUGO, }; /* O_PATH beats everything else. */ if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS; /* Modes should only be set for create-like flags. */ if (!WILL_CREATE(how.flags)) how.mode = 0; return how; } inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; u64 strip = FMODE_NONOTIFY | O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), "struct open_flags doesn't yet handle flags > 32 bits"); /* * Strip flags that either shouldn't be set by userspace like * FMODE_NONOTIFY or that aren't relevant in determining struct * open_flags like O_CLOEXEC. */ flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ if (flags & ~VALID_OPEN_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; /* Scoping flags are mutually exclusive. */ if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT)) return -EINVAL; /* Deal with the mode. */ if (WILL_CREATE(flags)) { if (how->mode & ~S_IALLUGO) return -EINVAL; op->mode = how->mode | S_IFREG; } else { if (how->mode != 0) return -EINVAL; op->mode = 0; } /* * In order to ensure programs get explicit errors when trying to use * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we * have to require userspace to explicitly set it. */ if (flags & __O_TMPFILE) { if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; } if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) return -EINVAL; acc_mode = 0; } /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's * always set instead of having to deal with possibly weird behaviour * for malicious applications setting only __O_SYNC. */ if (flags & __O_SYNC) flags |= O_DSYNC; op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ if (flags & O_TRUNC) acc_mode |= MAY_WRITE; /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flags & O_APPEND) acc_mode |= MAY_APPEND; op->acc_mode = acc_mode; op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; if (flags & O_CREAT) { op->intent |= LOOKUP_CREATE; if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL; flags |= O_NOFOLLOW; } } if (flags & O_DIRECTORY) lookup_flags |= LOOKUP_DIRECTORY; if (!(flags & O_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (how->resolve & RESOLVE_NO_XDEV) lookup_flags |= LOOKUP_NO_XDEV; if (how->resolve & RESOLVE_NO_MAGICLINKS) lookup_flags |= LOOKUP_NO_MAGICLINKS; if (how->resolve & RESOLVE_NO_SYMLINKS) lookup_flags |= LOOKUP_NO_SYMLINKS; if (how->resolve & RESOLVE_BENEATH) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } op->lookup_flags = lookup_flags; return 0; } /** * file_open_name - open file and return file pointer * * @name: struct filename containing path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *file_open_name(struct filename *name, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_filp_open(AT_FDCWD, name, &op); } /** * filp_open - open file and return file pointer * * @filename: path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *filp_open(const char *filename, int flags, umode_t mode) { struct filename *name = getname_kernel(filename); struct file *file = ERR_CAST(name); if (!IS_ERR(name)) { file = file_open_name(name, flags, mode); putname(name); } return file; } EXPORT_SYMBOL(filp_open); struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *filename, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); static long do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; int fd = build_open_flags(how, &op); struct filename *tmp; if (fd) return fd; tmp = getname(filename); if (IS_ERR(tmp)) return PTR_ERR(tmp); fd = get_unused_fd_flags(how->flags); if (fd >= 0) { struct file *f = do_filp_open(dfd, tmp, &op); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); } else { fsnotify_open(f); fd_install(fd, f); } } putname(tmp); return fd; } long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_how how = build_open_how(flags, mode); return do_sys_openat2(dfd, filename, &how); } SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(dfd, filename, flags, mode); } SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, struct open_how __user *, how, size_t, usize) { int err; struct open_how tmp; BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0); BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST); if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) return err; /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; return do_sys_openat2(dfd, filename, &tmp); } #ifdef CONFIG_COMPAT /* * Exactly like sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(AT_FDCWD, filename, flags, mode); } /* * Exactly like sys_openat(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(dfd, filename, flags, mode); } #endif #ifndef __alpha__ /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { int flags = O_CREAT | O_WRONLY | O_TRUNC; if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, pathname, flags, mode); } #endif /* * "id" is the POSIX thread ID. We use the * files pointer for this.. */ int filp_close(struct file *filp, fl_owner_t id) { int retval = 0; if (!file_count(filp)) { printk(KERN_ERR "VFS: Close: file count is 0\n"); return 0; } if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id); locks_remove_posix(filp, id); } fput(filp); return retval; } EXPORT_SYMBOL(filp_close); /* * Careful here! We test whether the file pointer is NULL before * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ SYSCALL_DEFINE1(close, unsigned int, fd) { int retval = __close_fd(current->files, fd); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || retval == -ERESTARTNOINTR || retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; return retval; } /** * close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: reserved for future extensions * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { return __close_range(fd, max_fd, flags); } /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); return 0; } return -EPERM; } /* * Called when an inode is about to be open. * We use this to disallow opening large files on 32bit systems if * the caller didn't specify O_LARGEFILE. On 64bit systems we force * on this flag in sys_open. */ int generic_file_open(struct inode * inode, struct file * filp) { if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(generic_file_open); /* * This is used by subsystems that don't want seekable * file descriptors. The function is not supposed to ever fail, the only * reason it returns an 'int' and not 'void' is so that it can be plugged * directly into file_operations structure. */ int nonseekable_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); return 0; } EXPORT_SYMBOL(nonseekable_open); /* * stream_open is used by subsystems that want stream-like file descriptors. * Such file descriptors are not seekable and don't have notion of position * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). * Contrary to file descriptors of other regular files, .read() and .write() * can run simultaneously. * * stream_open never fails and is marked to return int so that it could be * directly used as file_operations.open . */ int stream_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } EXPORT_SYMBOL(stream_open); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_H #define _LINUX_SCHED_TASK_H /* * Interface between the scheduler and various task lifetime (fork()/exit()) * functionality: */ #include <linux/sched.h> #include <linux/uaccess.h> struct task_struct; struct rusage; union thread_union; struct css_set; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL struct kernel_clone_args { u64 flags; int __user *pidfd; int __user *child_tid; int __user *parent_tid; int exit_signal; unsigned long stack; unsigned long stack_size; unsigned long tls; pid_t *set_tid; /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; int io_thread; struct cgroup *cgrp; struct css_set *cset; }; /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; extern union thread_union init_thread_union; extern struct task_struct init_task; #ifdef CONFIG_PROVE_RCU extern int lockdep_tasklist_lock_is_held(void); #endif /* #ifdef CONFIG_PROVE_RCU */ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); extern void release_task(struct task_struct * p); extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *, unsigned long); extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(struct task_struct *tsk); #else static inline void exit_thread(struct task_struct *tsk) { } #endif extern void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP extern void sched_exec(void); #else #define sched_exec() {} #endif static inline struct task_struct *get_task_struct(struct task_struct *t) { refcount_inc(&t->usage); return t; } extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); static inline void put_task_struct(struct task_struct *t) { if (!refcount_dec_and_test(&t->usage)) return; /* * under PREEMPT_RT, we can't call put_task_struct * in atomic context because it will indirectly * acquire sleeping locks. * * call_rcu() will schedule delayed_put_task_struct_rcu() * to be called in process context. * * __put_task_struct() is called when * refcount_dec_and_test(&t->usage) succeeds. * * This means that it can't "conflict" with * put_task_struct_rcu_user() which abuses ->rcu the same * way; rcu_users has a reference so task->usage can't be * zero after rcu_users 1 -> 0 transition. * * delayed_free_task() also uses ->rcu, but it is only called * when it fails to fork a process. Therefore, there is no * way it can conflict with put_task_struct(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) call_rcu(&t->rcu, __put_task_struct_rcu_cb); else __put_task_struct(t); } static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) __put_task_struct(t); } void put_task_struct_rcu_user(struct task_struct *task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else # define arch_task_struct_size (sizeof(struct task_struct)) #endif #ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST /* * If an architecture has not declared a thread_struct whitelist we * must assume something there may need to be copied to userspace. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = 0; /* Handle dynamically sized thread_struct. */ *size = arch_task_struct_size - offsetof(struct task_struct, thread); } #endif #ifdef CONFIG_VMAP_STACK static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return t->stack_vm_area; } #else static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return NULL; } #endif /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), * neither inside nor outside. */ static inline void task_lock(struct task_struct *p) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) { spin_unlock(&p->alloc_lock); } #endif /* _LINUX_SCHED_TASK_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-fallback.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H #include <linux/compiler.h> #ifndef arch_xchg_relaxed #define arch_xchg_relaxed arch_xchg #define arch_xchg_acquire arch_xchg #define arch_xchg_release arch_xchg #else /* arch_xchg_relaxed */ #ifndef arch_xchg_acquire #define arch_xchg_acquire(...) \ __atomic_op_acquire(arch_xchg, __VA_ARGS__) #endif #ifndef arch_xchg_release #define arch_xchg_release(...) \ __atomic_op_release(arch_xchg, __VA_ARGS__) #endif #ifndef arch_xchg #define arch_xchg(...) \ __atomic_op_fence(arch_xchg, __VA_ARGS__) #endif #endif /* arch_xchg_relaxed */ #ifndef arch_cmpxchg_relaxed #define arch_cmpxchg_relaxed arch_cmpxchg #define arch_cmpxchg_acquire arch_cmpxchg #define arch_cmpxchg_release arch_cmpxchg #else /* arch_cmpxchg_relaxed */ #ifndef arch_cmpxchg_acquire #define arch_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) #endif #ifndef arch_cmpxchg_release #define arch_cmpxchg_release(...) \ __atomic_op_release(arch_cmpxchg, __VA_ARGS__) #endif #ifndef arch_cmpxchg #define arch_cmpxchg(...) \ __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) #endif #endif /* arch_cmpxchg_relaxed */ #ifndef arch_cmpxchg64_relaxed #define arch_cmpxchg64_relaxed arch_cmpxchg64 #define arch_cmpxchg64_acquire arch_cmpxchg64 #define arch_cmpxchg64_release arch_cmpxchg64 #else /* arch_cmpxchg64_relaxed */ #ifndef arch_cmpxchg64_acquire #define arch_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) #endif #ifndef arch_cmpxchg64_release #define arch_cmpxchg64_release(...) \ __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) #endif #ifndef arch_cmpxchg64 #define arch_cmpxchg64(...) \ __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) #endif #endif /* arch_cmpxchg64_relaxed */ #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) { return smp_load_acquire(&(v)->counter); } #define arch_atomic_read_acquire arch_atomic_read_acquire #endif #ifndef arch_atomic_set_release static __always_inline void arch_atomic_set_release(atomic_t *v, int i) { smp_store_release(&(v)->counter, i); } #define arch_atomic_set_release arch_atomic_set_release #endif #ifndef arch_atomic_add_return_relaxed #define arch_atomic_add_return_acquire arch_atomic_add_return #define arch_atomic_add_return_release arch_atomic_add_return #define arch_atomic_add_return_relaxed arch_atomic_add_return #else /* arch_atomic_add_return_relaxed */ #ifndef arch_atomic_add_return_acquire static __always_inline int arch_atomic_add_return_acquire(int i, atomic_t *v) { int ret = arch_atomic_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_add_return_acquire arch_atomic_add_return_acquire #endif #ifndef arch_atomic_add_return_release static __always_inline int arch_atomic_add_return_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_add_return_relaxed(i, v); } #define arch_atomic_add_return_release arch_atomic_add_return_release #endif #ifndef arch_atomic_add_return static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_add_return arch_atomic_add_return #endif #endif /* arch_atomic_add_return_relaxed */ #ifndef arch_atomic_fetch_add_relaxed #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add #define arch_atomic_fetch_add_release arch_atomic_fetch_add #define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add #else /* arch_atomic_fetch_add_relaxed */ #ifndef arch_atomic_fetch_add_acquire static __always_inline int arch_atomic_fetch_add_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire #endif #ifndef arch_atomic_fetch_add_release static __always_inline int arch_atomic_fetch_add_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_add_relaxed(i, v); } #define arch_atomic_fetch_add_release arch_atomic_fetch_add_release #endif #ifndef arch_atomic_fetch_add static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_add arch_atomic_fetch_add #endif #endif /* arch_atomic_fetch_add_relaxed */ #ifndef arch_atomic_sub_return_relaxed #define arch_atomic_sub_return_acquire arch_atomic_sub_return #define arch_atomic_sub_return_release arch_atomic_sub_return #define arch_atomic_sub_return_relaxed arch_atomic_sub_return #else /* arch_atomic_sub_return_relaxed */ #ifndef arch_atomic_sub_return_acquire static __always_inline int arch_atomic_sub_return_acquire(int i, atomic_t *v) { int ret = arch_atomic_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire #endif #ifndef arch_atomic_sub_return_release static __always_inline int arch_atomic_sub_return_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_sub_return_relaxed(i, v); } #define arch_atomic_sub_return_release arch_atomic_sub_return_release #endif #ifndef arch_atomic_sub_return static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_sub_return arch_atomic_sub_return #endif #endif /* arch_atomic_sub_return_relaxed */ #ifndef arch_atomic_fetch_sub_relaxed #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub #define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub #else /* arch_atomic_fetch_sub_relaxed */ #ifndef arch_atomic_fetch_sub_acquire static __always_inline int arch_atomic_fetch_sub_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire #endif #ifndef arch_atomic_fetch_sub_release static __always_inline int arch_atomic_fetch_sub_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_sub_relaxed(i, v); } #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release #endif #ifndef arch_atomic_fetch_sub static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_sub arch_atomic_fetch_sub #endif #endif /* arch_atomic_fetch_sub_relaxed */ #ifndef arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { arch_atomic_add(1, v); } #define arch_atomic_inc arch_atomic_inc #endif #ifndef arch_atomic_inc_return_relaxed #ifdef arch_atomic_inc_return #define arch_atomic_inc_return_acquire arch_atomic_inc_return #define arch_atomic_inc_return_release arch_atomic_inc_return #define arch_atomic_inc_return_relaxed arch_atomic_inc_return #endif /* arch_atomic_inc_return */ #ifndef arch_atomic_inc_return static __always_inline int arch_atomic_inc_return(atomic_t *v) { return arch_atomic_add_return(1, v); } #define arch_atomic_inc_return arch_atomic_inc_return #endif #ifndef arch_atomic_inc_return_acquire static __always_inline int arch_atomic_inc_return_acquire(atomic_t *v) { return arch_atomic_add_return_acquire(1, v); } #define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire #endif #ifndef arch_atomic_inc_return_release static __always_inline int arch_atomic_inc_return_release(atomic_t *v) { return arch_atomic_add_return_release(1, v); } #define arch_atomic_inc_return_release arch_atomic_inc_return_release #endif #ifndef arch_atomic_inc_return_relaxed static __always_inline int arch_atomic_inc_return_relaxed(atomic_t *v) { return arch_atomic_add_return_relaxed(1, v); } #define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed #endif #else /* arch_atomic_inc_return_relaxed */ #ifndef arch_atomic_inc_return_acquire static __always_inline int arch_atomic_inc_return_acquire(atomic_t *v) { int ret = arch_atomic_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire #endif #ifndef arch_atomic_inc_return_release static __always_inline int arch_atomic_inc_return_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_inc_return_relaxed(v); } #define arch_atomic_inc_return_release arch_atomic_inc_return_release #endif #ifndef arch_atomic_inc_return static __always_inline int arch_atomic_inc_return(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_inc_return arch_atomic_inc_return #endif #endif /* arch_atomic_inc_return_relaxed */ #ifndef arch_atomic_fetch_inc_relaxed #ifdef arch_atomic_fetch_inc #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc #define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc #endif /* arch_atomic_fetch_inc */ #ifndef arch_atomic_fetch_inc static __always_inline int arch_atomic_fetch_inc(atomic_t *v) { return arch_atomic_fetch_add(1, v); } #define arch_atomic_fetch_inc arch_atomic_fetch_inc #endif #ifndef arch_atomic_fetch_inc_acquire static __always_inline int arch_atomic_fetch_inc_acquire(atomic_t *v) { return arch_atomic_fetch_add_acquire(1, v); } #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire #endif #ifndef arch_atomic_fetch_inc_release static __always_inline int arch_atomic_fetch_inc_release(atomic_t *v) { return arch_atomic_fetch_add_release(1, v); } #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release #endif #ifndef arch_atomic_fetch_inc_relaxed static __always_inline int arch_atomic_fetch_inc_relaxed(atomic_t *v) { return arch_atomic_fetch_add_relaxed(1, v); } #define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed #endif #else /* arch_atomic_fetch_inc_relaxed */ #ifndef arch_atomic_fetch_inc_acquire static __always_inline int arch_atomic_fetch_inc_acquire(atomic_t *v) { int ret = arch_atomic_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire #endif #ifndef arch_atomic_fetch_inc_release static __always_inline int arch_atomic_fetch_inc_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_inc_relaxed(v); } #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release #endif #ifndef arch_atomic_fetch_inc static __always_inline int arch_atomic_fetch_inc(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_inc arch_atomic_fetch_inc #endif #endif /* arch_atomic_fetch_inc_relaxed */ #ifndef arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { arch_atomic_sub(1, v); } #define arch_atomic_dec arch_atomic_dec #endif #ifndef arch_atomic_dec_return_relaxed #ifdef arch_atomic_dec_return #define arch_atomic_dec_return_acquire arch_atomic_dec_return #define arch_atomic_dec_return_release arch_atomic_dec_return #define arch_atomic_dec_return_relaxed arch_atomic_dec_return #endif /* arch_atomic_dec_return */ #ifndef arch_atomic_dec_return static __always_inline int arch_atomic_dec_return(atomic_t *v) { return arch_atomic_sub_return(1, v); } #define arch_atomic_dec_return arch_atomic_dec_return #endif #ifndef arch_atomic_dec_return_acquire static __always_inline int arch_atomic_dec_return_acquire(atomic_t *v) { return arch_atomic_sub_return_acquire(1, v); } #define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire #endif #ifndef arch_atomic_dec_return_release static __always_inline int arch_atomic_dec_return_release(atomic_t *v) { return arch_atomic_sub_return_release(1, v); } #define arch_atomic_dec_return_release arch_atomic_dec_return_release #endif #ifndef arch_atomic_dec_return_relaxed static __always_inline int arch_atomic_dec_return_relaxed(atomic_t *v) { return arch_atomic_sub_return_relaxed(1, v); } #define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed #endif #else /* arch_atomic_dec_return_relaxed */ #ifndef arch_atomic_dec_return_acquire static __always_inline int arch_atomic_dec_return_acquire(atomic_t *v) { int ret = arch_atomic_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire #endif #ifndef arch_atomic_dec_return_release static __always_inline int arch_atomic_dec_return_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_dec_return_relaxed(v); } #define arch_atomic_dec_return_release arch_atomic_dec_return_release #endif #ifndef arch_atomic_dec_return static __always_inline int arch_atomic_dec_return(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_dec_return arch_atomic_dec_return #endif #endif /* arch_atomic_dec_return_relaxed */ #ifndef arch_atomic_fetch_dec_relaxed #ifdef arch_atomic_fetch_dec #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec #define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec #endif /* arch_atomic_fetch_dec */ #ifndef arch_atomic_fetch_dec static __always_inline int arch_atomic_fetch_dec(atomic_t *v) { return arch_atomic_fetch_sub(1, v); } #define arch_atomic_fetch_dec arch_atomic_fetch_dec #endif #ifndef arch_atomic_fetch_dec_acquire static __always_inline int arch_atomic_fetch_dec_acquire(atomic_t *v) { return arch_atomic_fetch_sub_acquire(1, v); } #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire #endif #ifndef arch_atomic_fetch_dec_release static __always_inline int arch_atomic_fetch_dec_release(atomic_t *v) { return arch_atomic_fetch_sub_release(1, v); } #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release #endif #ifndef arch_atomic_fetch_dec_relaxed static __always_inline int arch_atomic_fetch_dec_relaxed(atomic_t *v) { return arch_atomic_fetch_sub_relaxed(1, v); } #define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed #endif #else /* arch_atomic_fetch_dec_relaxed */ #ifndef arch_atomic_fetch_dec_acquire static __always_inline int arch_atomic_fetch_dec_acquire(atomic_t *v) { int ret = arch_atomic_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire #endif #ifndef arch_atomic_fetch_dec_release static __always_inline int arch_atomic_fetch_dec_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_dec_relaxed(v); } #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release #endif #ifndef arch_atomic_fetch_dec static __always_inline int arch_atomic_fetch_dec(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_dec arch_atomic_fetch_dec #endif #endif /* arch_atomic_fetch_dec_relaxed */ #ifndef arch_atomic_fetch_and_relaxed #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and #define arch_atomic_fetch_and_release arch_atomic_fetch_and #define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and #else /* arch_atomic_fetch_and_relaxed */ #ifndef arch_atomic_fetch_and_acquire static __always_inline int arch_atomic_fetch_and_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire #endif #ifndef arch_atomic_fetch_and_release static __always_inline int arch_atomic_fetch_and_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_and_relaxed(i, v); } #define arch_atomic_fetch_and_release arch_atomic_fetch_and_release #endif #ifndef arch_atomic_fetch_and static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_and arch_atomic_fetch_and #endif #endif /* arch_atomic_fetch_and_relaxed */ #ifndef arch_atomic_andnot static __always_inline void arch_atomic_andnot(int i, atomic_t *v) { arch_atomic_and(~i, v); } #define arch_atomic_andnot arch_atomic_andnot #endif #ifndef arch_atomic_fetch_andnot_relaxed #ifdef arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot #endif /* arch_atomic_fetch_andnot */ #ifndef arch_atomic_fetch_andnot static __always_inline int arch_atomic_fetch_andnot(int i, atomic_t *v) { return arch_atomic_fetch_and(~i, v); } #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #endif #ifndef arch_atomic_fetch_andnot_acquire static __always_inline int arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) { return arch_atomic_fetch_and_acquire(~i, v); } #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #endif #ifndef arch_atomic_fetch_andnot_release static __always_inline int arch_atomic_fetch_andnot_release(int i, atomic_t *v) { return arch_atomic_fetch_and_release(~i, v); } #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #endif #ifndef arch_atomic_fetch_andnot_relaxed static __always_inline int arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) { return arch_atomic_fetch_and_relaxed(~i, v); } #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed #endif #else /* arch_atomic_fetch_andnot_relaxed */ #ifndef arch_atomic_fetch_andnot_acquire static __always_inline int arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #endif #ifndef arch_atomic_fetch_andnot_release static __always_inline int arch_atomic_fetch_andnot_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_andnot_relaxed(i, v); } #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #endif #ifndef arch_atomic_fetch_andnot static __always_inline int arch_atomic_fetch_andnot(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #endif #endif /* arch_atomic_fetch_andnot_relaxed */ #ifndef arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or #define arch_atomic_fetch_or_release arch_atomic_fetch_or #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or #else /* arch_atomic_fetch_or_relaxed */ #ifndef arch_atomic_fetch_or_acquire static __always_inline int arch_atomic_fetch_or_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire #endif #ifndef arch_atomic_fetch_or_release static __always_inline int arch_atomic_fetch_or_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_or_relaxed(i, v); } #define arch_atomic_fetch_or_release arch_atomic_fetch_or_release #endif #ifndef arch_atomic_fetch_or static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_or arch_atomic_fetch_or #endif #endif /* arch_atomic_fetch_or_relaxed */ #ifndef arch_atomic_fetch_xor_relaxed #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor #else /* arch_atomic_fetch_xor_relaxed */ #ifndef arch_atomic_fetch_xor_acquire static __always_inline int arch_atomic_fetch_xor_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire #endif #ifndef arch_atomic_fetch_xor_release static __always_inline int arch_atomic_fetch_xor_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_xor_relaxed(i, v); } #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release #endif #ifndef arch_atomic_fetch_xor static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #endif #endif /* arch_atomic_fetch_xor_relaxed */ #ifndef arch_atomic_xchg_relaxed #define arch_atomic_xchg_acquire arch_atomic_xchg #define arch_atomic_xchg_release arch_atomic_xchg #define arch_atomic_xchg_relaxed arch_atomic_xchg #else /* arch_atomic_xchg_relaxed */ #ifndef arch_atomic_xchg_acquire static __always_inline int arch_atomic_xchg_acquire(atomic_t *v, int i) { int ret = arch_atomic_xchg_relaxed(v, i); __atomic_acquire_fence(); return ret; } #define arch_atomic_xchg_acquire arch_atomic_xchg_acquire #endif #ifndef arch_atomic_xchg_release static __always_inline int arch_atomic_xchg_release(atomic_t *v, int i) { __atomic_release_fence(); return arch_atomic_xchg_relaxed(v, i); } #define arch_atomic_xchg_release arch_atomic_xchg_release #endif #ifndef arch_atomic_xchg static __always_inline int arch_atomic_xchg(atomic_t *v, int i) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_xchg_relaxed(v, i); __atomic_post_full_fence(); return ret; } #define arch_atomic_xchg arch_atomic_xchg #endif #endif /* arch_atomic_xchg_relaxed */ #ifndef arch_atomic_cmpxchg_relaxed #define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg #define arch_atomic_cmpxchg_release arch_atomic_cmpxchg #define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg #else /* arch_atomic_cmpxchg_relaxed */ #ifndef arch_atomic_cmpxchg_acquire static __always_inline int arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { int ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire #endif #ifndef arch_atomic_cmpxchg_release static __always_inline int arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) { __atomic_release_fence(); return arch_atomic_cmpxchg_relaxed(v, old, new); } #define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release #endif #ifndef arch_atomic_cmpxchg static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic_cmpxchg arch_atomic_cmpxchg #endif #endif /* arch_atomic_cmpxchg_relaxed */ #ifndef arch_atomic_try_cmpxchg_relaxed #ifdef arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg #endif /* arch_atomic_try_cmpxchg */ #ifndef arch_atomic_try_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg #endif #ifndef arch_atomic_try_cmpxchg_acquire static __always_inline bool arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire #endif #ifndef arch_atomic_try_cmpxchg_release static __always_inline bool arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release #endif #ifndef arch_atomic_try_cmpxchg_relaxed static __always_inline bool arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed #endif #else /* arch_atomic_try_cmpxchg_relaxed */ #ifndef arch_atomic_try_cmpxchg_acquire static __always_inline bool arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire #endif #ifndef arch_atomic_try_cmpxchg_release static __always_inline bool arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { __atomic_release_fence(); return arch_atomic_try_cmpxchg_relaxed(v, old, new); } #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release #endif #ifndef arch_atomic_try_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { bool ret; __atomic_pre_full_fence(); ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg #endif #endif /* arch_atomic_try_cmpxchg_relaxed */ #ifndef arch_atomic_sub_and_test /** * arch_atomic_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return arch_atomic_sub_return(i, v) == 0; } #define arch_atomic_sub_and_test arch_atomic_sub_and_test #endif #ifndef arch_atomic_dec_and_test /** * arch_atomic_dec_and_test - decrement and test * @v: pointer of type atomic_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return arch_atomic_dec_return(v) == 0; } #define arch_atomic_dec_and_test arch_atomic_dec_and_test #endif #ifndef arch_atomic_inc_and_test /** * arch_atomic_inc_and_test - increment and test * @v: pointer of type atomic_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return arch_atomic_inc_return(v) == 0; } #define arch_atomic_inc_and_test arch_atomic_inc_and_test #endif #ifndef arch_atomic_add_negative /** * arch_atomic_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return arch_atomic_add_return(i, v) < 0; } #define arch_atomic_add_negative arch_atomic_add_negative #endif #ifndef arch_atomic_fetch_add_unless /** * arch_atomic_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = arch_atomic_read(v); do { if (unlikely(c == u)) break; } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); return c; } #define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless #endif #ifndef arch_atomic_add_unless /** * arch_atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ static __always_inline bool arch_atomic_add_unless(atomic_t *v, int a, int u) { return arch_atomic_fetch_add_unless(v, a, u) != u; } #define arch_atomic_add_unless arch_atomic_add_unless #endif #ifndef arch_atomic_inc_not_zero /** * arch_atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ static __always_inline bool arch_atomic_inc_not_zero(atomic_t *v) { return arch_atomic_add_unless(v, 1, 0); } #define arch_atomic_inc_not_zero arch_atomic_inc_not_zero #endif #ifndef arch_atomic_inc_unless_negative static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v) { int c = arch_atomic_read(v); do { if (unlikely(c < 0)) return false; } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); return true; } #define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative #endif #ifndef arch_atomic_dec_unless_positive static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v) { int c = arch_atomic_read(v); do { if (unlikely(c > 0)) return false; } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); return true; } #define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive #endif #ifndef arch_atomic_dec_if_positive static __always_inline int arch_atomic_dec_if_positive(atomic_t *v) { int dec, c = arch_atomic_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!arch_atomic_try_cmpxchg(v, &c, dec)); return dec; } #define arch_atomic_dec_if_positive arch_atomic_dec_if_positive #endif #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> #endif #ifndef arch_atomic64_read_acquire static __always_inline s64 arch_atomic64_read_acquire(const atomic64_t *v) { return smp_load_acquire(&(v)->counter); } #define arch_atomic64_read_acquire arch_atomic64_read_acquire #endif #ifndef arch_atomic64_set_release static __always_inline void arch_atomic64_set_release(atomic64_t *v, s64 i) { smp_store_release(&(v)->counter, i); } #define arch_atomic64_set_release arch_atomic64_set_release #endif #ifndef arch_atomic64_add_return_relaxed #define arch_atomic64_add_return_acquire arch_atomic64_add_return #define arch_atomic64_add_return_release arch_atomic64_add_return #define arch_atomic64_add_return_relaxed arch_atomic64_add_return #else /* arch_atomic64_add_return_relaxed */ #ifndef arch_atomic64_add_return_acquire static __always_inline s64 arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire #endif #ifndef arch_atomic64_add_return_release static __always_inline s64 arch_atomic64_add_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_add_return_relaxed(i, v); } #define arch_atomic64_add_return_release arch_atomic64_add_return_release #endif #ifndef arch_atomic64_add_return static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_add_return arch_atomic64_add_return #endif #endif /* arch_atomic64_add_return_relaxed */ #ifndef arch_atomic64_fetch_add_relaxed #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add #define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add #else /* arch_atomic64_fetch_add_relaxed */ #ifndef arch_atomic64_fetch_add_acquire static __always_inline s64 arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire #endif #ifndef arch_atomic64_fetch_add_release static __always_inline s64 arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_add_relaxed(i, v); } #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release #endif #ifndef arch_atomic64_fetch_add static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_add arch_atomic64_fetch_add #endif #endif /* arch_atomic64_fetch_add_relaxed */ #ifndef arch_atomic64_sub_return_relaxed #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return #define arch_atomic64_sub_return_release arch_atomic64_sub_return #define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return #else /* arch_atomic64_sub_return_relaxed */ #ifndef arch_atomic64_sub_return_acquire static __always_inline s64 arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire #endif #ifndef arch_atomic64_sub_return_release static __always_inline s64 arch_atomic64_sub_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_sub_return_relaxed(i, v); } #define arch_atomic64_sub_return_release arch_atomic64_sub_return_release #endif #ifndef arch_atomic64_sub_return static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_sub_return arch_atomic64_sub_return #endif #endif /* arch_atomic64_sub_return_relaxed */ #ifndef arch_atomic64_fetch_sub_relaxed #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub #define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub #else /* arch_atomic64_fetch_sub_relaxed */ #ifndef arch_atomic64_fetch_sub_acquire static __always_inline s64 arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire #endif #ifndef arch_atomic64_fetch_sub_release static __always_inline s64 arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_sub_relaxed(i, v); } #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release #endif #ifndef arch_atomic64_fetch_sub static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub #endif #endif /* arch_atomic64_fetch_sub_relaxed */ #ifndef arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { arch_atomic64_add(1, v); } #define arch_atomic64_inc arch_atomic64_inc #endif #ifndef arch_atomic64_inc_return_relaxed #ifdef arch_atomic64_inc_return #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return #define arch_atomic64_inc_return_release arch_atomic64_inc_return #define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return #endif /* arch_atomic64_inc_return */ #ifndef arch_atomic64_inc_return static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { return arch_atomic64_add_return(1, v); } #define arch_atomic64_inc_return arch_atomic64_inc_return #endif #ifndef arch_atomic64_inc_return_acquire static __always_inline s64 arch_atomic64_inc_return_acquire(atomic64_t *v) { return arch_atomic64_add_return_acquire(1, v); } #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire #endif #ifndef arch_atomic64_inc_return_release static __always_inline s64 arch_atomic64_inc_return_release(atomic64_t *v) { return arch_atomic64_add_return_release(1, v); } #define arch_atomic64_inc_return_release arch_atomic64_inc_return_release #endif #ifndef arch_atomic64_inc_return_relaxed static __always_inline s64 arch_atomic64_inc_return_relaxed(atomic64_t *v) { return arch_atomic64_add_return_relaxed(1, v); } #define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed #endif #else /* arch_atomic64_inc_return_relaxed */ #ifndef arch_atomic64_inc_return_acquire static __always_inline s64 arch_atomic64_inc_return_acquire(atomic64_t *v) { s64 ret = arch_atomic64_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire #endif #ifndef arch_atomic64_inc_return_release static __always_inline s64 arch_atomic64_inc_return_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_inc_return_relaxed(v); } #define arch_atomic64_inc_return_release arch_atomic64_inc_return_release #endif #ifndef arch_atomic64_inc_return static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_inc_return arch_atomic64_inc_return #endif #endif /* arch_atomic64_inc_return_relaxed */ #ifndef arch_atomic64_fetch_inc_relaxed #ifdef arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc #endif /* arch_atomic64_fetch_inc */ #ifndef arch_atomic64_fetch_inc static __always_inline s64 arch_atomic64_fetch_inc(atomic64_t *v) { return arch_atomic64_fetch_add(1, v); } #define arch_atomic64_fetch_inc arch_atomic64_fetch_inc #endif #ifndef arch_atomic64_fetch_inc_acquire static __always_inline s64 arch_atomic64_fetch_inc_acquire(atomic64_t *v) { return arch_atomic64_fetch_add_acquire(1, v); } #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire #endif #ifndef arch_atomic64_fetch_inc_release static __always_inline s64 arch_atomic64_fetch_inc_release(atomic64_t *v) { return arch_atomic64_fetch_add_release(1, v); } #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release #endif #ifndef arch_atomic64_fetch_inc_relaxed static __always_inline s64 arch_atomic64_fetch_inc_relaxed(atomic64_t *v) { return arch_atomic64_fetch_add_relaxed(1, v); } #define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed #endif #else /* arch_atomic64_fetch_inc_relaxed */ #ifndef arch_atomic64_fetch_inc_acquire static __always_inline s64 arch_atomic64_fetch_inc_acquire(atomic64_t *v) { s64 ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire #endif #ifndef arch_atomic64_fetch_inc_release static __always_inline s64 arch_atomic64_fetch_inc_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_inc_relaxed(v); } #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release #endif #ifndef arch_atomic64_fetch_inc static __always_inline s64 arch_atomic64_fetch_inc(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_inc arch_atomic64_fetch_inc #endif #endif /* arch_atomic64_fetch_inc_relaxed */ #ifndef arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { arch_atomic64_sub(1, v); } #define arch_atomic64_dec arch_atomic64_dec #endif #ifndef arch_atomic64_dec_return_relaxed #ifdef arch_atomic64_dec_return #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return #define arch_atomic64_dec_return_release arch_atomic64_dec_return #define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return #endif /* arch_atomic64_dec_return */ #ifndef arch_atomic64_dec_return static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { return arch_atomic64_sub_return(1, v); } #define arch_atomic64_dec_return arch_atomic64_dec_return #endif #ifndef arch_atomic64_dec_return_acquire static __always_inline s64 arch_atomic64_dec_return_acquire(atomic64_t *v) { return arch_atomic64_sub_return_acquire(1, v); } #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire #endif #ifndef arch_atomic64_dec_return_release static __always_inline s64 arch_atomic64_dec_return_release(atomic64_t *v) { return arch_atomic64_sub_return_release(1, v); } #define arch_atomic64_dec_return_release arch_atomic64_dec_return_release #endif #ifndef arch_atomic64_dec_return_relaxed static __always_inline s64 arch_atomic64_dec_return_relaxed(atomic64_t *v) { return arch_atomic64_sub_return_relaxed(1, v); } #define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed #endif #else /* arch_atomic64_dec_return_relaxed */ #ifndef arch_atomic64_dec_return_acquire static __always_inline s64 arch_atomic64_dec_return_acquire(atomic64_t *v) { s64 ret = arch_atomic64_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire #endif #ifndef arch_atomic64_dec_return_release static __always_inline s64 arch_atomic64_dec_return_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_dec_return_relaxed(v); } #define arch_atomic64_dec_return_release arch_atomic64_dec_return_release #endif #ifndef arch_atomic64_dec_return static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_dec_return arch_atomic64_dec_return #endif #endif /* arch_atomic64_dec_return_relaxed */ #ifndef arch_atomic64_fetch_dec_relaxed #ifdef arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec #endif /* arch_atomic64_fetch_dec */ #ifndef arch_atomic64_fetch_dec static __always_inline s64 arch_atomic64_fetch_dec(atomic64_t *v) { return arch_atomic64_fetch_sub(1, v); } #define arch_atomic64_fetch_dec arch_atomic64_fetch_dec #endif #ifndef arch_atomic64_fetch_dec_acquire static __always_inline s64 arch_atomic64_fetch_dec_acquire(atomic64_t *v) { return arch_atomic64_fetch_sub_acquire(1, v); } #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire #endif #ifndef arch_atomic64_fetch_dec_release static __always_inline s64 arch_atomic64_fetch_dec_release(atomic64_t *v) { return arch_atomic64_fetch_sub_release(1, v); } #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release #endif #ifndef arch_atomic64_fetch_dec_relaxed static __always_inline s64 arch_atomic64_fetch_dec_relaxed(atomic64_t *v) { return arch_atomic64_fetch_sub_relaxed(1, v); } #define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed #endif #else /* arch_atomic64_fetch_dec_relaxed */ #ifndef arch_atomic64_fetch_dec_acquire static __always_inline s64 arch_atomic64_fetch_dec_acquire(atomic64_t *v) { s64 ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire #endif #ifndef arch_atomic64_fetch_dec_release static __always_inline s64 arch_atomic64_fetch_dec_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_dec_relaxed(v); } #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release #endif #ifndef arch_atomic64_fetch_dec static __always_inline s64 arch_atomic64_fetch_dec(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_dec arch_atomic64_fetch_dec #endif #endif /* arch_atomic64_fetch_dec_relaxed */ #ifndef arch_atomic64_fetch_and_relaxed #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and #define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and #else /* arch_atomic64_fetch_and_relaxed */ #ifndef arch_atomic64_fetch_and_acquire static __always_inline s64 arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire #endif #ifndef arch_atomic64_fetch_and_release static __always_inline s64 arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_and_relaxed(i, v); } #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release #endif #ifndef arch_atomic64_fetch_and static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_and arch_atomic64_fetch_and #endif #endif /* arch_atomic64_fetch_and_relaxed */ #ifndef arch_atomic64_andnot static __always_inline void arch_atomic64_andnot(s64 i, atomic64_t *v) { arch_atomic64_and(~i, v); } #define arch_atomic64_andnot arch_atomic64_andnot #endif #ifndef arch_atomic64_fetch_andnot_relaxed #ifdef arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot #endif /* arch_atomic64_fetch_andnot */ #ifndef arch_atomic64_fetch_andnot static __always_inline s64 arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and(~i, v); } #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #endif #ifndef arch_atomic64_fetch_andnot_acquire static __always_inline s64 arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_acquire(~i, v); } #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #endif #ifndef arch_atomic64_fetch_andnot_release static __always_inline s64 arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_release(~i, v); } #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #endif #ifndef arch_atomic64_fetch_andnot_relaxed static __always_inline s64 arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_relaxed(~i, v); } #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed #endif #else /* arch_atomic64_fetch_andnot_relaxed */ #ifndef arch_atomic64_fetch_andnot_acquire static __always_inline s64 arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #endif #ifndef arch_atomic64_fetch_andnot_release static __always_inline s64 arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_andnot_relaxed(i, v); } #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #endif #ifndef arch_atomic64_fetch_andnot static __always_inline s64 arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #endif #endif /* arch_atomic64_fetch_andnot_relaxed */ #ifndef arch_atomic64_fetch_or_relaxed #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or #define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or #else /* arch_atomic64_fetch_or_relaxed */ #ifndef arch_atomic64_fetch_or_acquire static __always_inline s64 arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire #endif #ifndef arch_atomic64_fetch_or_release static __always_inline s64 arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_or_relaxed(i, v); } #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release #endif #ifndef arch_atomic64_fetch_or static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_or arch_atomic64_fetch_or #endif #endif /* arch_atomic64_fetch_or_relaxed */ #ifndef arch_atomic64_fetch_xor_relaxed #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor #define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor #else /* arch_atomic64_fetch_xor_relaxed */ #ifndef arch_atomic64_fetch_xor_acquire static __always_inline s64 arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire #endif #ifndef arch_atomic64_fetch_xor_release static __always_inline s64 arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_xor_relaxed(i, v); } #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release #endif #ifndef arch_atomic64_fetch_xor static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor #endif #endif /* arch_atomic64_fetch_xor_relaxed */ #ifndef arch_atomic64_xchg_relaxed #define arch_atomic64_xchg_acquire arch_atomic64_xchg #define arch_atomic64_xchg_release arch_atomic64_xchg #define arch_atomic64_xchg_relaxed arch_atomic64_xchg #else /* arch_atomic64_xchg_relaxed */ #ifndef arch_atomic64_xchg_acquire static __always_inline s64 arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) { s64 ret = arch_atomic64_xchg_relaxed(v, i); __atomic_acquire_fence(); return ret; } #define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire #endif #ifndef arch_atomic64_xchg_release static __always_inline s64 arch_atomic64_xchg_release(atomic64_t *v, s64 i) { __atomic_release_fence(); return arch_atomic64_xchg_relaxed(v, i); } #define arch_atomic64_xchg_release arch_atomic64_xchg_release #endif #ifndef arch_atomic64_xchg static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 i) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_xchg_relaxed(v, i); __atomic_post_full_fence(); return ret; } #define arch_atomic64_xchg arch_atomic64_xchg #endif #endif /* arch_atomic64_xchg_relaxed */ #ifndef arch_atomic64_cmpxchg_relaxed #define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg #define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg #define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg #else /* arch_atomic64_cmpxchg_relaxed */ #ifndef arch_atomic64_cmpxchg_acquire static __always_inline s64 arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire #endif #ifndef arch_atomic64_cmpxchg_release static __always_inline s64 arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { __atomic_release_fence(); return arch_atomic64_cmpxchg_relaxed(v, old, new); } #define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release #endif #ifndef arch_atomic64_cmpxchg static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg #endif #endif /* arch_atomic64_cmpxchg_relaxed */ #ifndef arch_atomic64_try_cmpxchg_relaxed #ifdef arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg #endif /* arch_atomic64_try_cmpxchg */ #ifndef arch_atomic64_try_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg #endif #ifndef arch_atomic64_try_cmpxchg_acquire static __always_inline bool arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire #endif #ifndef arch_atomic64_try_cmpxchg_release static __always_inline bool arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release #endif #ifndef arch_atomic64_try_cmpxchg_relaxed static __always_inline bool arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed #endif #else /* arch_atomic64_try_cmpxchg_relaxed */ #ifndef arch_atomic64_try_cmpxchg_acquire static __always_inline bool arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire #endif #ifndef arch_atomic64_try_cmpxchg_release static __always_inline bool arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { __atomic_release_fence(); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); } #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release #endif #ifndef arch_atomic64_try_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg #endif #endif /* arch_atomic64_try_cmpxchg_relaxed */ #ifndef arch_atomic64_sub_and_test /** * arch_atomic64_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic64_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) { return arch_atomic64_sub_return(i, v) == 0; } #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test #endif #ifndef arch_atomic64_dec_and_test /** * arch_atomic64_dec_and_test - decrement and test * @v: pointer of type atomic64_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) { return arch_atomic64_dec_return(v) == 0; } #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test #endif #ifndef arch_atomic64_inc_and_test /** * arch_atomic64_inc_and_test - increment and test * @v: pointer of type atomic64_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) { return arch_atomic64_inc_return(v) == 0; } #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test #endif #ifndef arch_atomic64_add_negative /** * arch_atomic64_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic64_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) { return arch_atomic64_add_return(i, v) < 0; } #define arch_atomic64_add_negative arch_atomic64_add_negative #endif #ifndef arch_atomic64_fetch_add_unless /** * arch_atomic64_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 c = arch_atomic64_read(v); do { if (unlikely(c == u)) break; } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); return c; } #define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless #endif #ifndef arch_atomic64_add_unless /** * arch_atomic64_add_unless - add unless the number is already a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ static __always_inline bool arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { return arch_atomic64_fetch_add_unless(v, a, u) != u; } #define arch_atomic64_add_unless arch_atomic64_add_unless #endif #ifndef arch_atomic64_inc_not_zero /** * arch_atomic64_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic64_t * * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ static __always_inline bool arch_atomic64_inc_not_zero(atomic64_t *v) { return arch_atomic64_add_unless(v, 1, 0); } #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero #endif #ifndef arch_atomic64_inc_unless_negative static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v) { s64 c = arch_atomic64_read(v); do { if (unlikely(c < 0)) return false; } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); return true; } #define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative #endif #ifndef arch_atomic64_dec_unless_positive static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v) { s64 c = arch_atomic64_read(v); do { if (unlikely(c > 0)) return false; } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); return true; } #define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive #endif #ifndef arch_atomic64_dec_if_positive static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) { s64 dec, c = arch_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); return dec; } #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ // 90cd26cfd69d2250303d654955a0cc12620fb91b |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/uaccess.h> #include <linux/nospec.h> /* out-of-line parts */ #ifndef INLINE_COPY_FROM_USER unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } EXPORT_SYMBOL(_copy_from_user); #endif #ifndef INLINE_COPY_TO_USER unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (likely(access_ok(to, n))) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } EXPORT_SYMBOL(_copy_to_user); #endif /** * check_zeroed_user: check if a userspace buffer only contains zero bytes * @from: Source address, in userspace. * @size: Size of buffer. * * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for * userspace addresses (and is more efficient because we don't care where the * first non-zero byte is). * * Returns: * * 0: There were non-zero bytes present in the buffer. * * 1: The buffer was full of zero bytes. * * -EFAULT: access to userspace failed. */ int check_zeroed_user(const void __user *from, size_t size) { unsigned long val; uintptr_t align = (uintptr_t) from % sizeof(unsigned long); if (unlikely(size == 0)) return 1; from -= align; size += align; if (!user_read_access_begin(from, size)) return -EFAULT; unsafe_get_user(val, (unsigned long __user *) from, err_fault); if (align) val &= ~aligned_byte_mask(align); while (size > sizeof(unsigned long)) { if (unlikely(val)) goto done; from += sizeof(unsigned long); size -= sizeof(unsigned long); unsafe_get_user(val, (unsigned long __user *) from, err_fault); } if (size < sizeof(unsigned long)) val &= aligned_byte_mask(size); done: user_read_access_end(); return (val == 0); err_fault: user_read_access_end(); return -EFAULT; } EXPORT_SYMBOL(check_zeroed_user); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.rst for more details. */ #ifndef __LINUX_LOCKDEP_H #define __LINUX_LOCKDEP_H #include <linux/lockdep_types.h> #include <linux/smp.h> #include <asm/percpu.h> struct task_struct; /* for sysctl */ extern int prove_locking; extern int lock_stat; #ifdef CONFIG_LOCKDEP #include <linux/linkage.h> #include <linux/list.h> #include <linux/debug_locks.h> #include <linux/stacktrace.h> static inline void lockdep_copy_map(struct lockdep_map *to, struct lockdep_map *from) { int i; *to = *from; /* * Since the class cache can be modified concurrently we could observe * half pointers (64bit arch using 32bit copy insns). Therefore clear * the caches and take the performance hit. * * XXX it doesn't work well with lockdep_set_class_and_subclass(), since * that relies on cache abuse. */ for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) to->class_cache[i] = NULL; } /* * Every lock has a list of other locks that were taken after it. * We only grow the list, never remove from it: */ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; const struct lock_trace *trace; u16 distance; /* bitmap of different dependencies from head to this */ u8 dep; /* used by BFS to record whether "prev -> this" only has -(*R)-> */ u8 only_xr; /* * The parent field is used to implement breadth-first search, and the * bit 0 is reused to indicate if the lock has been accessed in BFS. */ struct lock_list *parent; }; /** * struct lock_chain - lock dependency chain record * * @irq_context: the same as irq_context in held_lock below * @depth: the number of held locks in this chain * @base: the index in chain_hlocks for this chain * @entry: the collided lock chains in lock_chain hash list * @chain_key: the hash key of this lock_chain */ struct lock_chain { /* see BUILD_BUG_ON()s in add_chain_cache() */ unsigned int irq_context : 2, depth : 6, base : 24; /* 4 byte hole */ struct hlist_node entry; u64 chain_key; }; #define MAX_LOCKDEP_KEYS_BITS 13 #define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) #define INITIAL_CHAIN_KEY -1 struct held_lock { /* * One-way hash of the dependency chain up to this point. We * hash the hashes step by step as the dependency chain grows. * * We use it for dependency-caching and we skip detection * passes and dependency-updates if there is a cache-hit, so * it is absolutely critical for 100% coverage of the validator * to have a unique key value for every unique dependency path * that can occur in the system, to make a unique hash value * as likely as possible - hence the 64-bit width. * * The task struct holds the current hash value (initialized * with zero), here we store the previous hash value: */ u64 prev_chain_key; unsigned long acquire_ip; struct lockdep_map *instance; struct lockdep_map *nest_lock; #ifdef CONFIG_LOCK_STAT u64 waittime_stamp; u64 holdtime_stamp; #endif /* * class_idx is zero-indexed; it points to the element in * lock_classes this held lock instance belongs to. class_idx is in * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. */ unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; /* * The lock-stack is unified in that the lock chains of interrupt * contexts nest ontop of process context chains, but we 'separate' * the hashes by starting with 0 if we cross into an interrupt * context, and we also keep do not add cross-context lock * dependencies - the lock usage graph walking covers that area * anyway, and we'd just unnecessarily increase the number of * dependencies otherwise. [Note: hardirq and softirq contexts * are separated from each other too.] * * The following field is used to detect when we cross into an * interrupt context: */ unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ unsigned int trylock:1; /* 16 bits */ unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ unsigned int pin_count; }; /* * Initialization, self-test and debugging-output methods: */ extern void lockdep_init(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); extern asmlinkage void lockdep_sys_exit(void); extern void lockdep_set_selftest_task(struct task_struct *task); extern void lockdep_init_task(struct task_struct *task); /* * Split the recrursion counter in two to readily detect 'off' vs recursion. */ #define LOCKDEP_RECURSION_BITS 16 #define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS) #define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1) /* * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due * to header dependencies. */ #define lockdep_off() \ do { \ current->lockdep_recursion += LOCKDEP_OFF; \ } while (0) #define lockdep_on() \ do { \ current->lockdep_recursion -= LOCKDEP_OFF; \ } while (0) extern void lockdep_register_key(struct lock_class_key *key); extern void lockdep_unregister_key(struct lock_class_key *key); /* * These methods are used by specific locking variants (spinlocks, * rwlocks, mutexes and rwsems) to pass init/acquire/release events * to lockdep: */ extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type); static inline void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer) { lockdep_init_map_type(lock, name, key, subclass, inner, outer, LD_LOCK_NORMAL); } static inline void lockdep_init_map_wait(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner) { lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV); } static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass) { lockdep_init_map_wait(lock, name, key, subclass, LD_WAIT_INV); } /* * Reinitialize a lock key - for cases where there is special locking or * special initialization of locks so that the validator gets the scope * of dependencies wrong: they are either too broad (they need a class-split) * or they are too narrow (they suffer from a false class-split): */ #define lockdep_set_class(lock, key) \ lockdep_init_map_type(&(lock)->dep_map, #key, key, 0, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_class_and_name(lock, key, name) \ lockdep_init_map_type(&(lock)->dep_map, name, key, 0, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_class_and_subclass(lock, key, sub) \ lockdep_init_map_type(&(lock)->dep_map, #key, key, sub, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_subclass(lock, sub) \ lockdep_init_map_type(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_novalidate_class(lock) \ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) /* * Compare locking classes */ #define lockdep_match_class(lock, key) lockdep_match_key(&(lock)->dep_map, key) static inline int lockdep_match_key(struct lockdep_map *lock, struct lock_class_key *key) { return lock->key == key; } /* * Acquire a lock. * * Values for "read": * * 0: exclusive (write) acquire * 1: read-acquire (no recursion allowed) * 2: read-acquire with same-instance recursion allowed * * Values for check: * * 0: simple checks (freeing, held-at-exit-time, etc.) * 1: full validation */ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); extern void lock_release(struct lockdep_map *lock, unsigned long ip); /* * Same "read" as for lock_acquire(), except -1 means any. */ extern int lock_is_held_type(const struct lockdep_map *lock, int read); static inline int lock_is_held(const struct lockdep_map *lock) { return lock_is_held_type(lock, -1); } #define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) #define lockdep_is_held_type(lock, r) lock_is_held_type(&(lock)->dep_map, (r)) extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, unsigned long ip); static inline void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, unsigned long ip) { lock_set_class(lock, lock->name, lock->key, subclass, ip); } extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); #define NIL_COOKIE (struct pin_cookie){ .val = 0U, } extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) #define lockdep_assert_held(l) do { \ WARN_ON(debug_locks && !lockdep_is_held(l)); \ } while (0) #define lockdep_assert_held_write(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 0)); \ } while (0) #define lockdep_assert_held_read(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 1)); \ } while (0) #define lockdep_assert_held_once(l) do { \ WARN_ON_ONCE(debug_locks && !lockdep_is_held(l)); \ } while (0) #define lockdep_assert_none_held_once() do { \ WARN_ON_ONCE(debug_locks && current->lockdep_depth); \ } while (0) #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) #define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) { } static inline void lockdep_off(void) { } static inline void lockdep_on(void) { } static inline void lockdep_set_selftest_task(struct task_struct *task) { } # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_wait(lock, name, key, sub, inner) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) # define lockdep_set_class_and_name(lock, key, name) \ do { (void)(key); (void)(name); } while (0) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) #define lockdep_set_subclass(lock, sub) do { } while (0) #define lockdep_set_novalidate_class(lock) do { } while (0) /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP * case since the result is not well defined and the caller should rather * #ifdef the call himself. */ # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) # define lockdep_sys_exit() do { } while (0) static inline void lockdep_register_key(struct lock_class_key *key) { } static inline void lockdep_unregister_key(struct lock_class_key *key) { } #define lockdep_depth(tsk) (0) #define lockdep_is_held_type(l, r) (1) #define lockdep_assert_held(l) do { (void)(l); } while (0) #define lockdep_assert_held_write(l) do { (void)(l); } while (0) #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_assert_none_held_once() do { } while (0) #define lockdep_recursing(tsk) (0) #define NIL_COOKIE (struct pin_cookie){ } #define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) #endif /* !LOCKDEP */ enum xhlock_context_t { XHLOCK_HARD, XHLOCK_SOFT, XHLOCK_CTX_NR, }; #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) /* * To initialize a lockdep_map statically use this macro. * Note that _name must not be NULL. */ #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_free_task(struct task_struct *task) {} #ifdef CONFIG_LOCK_STAT extern void lock_contended(struct lockdep_map *lock, unsigned long ip); extern void lock_acquired(struct lockdep_map *lock, unsigned long ip); #define LOCK_CONTENDED(_lock, try, lock) \ do { \ if (!try(_lock)) { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ lock(_lock); \ } \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ } while (0) #define LOCK_CONTENDED_RETURN(_lock, try, lock) \ ({ \ int ____err = 0; \ if (!try(_lock)) { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ ____err = lock(_lock); \ } \ if (!____err) \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ ____err; \ }) #else /* CONFIG_LOCK_STAT */ #define lock_contended(lockdep_map, ip) do {} while (0) #define lock_acquired(lockdep_map, ip) do {} while (0) #define LOCK_CONTENDED(_lock, try, lock) \ lock(_lock) #define LOCK_CONTENDED_RETURN(_lock, try, lock) \ lock(_lock) #endif /* CONFIG_LOCK_STAT */ #ifdef CONFIG_LOCKDEP /* * On lockdep we dont want the hand-coded irq-enable of * _raw_*_lock_flags() code, because lockdep assumes * that interrupts are not re-enabled during lock-acquire: */ #define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ LOCK_CONTENDED((_lock), (try), (lock)) #else /* CONFIG_LOCKDEP */ #define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ lockfl((_lock), (flags)) #endif /* CONFIG_LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING extern void print_irqtrace_events(struct task_struct *curr); #else static inline void print_irqtrace_events(struct task_struct *curr) { } #endif /* Variable used to make lockdep treat read_lock() as recursive in selftests */ #ifdef CONFIG_DEBUG_LOCKING_API_SELFTESTS extern unsigned int force_read_lock_recursive; #else /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ #define force_read_lock_recursive 0 #endif /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ #ifdef CONFIG_LOCKDEP extern bool read_lock_is_recursive(void); #else /* CONFIG_LOCKDEP */ /* If !LOCKDEP, the value is meaningless */ #define read_lock_is_recursive() 0 #endif /* * For trivial one-depth nesting of a lock-class, the following * global define can be used. (Subsystems with multiple levels * of nesting should define their own lock-nesting subclasses.) */ #define SINGLE_DEPTH_NESTING 1 /* * Map the dependency ops to NOP or to real lockdep ops, depending * on the per lock-class debug mode: */ #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define spin_release(l, i) lock_release(l, i) #define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwlock_acquire_read(l, s, t, i) \ do { \ if (read_lock_is_recursive()) \ lock_acquire_shared_recursive(l, s, t, NULL, i); \ else \ lock_acquire_shared(l, s, t, NULL, i); \ } while (0) #define rwlock_release(l, i) lock_release(l, i) #define seqcount_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define seqcount_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) #define seqcount_release(l, i) lock_release(l, i) #define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define mutex_release(l, i) lock_release(l, i) #define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_nested(lock, subclass) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL, \ _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); DECLARE_PER_CPU(unsigned int, lockdep_recursion); #define __lockdep_enabled (debug_locks && !this_cpu_read(lockdep_recursion)) #define lockdep_assert_irqs_enabled() \ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ WARN_ON_ONCE(__lockdep_enabled && this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() != 0 || \ !this_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() == 0 && \ this_cpu_read(hardirqs_enabled))); \ } while (0) #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) # define might_lock_nested(lock, subclass) do { } while (0) # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING # define lockdep_assert_RT_in_threaded_ctx() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ lockdep_hardirq_context() && \ !(current->hardirq_threaded || current->irq_config), \ "Not in threaded context on PREEMPT_RT as expected\n"); \ } while (0) #else # define lockdep_assert_RT_in_threaded_ctx() do { } while (0) #endif #ifdef CONFIG_LOCKDEP void lockdep_rcu_suspicious(const char *file, const int line, const char *s); #else static inline void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { } #endif #endif /* __LINUX_LOCKDEP_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> #ifdef CONFIG_SET_FS /* * Force the uaccess routines to be wired up for actual userspace access, * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone * using force_uaccess_end below. */ static inline mm_segment_t force_uaccess_begin(void) { mm_segment_t fs = get_fs(); set_fs(USER_DS); return fs; } static inline void force_uaccess_end(mm_segment_t oldfs) { set_fs(oldfs); } #else /* CONFIG_SET_FS */ typedef struct { /* empty dummy */ } mm_segment_t; #ifndef TASK_SIZE_MAX #define TASK_SIZE_MAX TASK_SIZE #endif #define uaccess_kernel() (false) #define user_addr_max() (TASK_SIZE_MAX) static inline mm_segment_t force_uaccess_begin(void) { return (mm_segment_t) { }; } static inline void force_uaccess_end(mm_segment_t oldfs) { } #endif /* CONFIG_SET_FS */ /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } #ifdef INLINE_COPY_FROM_USER static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } #else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (likely(check_copy_size(to, n, false))) n = _copy_from_user(to, from, n); return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (likely(check_copy_size(from, n, true))) n = _copy_to_user(to, from, n); return n; } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(to, n) && access_ok(from, n)) n = raw_copy_in_user(to, from, n); return n; } #endif #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { atomic_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (atomic_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) extern struct group_info init_groups; #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; #ifdef CONFIG_DEBUG_CREDENTIALS atomic_t subscribers; /* number of processes subscribed */ void *put_addr; unsigned magic; #define CRED_MAGIC 0x43736564 #define CRED_MAGIC_DEAD 0x44656144 #endif kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* subjective LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int change_create_files_as(struct cred *, struct inode *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); /* * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS extern void __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); extern bool creds_are_invalid(const struct cred *cred); static inline void __validate_creds(const struct cred *cred, const char *file, unsigned line) { if (unlikely(creds_are_invalid(cred))) __invalid_creds(cred, file, line); } #define validate_creds(cred) \ do { \ __validate_creds((cred), __FILE__, __LINE__); \ } while(0) #define validate_process_creds() \ do { \ __validate_process_creds(current, __FILE__, __LINE__); \ } while(0) extern void validate_creds_for_do_exit(struct task_struct *); #else static inline void validate_creds(const struct cred *cred) { } static inline void validate_creds_for_do_exit(struct task_struct *tsk) { } static inline void validate_process_creds(void) { } #endif static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { atomic_long_inc(&cred->usage); return cred; } /** * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred(const struct cred *_cred) { struct cred *cred = (struct cred *) _cred; if (cred) { validate_creds(cred); if (atomic_long_dec_and_test(&(cred)->usage)) __put_cred(cred); } } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages not added to the page allocator when onlining a section because * they were excluded via the online_page_callback() or because they are * PG_hwpoison. * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - Pages part of an offline section (struct pages of offline sections should * not be trusted as they will be initialized when first onlined). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_uptodate tells whether the page's contents is valid. When a read * completes, the page becomes uptodate, unless a disk I/O error happened. * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_error is set to indicate that an I/O error occurred on this page. * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the *_dontuse flags. Use the macros. Otherwise you'll break * locked- and dirty-page accounting. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ PG_head, /* A head page */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PG_uncached, /* Page has been mapped as uncached */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_64BIT PG_arch_2, #endif __NR_PAGEFLAGS, /* Filesystems */ PG_checked = PG_owner_priv_1, /* SwapBacked */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, /* Compound pages. Stored in first tail page's flags */ PG_double_map = PG_workingset, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, }; #ifndef __GENERATING_BOUNDS_H struct page; /* forward declaration */ static inline struct page *compound_head(struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return (struct page *) (head - 1); return page; } static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; } static __always_inline int PageCompound(struct page *page) { return test_bit(PG_head, &page->flags) || PageTail(page); } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return page->flags == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_ONLY_HEAD: * for compound page, callers only ever operate on the head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_ONLY_HEAD(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(PageTail(page), page); \ PF_POISONED_CHECK(page); }) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname, policy) \ static __always_inline int Page##uname(struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) #define TESTSCFLAG_FALSE(uname) \ TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) __SETPAGEFLAG(Referenced, referenced, PF_HEAD) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause releasepage() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY) __CLEARPAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #else PAGEFLAG_FALSE(HighMem) #endif #ifdef CONFIG_SWAP static __always_inline int PageSwapCache(struct page *page) { #ifdef CONFIG_THP_SWAP page = compound_head(page); #endif return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); } SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else PAGEFLAG_FALSE(SwapCache) #endif PAGEFLAG(Unevictable, unevictable, PF_HEAD) __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) #ifdef CONFIG_MMU PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) TESTSCFLAG_FALSE(Mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(Uncached) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) extern bool take_page_off_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) TESTPAGEFLAG(Young, young, PF_ANY) SETPAGEFLAG(Young, young, PF_ANY) TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then page->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then page->mapping points a struct address_space. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline int PageAnon(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline int __PageMovable(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline int PageKsm(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } #else TESTPAGEFLAG_FALSE(Ksm) #endif u64 stable_page_flags(struct page *page); static inline int PageUptodate(struct page *page) { int ret; page = compound_head(page); ret = test_bit(PG_uptodate, &(page)->flags); /* * Must ensure that the data we read out of the page is loaded * _after_ we've loaded page->flags to check for PageUptodate. * We can skip the barrier if the page is not uptodate, because * we wouldn't be reading anything from it. * * See SetPageUptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static __always_inline void __SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); __set_bit(PG_uptodate, &page->flags); } static __always_inline void SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the page * uptodate are actually visible before PageUptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, &page->flags); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) int test_clear_page_writeback(struct page *page); int __test_set_page_writeback(struct page *page, bool keep_write); #define test_set_page_writeback(page) \ __test_set_page_writeback(page, false) #define test_set_page_writeback_keepwrite(page) \ __test_set_page_writeback(page, true) static inline void set_page_writeback(struct page *page) { test_set_page_writeback(page); } static inline void set_page_writeback_keepwrite(struct page *page) { test_set_page_writeback_keepwrite(page); } __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); bool page_huge_active(struct page *page); #else TESTPAGEFLAG_FALSE(Huge) TESTPAGEFLAG_FALSE(HeadHuge) static inline bool page_huge_active(struct page *page) { return 0; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(struct page *page) { return PageCompound(page); } /* * PageTransCompoundMap is the same as PageTransCompound, but it also * guarantees the primary MMU has the entire compound page mapped * through pmd_trans_huge, which in turn guarantees the secondary MMUs * can also map the entire compound page. This allows the secondary * MMUs to call get_user_pages() only once for each compound page and * to immediately map the entire compound page with a single secondary * MMU fault. If there will be a pmd split later, the secondary MMUs * will get an update through the MMU notifier invalidation through * split_huge_pmd(). * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the * MMU notifier, otherwise it may result in page->_mapcount check false * positives. * * We have to treat page cache THP differently since every subpage of it * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE * mapped in the current process so comparing subpage's _mapcount to * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { struct page *head; if (!PageTransCompound(page)) return 0; if (PageAnon(page)) return atomic_read(&page->_mapcount) < 0; head = compound_head(page); /* File THP is PMD mapped and not PTE mapped */ return atomic_read(&page->_mapcount) == atomic_read(compound_mapcount_ptr(head)); } /* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransTail(struct page *page) { return PageTail(page); } /* * PageDoubleMap indicates that the compound page is mapped with PTEs as well * as PMDs. * * This is required for optimization of rmap operations for THP: we can postpone * per small page mapcount accounting (and its overhead from atomic operations) * until the first PMD split. * * For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up * by one. This reference will go away with last compound_mapcount. * * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). */ PAGEFLAG(DoubleMap, double_map, PF_SECOND) TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) PAGEFLAG_FALSE(DoubleMap) TESTSCFLAG_FALSE(DoubleMap) #endif /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and * low bits so that an underflow or overflow of page_mapcount() won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 /* Reserve 0x0000007f to catch underflows of page_mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_kmemcg 0x00000200 #define PG_table 0x00000400 #define PG_guard 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) static inline int page_has_type(struct page *page) { return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; } #define PAGE_TYPE_OPS(uname, lname) \ static __always_inline int Page##uname(struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free pages, * allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require to re-set the pages PageOffline() and not giving them to the * buddy via online_page_callback_t. */ PAGE_TYPE_OPS(Offline, offline) /* * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on * pages allocated with __GFP_ACCOUNT. It gets cleared on page free. */ PAGE_TYPE_OPS(Kmemcg, kmemcg) /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard) extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); /* * If network-based swap is enabled, sl*b must keep track of whether pages * were allocated from pfmemalloc reserves. */ static inline int PageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); return PageActive(page); } static inline void SetPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); SetPageActive(page); } static inline void __ClearPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); __ClearPageActive(page); } static inline void ClearPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); ClearPageActive(page); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_slab | 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ (((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * page_has_private - Determine if page has private stuff * @page: The page to be checked * * Determine if a page has private stuff, indicating that release routines * should be invoked upon it. */ static inline int page_has_private(struct page *page) { return !!(page->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_ONLY_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analagous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_INTERNAL_H #define _ASM_X86_FPU_INTERNAL_H #include <linux/compat.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <asm/user.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #include <asm/cpufeature.h> #include <asm/trace/fpu.h> /* * High level FPU state handling functions: */ extern void fpu__prepare_read(struct fpu *fpu); extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); extern void fpu__drop(struct fpu *fpu); extern int fpu__copy(struct task_struct *dst, struct task_struct *src); extern void fpu__clear_user_states(struct fpu *fpu); extern void fpu__clear_all(struct fpu *fpu); extern int fpu__exception_code(struct fpu *fpu, int trap_nr); /* * Boot time FPU initialization functions: */ extern void fpu__init_cpu(void); extern void fpu__init_system_xstate(void); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: */ #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ (void)(x); 0; }) #endif /* * FPU related CPU feature flag helper routines: */ static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { return static_cpu_has(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return static_cpu_has(X86_FEATURE_FXSR); } /* * fpstate handling functions: */ extern union fpregs_state init_fpstate; extern void fpstate_init(union fpregs_state *state); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif static inline void fpstate_init_xstate(struct xregs_state *xsave) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; } static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; fx->mxcsr = MXCSR_DEFAULT; } extern void fpstate_sanitize_xstate(struct fpu *fpu); /* Returns 0 or the negated trap number, which results in -EFAULT for #PF */ #define user_insn(insn, output, input...) \ ({ \ int err; \ \ might_fault(); \ \ asm volatile(ASM_STAC "\n" \ "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: negl %%eax\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn_err(insn, output, input...) \ ({ \ int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: movl $-1,%[err]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE(1b, 3b) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); } static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_kernel_to_fregs(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fregs_err(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_fxregs_to_kernel(struct fpu *fpu) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); } static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); } /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" /* * After this @err contains 0 on success or the negated trap number when * the operation raises an exception. For faults this results in -EFAULT. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n\t" \ ".pushsection .fixup,\"ax\"\n\t" \ "3: negl %%eax\n\t" \ "jmp 2b\n\t" \ ".popsection\n\t" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact * format and supervisor states in addition to modified optimization in * XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * We use XSAVE as a fallback. * * The 661 label is defined in the ALTERNATIVE* macros as the address of the * original instruction which gets replaced. We need to use it here as the * address of the instruction where we might get an exception at. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile(ALTERNATIVE_2(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ ".pushsection .fixup,\"ax\"\n" \ "4: movl $-2, %[err]\n" \ "jmp 3b\n" \ ".popsection\n" \ _ASM_EXTABLE(661b, 4b) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) { u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON(system_state != SYSTEM_BOOTING); if (boot_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * Save processor xstate to xsave area. */ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) { u64 mask = xfeatures_mask_all; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. */ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(xstate, lmask, hmask); } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for * backward compatibility for old applications which don't understand * compacted format of xsave area. */ static inline int copy_xregs_to_user(struct xregs_state __user *buf) { u64 mask = xfeatures_mask_user(); u32 lmask = mask; u32 hmask = mask >> 32; int err; /* * Clear the xsave header first, so that reserved fields are * initialized to zero. */ err = __clear_user(&buf->header, sizeof(buf->header)); if (unlikely(err)) return -EFAULT; stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); return err; } /* * Restore xstate from user space xsave area. */ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; int err; if (static_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } extern int copy_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); else copy_kernel_to_fregs(&fpstate->fsave); } } static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) { /* * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is * pending. Clear the x87 state here by setting it to fixed values. * "m" is a random variable that should be in L1. */ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" "fildl %P[addr]" /* set F?P to defined value */ : : [addr] "m" (fpstate)); } __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); /* * FPU context switch related helper methods: */ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Either one of these invalidation functions is enough. Invalidate * a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* * These generally need preemption protection to work, * do try to avoid using these on their own: */ static inline void fpregs_deactivate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* * Internal helper, do not use directly. Use switch_fpu_return() instead. */ static inline void __fpregs_load_activate(void) { struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return; if (!fpregs_state_valid(fpu, cpu)) { copy_kernel_to_fpregs(&fpu->state); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } /* * FPU state switching for scheduling. * * This is a two-stage process: * * - switch_fpu_prepare() saves the old state. * This is done within the context of the old process. * * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state * will get loaded on return to userspace, or when the kernel needs it. * * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers * are saved in the current thread's FPU register state. * * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not * hold current()'s FPU registers. It is required to load the * registers before returning to userland or using the content * otherwise. * * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ static inline void switch_fpu_prepare(struct task_struct *prev, int cpu) { struct fpu *old_fpu = &prev->thread.fpu; if (static_cpu_has(X86_FEATURE_FPU) && !(prev->flags & PF_KTHREAD)) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ trace_x86_fpu_regs_deactivated(old_fpu); } } /* * Misc helper functions: */ /* * Load PKRU from the FPU context if available. Delay loading of the * complete FPU state until the return to userland. */ static inline void switch_fpu_finish(struct task_struct *next) { u32 pkru_val = init_pkru_value; struct pkru_state *pk; struct fpu *next_fpu = &next->thread.fpu; if (!static_cpu_has(X86_FEATURE_FPU)) return; set_thread_flag(TIF_NEED_FPU_LOAD); if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * PKRU state is switched eagerly because it needs to be valid before we * return to userland e.g. for a copy_to_user() operation. */ if (!(next->flags & PF_KTHREAD)) { /* * If the PKRU bit in xsave.header.xfeatures is not set, * then the PKRU component was in init state, which means * XRSTOR will set PKRU to 0. If the bit is not set then * get_xsave_addr() will return NULL because the PKRU value * in memory is not valid. This means pkru_val has to be * set to 0 and not to init_pkru_value. */ pk = get_xsave_addr(&next_fpu->state.xsave, XFEATURE_PKRU); pkru_val = pk ? pk->pkru : 0; } __write_pkru(pkru_val); } #endif /* _ASM_X86_FPU_INTERNAL_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BITMAP_H #define __LINUX_BITMAP_H #ifndef __ASSEMBLY__ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/types.h> struct device; /* * bitmaps provide bit arrays that consume one or more unsigned * longs. The bitmap interface and available operations are listed * here, in bitmap.h * * Function implementations generic to all architectures are in * lib/bitmap.c. Functions implementations that are architecture * specific are in various include/asm-<arch>/bitops.h headers * and other arch/<arch> specific files. * * See lib/bitmap.c for more details. */ /** * DOC: bitmap overview * * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * * The generated code is more efficient when nbits is known at * compile-time and at most BITS_PER_LONG. * * :: * * bitmap_zero(dst, nbits) *dst = 0UL * bitmap_fill(dst, nbits) *dst = ~0UL * bitmap_copy(dst, src, nbits) *dst = *src * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) * bitmap_complement(dst, src, nbits) *dst = ~(*src) * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? * bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2? * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region * bitmap_next_set_region(map, &start, &end, nbits) Find next set region * bitmap_for_each_clear_region(map, rs, re, start, end) * Iterate over all clear regions * bitmap_for_each_set_region(map, rs, re, start, end) * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long * boundary will be zeroed or filled as well. Consider to use * bitmap_clear() or bitmap_set() to make explicit zeroing or filling * respectively. */ /** * DOC: bitmap bitops * * Also the following operations in asm/bitops.h apply to bitmaps.:: * * set_bit(bit, addr) *addr |= bit * clear_bit(bit, addr) *addr &= ~bit * change_bit(bit, addr) *addr ^= bit * test_bit(bit, addr) Is bit set in *addr? * test_and_set_bit(bit, addr) Set bit and return old value * test_and_clear_bit(bit, addr) Clear bit and return old value * test_and_change_bit(bit, addr) Change bit and return old value * find_first_zero_bit(addr, nbits) Position first zero bit in *addr * find_first_bit(addr, nbits) Position first set bit in *addr * find_next_zero_bit(addr, nbits, bit) * Position next zero bit in *addr >= bit * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit * find_next_and_bit(addr1, addr2, nbits, bit) * Same as find_next_bit, but in * (*addr1 & *addr2) * */ /** * DOC: declare bitmap * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used * to declare an array named 'name' of just enough unsigned longs to * contain all bit positions from 0 to 'bits' - 1. */ /* * Allocation and deallocation of bitmap. * Provided in lib/bitmap.c to avoid circular dependency. */ extern unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); extern unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); extern void bitmap_free(const unsigned long *bitmap); /* Managed variants of the above. */ unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags); /* * lib/bitmap.c provides these functions: */ extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits); extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); extern void __bitmap_set(unsigned long *map, unsigned int start, int len); extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset); /** * bitmap_find_next_zero_area - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ static inline unsigned long bitmap_find_next_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); } extern int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits); extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits); extern int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits); extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else #define bitmap_copy_le bitmap_copy #endif extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); extern int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) /* * The static inlines below do not handle constant nbits==0 correctly, * so make such users (should any ever turn up) call the out-of-line * versions. */ #define small_const_nbits(nbits) \ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); memcpy(dst, src, len); } /* * Copy bitmap and clear tail bits in last word. */ static inline void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } /* * On 32-bit systems bitmaps are represented as u32 arrays internally, and * therefore conversion is not needed when copying data from/to arrays of u32. */ #if BITS_PER_LONG == 64 extern void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits); extern void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr32(bitmap, buf, nbits) \ bitmap_copy_clear_tail((unsigned long *) (bitmap), \ (const unsigned long *) (buf), (nbits)) #define bitmap_to_arr32(buf, bitmap, nbits) \ bitmap_copy_clear_tail((unsigned long *) (buf), \ (const unsigned long *) (bitmap), (nbits)) #endif static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; else __bitmap_or(dst, src1, src2, nbits); } static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; else __bitmap_xor(dst, src1, src2, nbits); } static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); else __bitmap_complement(dst, src, nbits); } #ifdef __LITTLE_ENDIAN #define BITMAP_MEM_ALIGNMENT 8 #else #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) static inline int bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) return !memcmp(src1, src2, nbits / 8); return __bitmap_equal(src1, src2, nbits); } /** * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ static inline bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } static inline int bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; else return __bitmap_intersects(src1, src2, nbits); } static inline int bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); else return __bitmap_subset(src1, src2, nbits); } static inline int bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); return find_first_bit(src, nbits) == nbits; } static inline int bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); return find_first_zero_bit(src, nbits) == nbits; } static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight(src, nbits); } static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0xff, nbits / 8); else __bitmap_set(map, start, nbits); } static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0, nbits / 8); else __bitmap_clear(map, start, nbits); } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; else __bitmap_shift_right(dst, src, shift, nbits); } static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); else __bitmap_shift_left(dst, src, shift, nbits); } static inline void bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); else __bitmap_replace(dst, old, new, mask, nbits); } static inline void bitmap_next_clear_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_zero_bit(bitmap, end, *rs); *re = find_next_bit(bitmap, end, *rs + 1); } static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); } /* * Bitmap region iterators. Iterates over the bitmap between [@start, @end). * @rs and @re should be integer variables and will be set to start and end * index of the current clear or set region. */ #define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ for ((rs) = (start), \ bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ (rs) < (re); \ (rs) = (re) + 1, \ bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) #define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ for ((rs) = (start), \ bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ (rs) < (re); \ (rs) = (re) + 1, \ bitmap_next_set_region((bitmap), &(rs), &(re), (end))) /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value * * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit * integers in 32-bit environment, and 64-bit integers in 64-bit one. * * There are four combinations of endianness and length of the word in linux * ABIs: LE64, BE64, LE32 and BE32. * * On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in * bitmaps and therefore don't require any special handling. * * On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory * prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the * other hand is represented as an array of 32-bit words and the position of * bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that * word. For example, bit #42 is located at 10th position of 2nd word. * It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit * values in memory as it usually does. But for BE we need to swap hi and lo * words manually. * * With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and * lo parts of u64. For LE32 it does nothing, and for BE environment it swaps * hi and lo words, as is expected by bitmap. */ #if __BITS_PER_LONG == 64 #define BITMAP_FROM_U64(n) (n) #else #define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \ ((unsigned long) ((u64)(n) >> 32)) #endif /** * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap * @dst: destination bitmap * * In 32-bit Big Endian kernel, when using ``(u32 *)(&val)[*]`` * to read u64 mask, we will get the wrong word. * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) { dst[0] = mask & ULONG_MAX; if (sizeof(mask) > sizeof(unsigned long)) dst[1] = mask >> 32; } /** * bitmap_get_value8 - get an 8-bit value within a memory region * @map: address to the bitmap memory region * @start: bit offset of the 8-bit value; must be a multiple of 8 * * Returns the 8-bit value located at the @start bit offset within the @src * memory region. */ static inline unsigned long bitmap_get_value8(const unsigned long *map, unsigned long start) { const size_t index = BIT_WORD(start); const unsigned long offset = start % BITS_PER_LONG; return (map[index] >> offset) & 0xFF; } /** * bitmap_set_value8 - set an 8-bit value within a memory region * @map: address to the bitmap memory region * @value: the 8-bit value; values wider than 8 bits may clobber bitmap * @start: bit offset of the 8-bit value; must be a multiple of 8 */ static inline void bitmap_set_value8(unsigned long *map, unsigned long value, unsigned long start) { const size_t index = BIT_WORD(start); const unsigned long offset = start % BITS_PER_LONG; map[index] &= ~(0xFFUL << offset); map[index] |= value << offset; } #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <linux/kernel.h> /* * Simple doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); list->prev = list; } #ifdef CONFIG_DEBUG_LIST extern bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next); extern bool __list_del_entry_valid(struct list_head *entry); #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); entry->prev = entry; smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return (next == head) && (next == head->prev); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && (head->next != entry && head != entry)) return; if (entry == head) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; pos != (head); pos = pos->next) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; pos != (head); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; pos != (head); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ pos != (head); \ pos = n, n = pos->prev) /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ (&pos->member == (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behing - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) #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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) static inline void * __must_check ERR_PTR(long error) { return (void *) error; } static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set. */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS ((slab_flags_t __force)0x00000100U) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC ((slab_flags_t __force)0x00040000U) /* * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * rcu_read_lock() * again: * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * goto again; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * goto again; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU ((slab_flags_t __force)0x00080000U) /* Spread some memory over cpuset */ #define SLAB_MEM_SPREAD ((slab_flags_t __force)0x00100000U) /* Trace allocations and frees */ #define SLAB_TRACE ((slab_flags_t __force)0x00200000U) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS ((slab_flags_t __force)0x00400000U) #else # define SLAB_DEBUG_OBJECTS 0 #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE ((slab_flags_t __force)0x00800000U) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB ((slab_flags_t __force)0x02000000U) #else # define SLAB_FAILSLAB 0 #endif /* Account to memcg */ #ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U) #else # define SLAB_ACCOUNT 0 #endif #ifdef CONFIG_KASAN #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 #endif /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab deactivation flag */ #define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct mem_cgroup; /* * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); bool slab_is_available(void); extern bool usercopy_fallback; struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ kmem_cache_create(#__struct, sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), NULL) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ kmem_cache_create_usercopy(#__struct, \ sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ sizeof_field(struct __struct, __field), NULL) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); #else static inline void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user) { } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) #else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN * aligned pointers. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ #ifdef CONFIG_SLAB /* * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * * WARNING: Its not easy to increase this value since the allocators have * to do various tricks to work around compiler limitations in order to * ensure proper constant folding. */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif #ifdef CONFIG_SLOB /* * SLOB passes all requests larger than one page to the page allocator. * No kmalloc array is necessary since objects of different sizes can * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif NR_KMALLOC_TYPES }; #ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { #ifdef CONFIG_ZONE_DMA /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for both flags. */ if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0)) return KMALLOC_NORMAL; /* * At least one of the flags has to be set. If both are, __GFP_DMA * is more important. */ return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM; #else return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL; #endif } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n */ static __always_inline unsigned int kmalloc_index(size_t size) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (size <= 4 * 1024 * 1024) return 22; if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; if (size <= 64 * 1024 * 1024) return 26; BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *, void *); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); /* * Caller must not use kfree_bulk() on memory not originally allocated * by kmalloc(), because the SLOB allocator cannot handle this. */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) { return kmem_cache_alloc(s, flags); } #endif #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_slab_alignment __malloc; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); ret = kasan_kmalloc(s, ret, size, flags); return ret; } static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } #endif static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); } /** * kmalloc - allocate memory * @size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * %GFP_HIGHUSER * Allocate memory from high memory on behalf of user. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB unsigned int index; #endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB index = kmalloc_index(size); if (!index) return ZERO_SIZE_PTR; return kmem_cache_alloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif } return __kmalloc(size, flags); } static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; return kmem_cache_alloc_node_trace( kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif return __kmalloc_node(size, flags, node); } /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc(bytes, flags); return __kmalloc(bytes, flags); } /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node(bytes, flags, node); return __kmalloc_node(bytes, flags, node); } static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) #else /* CONFIG_NUMA */ #define kmalloc_node_track_caller(size, flags, node) \ kmalloc_track_caller(size, flags) #endif /* CONFIG_NUMA */ /* * Shortcuts */ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) { return kmem_cache_alloc(k, flags | __GFP_ZERO); } /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } /** * kzalloc_node - allocate zeroed memory from a particular memory node. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); #if defined(CONFIG_SMP) && defined(CONFIG_SLAB) int slab_prepare_cpu(unsigned int cpu); int slab_dead_cpu(unsigned int cpu); #else #define slab_prepare_cpu NULL #define slab_dead_cpu NULL #endif #endif /* _LINUX_SLAB_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/mmdebug.h> #include <linux/mmzone.h> #include <linux/stddef.h> #include <linux/linkage.h> #include <linux/topology.h> struct vm_area_struct; /* * In case of changes, please don't forget to update * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c */ /* Plain integer GFP bitmasks. Do not use this directly. */ #define ___GFP_DMA 0x01u #define ___GFP_HIGHMEM 0x02u #define ___GFP_DMA32 0x04u #define ___GFP_MOVABLE 0x08u #define ___GFP_RECLAIMABLE 0x10u #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u #define ___GFP_ZERO 0x100u #define ___GFP_ATOMIC 0x200u #define ___GFP_DIRECT_RECLAIM 0x400u #define ___GFP_KSWAPD_RECLAIM 0x800u #define ___GFP_WRITE 0x1000u #define ___GFP_NOWARN 0x2000u #define ___GFP_RETRY_MAYFAIL 0x4000u #define ___GFP_NOFAIL 0x8000u #define ___GFP_NORETRY 0x10000u #define ___GFP_MEMALLOC 0x20000u #define ___GFP_COMP 0x40000u #define ___GFP_NOMEMALLOC 0x80000u #define ___GFP_HARDWALL 0x100000u #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #ifdef CONFIG_LOCKDEP #define ___GFP_NOLOCKDEP 0x800000u #else #define ___GFP_NOLOCKDEP 0 #endif /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) * * Do not put any conditional on these. If necessary modify the definitions * without the underscores and use them consistently. The definitions here may * be used in bit comparisons. */ #define __GFP_DMA ((__force gfp_t)___GFP_DMA) #define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) #define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) /** * DOC: Page mobility and placement hints * * Page mobility and placement hints * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due * to external fragmentation. * * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be * moved by page migration during memory compaction or can be reclaimed. * * %__GFP_RECLAIMABLE is used for slab allocations that specify * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. * * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, * these pages will be spread between local zones to avoid all the dirty * pages being in one zone (fair zone allocation policy). * * %__GFP_HARDWALL enforces the cpuset memory allocation policy. * * %__GFP_THISNODE forces the allocation to be satisfied from the requested * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) /** * DOC: Watermark modifiers * * Watermark modifiers -- controls access to emergency reserves * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. * For example, creating an IO context to clean pages. * * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is * high priority. Users are typically interrupt handlers. This may be * used in conjunction with %__GFP_HIGH * * %__GFP_MEMALLOC allows access to all memory. This should only be used when * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). * Users of this flag have to be extremely careful to not deplete the reserve * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. * Usage of a pre-allocated pool (e.g. mempool) should be always considered * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. */ #define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /** * DOC: Reclaim modifiers * * Reclaim modifiers * ~~~~~~~~~~~~~~~~~ * Please note that all the following flags are only applicable to sleepable * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). * * %__GFP_IO can start physical IO. * * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the * allocator recursing into the filesystem which might already be holding * locks. * * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. * This flag can be cleared to avoid unnecessary delays when a fallback * option is available. * * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when * the low watermark is reached and have it reclaim pages until the high * watermark is reached. A caller may wish to clear this flag when fallback * options are available and the reclaim is likely to disrupt the system. The * canonical example is THP allocation where a fallback is cheap but * reclaim/compaction may cause indirect stalls. * * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * * The default allocator behavior depends on the request size. We have a concept * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). * !costly allocations are too essential to fail so they are implicitly * non-failing by default (with some exceptions like OOM victims might fail so * the caller still has to check for failures) while costly requests try to be * not disruptive and back off even without invoking the OOM killer. * The following three modifiers might be used to override some of these * implicit rules * * %__GFP_NORETRY: The VM implementation will try only very lightweight * memory direct reclaim to get some memory under memory pressure (thus * it can sleep). It will avoid disruptive actions like OOM killer. The * caller must handle the failure which is quite likely to happen under * heavy memory pressure. The flag is suitable when failure can easily be * handled at small cost, such as reduced throughput * * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim * procedures that have previously failed if there is some indication * that progress has been made else where. It can wait for other * tasks to attempt high level approaches to freeing memory such as * compaction (which removes fragmentation) and page-out. * There is still a definite limit to the number of retries, but it is * a larger limit than with %__GFP_NORETRY. * Allocations with this flag may fail, but only when there is * genuinely little unused memory. While these allocations do not * directly trigger the OOM killer, their failure indicates that * the system is likely to need to use the OOM killer soon. The * caller must handle failure, but can reasonably do so by failing * a higher-level request, or completing it only in a much less * efficient manner. * If the allocation does fail, and the caller is in a position to * free some non-essential memory, doing so could benefit the system * as a whole. * * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller * cannot handle allocation failures. The allocation could block * indefinitely but will never return with failure. Testing for * failure is pointless. * New users should be evaluated carefully (and the flag should be * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless * loop around allocator. * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) #define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /** * DOC: Action modifiers * * Action modifiers * ~~~~~~~~~~~~~~~~ * * %__GFP_NOWARN suppresses allocation failure reports. * * %__GFP_COMP address compound page metadata. * * %__GFP_ZERO returns a zeroed page on success. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ #define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** * DOC: Useful GFP flag combinations * * Useful GFP flag combinations * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear * %__GFP_FOO flags as necessary. * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower * watermark is applied to allow access to "atomic reserves". * The current implementation doesn't support NMI and few other strict * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. * * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is * accounted to kmemcg. * * %GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. * Please try to avoid using this flag directly and instead use * memalloc_noio_{save,restore} to mark the whole scope which cannot * perform any IO with a short explanation why. All allocation requests * will inherit GFP_NOIO implicitly. * * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. * Please try to avoid using this flag directly and instead use * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't * recurse into the FS layer with a short explanation why. All allocation * requests will inherit GFP_NOFS implicitly. * * %GFP_USER is for userspace allocations that also need to be directly * accessibly by the kernel or hardware. It is typically used by hardware * for buffers that are mapped to userspace (e.g. graphics) that hardware * still must DMA to. cpuset limits are enforced for these allocations. * * %GFP_DMA exists for historical reasons and should be avoided where possible. * The flags indicates that the caller requires that the lowest zone be * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but * it would require careful auditing as some users really require it and * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit * address. * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot * move once in use. An example may be a hardware allocation that maps * data directly into userspace but has no addressing limitations. * * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not * need direct access to but can use kmap() when access is required. They * are expected to be movable via page reclaim or page migration. Typically, * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. * * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They * are compound allocations that will generally fail quickly if memory is not * available and will not wake kswapd/kcompactd on failure. The _LIGHT * version does not attempt reclaim/compaction at all and is by default used * in page fault path, while the non-light is used by khugepaged. */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } /** * gfpflags_normal_context - is gfp_flags a normal sleepable context? * @gfp_flags: gfp_flags to test * * Test whether @gfp_flags indicates that the allocation is from the * %current context and allowed to sleep. * * An allocation being allowed to block doesn't mean it owns the %current * context. When direct reclaim path tries to allocate memory, the * allocation context is nested inside whatever %current was doing at the * time of the original allocation. The nested allocation may be allowed * to block but modifying anything %current owns can corrupt the outer * context's expectations. * * %true result from this function indicates that the allocation context * can sleep and use anything that's associated with %current. */ static inline bool gfpflags_normal_context(const gfp_t gfp_flags) { return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == __GFP_DIRECT_RECLAIM; } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets * optimized to &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { return 0; } #endif struct page * __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, nodemask_t *nodemask); static inline struct page * __alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) { return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); return __alloc_pages(gfp_mask, order, nid); } /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node(nid, gfp_mask, order); } #ifdef CONFIG_NUMA extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); static inline struct page * alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_current(gfp_mask, order); } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); extern void free_unref_page(struct page *page); extern void free_unref_page_list(struct list_head *list); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); extern void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask); extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else static inline bool pm_suspended_storage(void) { return false; } #endif /* CONFIG_PM_SLEEP */ /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif void free_contig_range(unsigned long pfn, unsigned int nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ extern void init_cma_reserved_pageblock(struct page *page); #endif #endif /* __LINUX_GFP_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 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #endif /* _LINUX_TOPOLOGY_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Tracing hooks * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This file defines hook entry points called by core code where * user tracing/debugging support might need to do something. These * entry points are called tracehook_*(). Each hook declared below * has a detailed kerneldoc comment giving the context (locking et * al) from which it is called, and the meaning of its return value. * * Each function here typically has only one call site, so it is ok * to have some nontrivial tracehook_*() inlines. In all cases, the * fast path when no tracing is enabled should be very short. * * The purpose of this file and the tracehook_* layer is to consolidate * the interface that the kernel core and arch code uses to enable any * user debugging or tracing facility (such as ptrace). The interfaces * here are carefully documented so that maintainers of core and arch * code do not need to think about the implementation details of the * tracing facilities. Likewise, maintainers of the tracing code do not * need to understand all the calling core or arch code in detail, just * documented circumstances of each call, such as locking conditions. * * If the calling core code changes so that locking is different, then * it is ok to change the interface documented here. The maintainer of * core code changing should notify the maintainers of the tracing code * that they need to work out the change. * * Some tracehook_*() inlines take arguments that the current tracing * implementations might not necessarily use. These function signatures * are chosen to pass in all the information that is on hand in the * caller and might conceivably be relevant to a tracer, so that the * core code won't have to be updated when tracing adds more features. * If a call site changes so that some of those parameters are no longer * already on hand without extra work, then the tracehook_* interface * can change so there is no make-work burden on the core code. The * maintainer of core code changing should notify the maintainers of the * tracing code that they need to work out the change. */ #ifndef _LINUX_TRACEHOOK_H #define _LINUX_TRACEHOOK_H 1 #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/blk-cgroup.h> struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(struct pt_regs *regs, unsigned long message) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; current->ptrace_message = message; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (current->exit_code) { send_sig(current->exit_code, current, 1); current->exit_code = 0; } current->ptrace_message = 0; return fatal_signal_pending(current); } /** * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * tracehook_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %TIF_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); } /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use * * Called by the arch code after a signal handler has been set up. * Register and stack state reflects the user handler about to run. * Signal mask changes have already been made. * * Called without locks, shortly before returning to user mode * (or handling more signals). */ static inline void tracehook_signal_handler(int stepping) { if (stepping) ptrace_notify(SIGTRAP); } /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() * * Calling this arranges that @task will call tracehook_notify_resume() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call tracehook_notify_resume() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { #ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); #endif } /** * tracehook_notify_resume - report when about to return to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void tracehook_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); } /* * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This * is currently used by TWA_SIGNAL based task_work, which requires breaking * wait loops to ensure that task_work is noticed and run. */ static inline void tracehook_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); if (current->task_works) task_work_run(); } /* * Called when we have work to process from exit_to_user_mode_loop() */ static inline void set_notify_signal(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE)) kick_process(task); } #endif /* <linux/tracehook.h> */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_FORCE_MAX_ZONEORDER #define MAX_ORDER 11 #else #define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. What is important though * is that a range of pageblocks must be aligned to * MAX_ORDER_NR_PAGES should biggest page be bigger then * a single pageblock. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; static inline struct page *get_page_from_free_area(struct free_area *area, int migratetype) { return list_first_entry_or_null(&area->free_list[migratetype], struct page, lru); } static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } struct pglist_data; /* * zone->lock and the zone lru_lock are two of the hottest locks in the kernel. * So add a wild amount of padding here to ensure that they fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ #if defined(CONFIG_SMP) struct zone_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define ZONE_PADDING(name) struct zone_padding name; #else #define ZONE_PADDING(name) #endif #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_STAT_ITEMS }; #else #define NR_VM_NUMA_STAT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define ANON_AND_FILE 2 enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI */ }; struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif }; /* Isolate unmapped pages */ #define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, NR_WMARK }; #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[MIGRATE_PCPTYPES]; }; struct per_cpu_pageset { struct per_cpu_pages pcp; #ifdef CONFIG_NUMA s8 expire; u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif #ifdef CONFIG_SMP s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Memory offlining might * retry a long time. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NEED_MULTIPLE_NODES int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/end(). Any reader who can't tolerant drift of * present_pages should get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ ZONE_PADDING(_pad1_) /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ ZONE_PADDING(_pad2_) /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; #ifndef CONFIG_DISCONTIGMEM /* The array of struct pages - for discontigmem use pgdat->lmem_map */ extern struct page *mem_map; #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ ZONE_PADDING(_pad1_) spinlock_t lru_lock; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; ZONE_PADDING(_pad2_) /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #ifdef CONFIG_FLAT_NODE_MEM_MAP #define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) #else #define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } static inline bool pgdat_is_empty(pg_data_t *pgdat) { return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NEED_MULTIPLE_NODES static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; #ifdef CONFIG_HIGHMEM static inline int zone_movable_is_highmem(void) { #ifdef CONFIG_NEED_MULTIPLE_NODES return movable_zone == ZONE_HIGHMEM; #else return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; #endif } #endif static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && zone_movable_is_highmem())); #else return 0; #endif } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable */ static inline int is_highmem(struct zone *zone) { #ifdef CONFIG_HIGHMEM return is_highmem_idx(zone_idx(zone)); #else return 0; #endif } /* These two functions are used to setup the per zone pages min values */ struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NEED_MULTIPLE_NODES extern struct pglist_data contig_page_data; #define NODE_DATA(nid) (&contig_page_data) #define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NEED_MULTIPLE_NODES */ #include <asm/mmzone.h> #endif /* !CONFIG_NEED_MULTIPLE_NODES */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat - pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone - pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z - The cursor used as a starting point for the search * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone - The current zone in the iterator * @z - The current pointer within zonelist->_zonerefs being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * @nodemask - Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone - The current zone in the iterator * @z - The current pointer within zonelist->zones being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * SECTION_SHIFT #bits space required to store a section # * * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern unsigned long __section_nr(struct mem_section *ms); extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available. */ #define SECTION_MARKED_PRESENT (1UL<<0) #define SECTION_HAS_MEM_MAP (1UL<<1) #define SECTION_IS_ONLINE (1UL<<2) #define SECTION_IS_EARLY (1UL<<3) #define SECTION_MAP_LAST_BIT (1UL<<4) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) #define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock(); if (!valid_section(ms)) { rcu_read_unlock(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ /* * During memory init memblocks map pfns to nids. The search is expensive and * this caches recent lookups. The implementation of __early_pfn_to_nid * may treat start/end as pfns or sections. */ struct mminit_pfnnid_cache { unsigned long last_start; unsigned long last_end; int last_nid; }; /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we * need to check pfn validity within that MAX_ORDER_NR_PAGES block. * pfn_valid_within() should be used in this case; we optimise this away * when we have no holes within a MAX_ORDER_NR_PAGES block. */ #ifdef CONFIG_HOLES_IN_ZONE #define pfn_valid_within(pfn) pfn_valid(pfn) #else #define pfn_valid_within(pfn) (1) #endif #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support four policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_PREFERRED, .flags = MPOL_F_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /** * numa_map_to_online_node - Find closest online node * @node: Node id to start the search * * Lookup the next closest node by distance if @nid is not online. */ int numa_map_to_online_node(int node) { int min_dist = INT_MAX, dist, n, min_node; if (node == NUMA_NO_NODE || node_online(node)) return node; min_node = node; for_each_online_node(n) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_map_to_online_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (!nodes) pol->flags |= MPOL_F_LOCAL; /* local allocation */ else if (nodes_empty(*nodes)) return -EINVAL; /* no allowed nodes */ else pol->v.preferred_node = first_node(*nodes); return 0; } static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. But, we need to * handle an empty nodemask with MPOL_PREFERRED here. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ if (pol == NULL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) nodes = NULL; /* explicit local allocation */ else { if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; } if (nodes) ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); else ret = mpol_ops[pol->mode].create(pol, NULL); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; pr_debug("setting mode %d flags %d nodes[0] %lx\n", mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); mode = MPOL_PREFERRED; } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *p) { if (!atomic_dec_and_test(&p->refcnt)) return; kmem_cache_free(policy_cache, p); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->v.nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) { int node = first_node(pol->w.user_nodemask); if (node_isset(node, *nodes)) { pol->v.preferred_node = node; pol->flags &= ~MPOL_F_LOCAL; } else pol->flags |= MPOL_F_LOCAL; } else if (pol->flags & MPOL_F_RELATIVE_NODES) { mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); pol->v.preferred_node = first_node(tmp); } else if (!(pol->flags & MPOL_F_LOCAL)) { pol->v.preferred_node = node_remap(pol->v.preferred_node, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; mmap_write_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) mpol_rebind_policy(vma->vm_policy, new); mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_interleave, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; }; /* * Check if the page's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_pages_required(struct page *page, struct queue_pages *qp) { int nid = page_to_nid(page); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } /* * queue_pages_pmd() has four possible return values: * 0 - pages are placed on the right node or queued successfully. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing page was already on a node that does not follow the * policy. */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) __releases(ptl) { int ret = 0; struct page *page; struct queue_pages *qp = walk->private; unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) { ret = -EIO; goto unlock; } page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); __split_huge_pmd(walk->vma, pmd, addr, false, NULL); ret = 2; goto out; } if (!queue_pages_required(page, qp)) goto unlock; flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_page_add(page, qp->pagelist, flags)) { ret = 1; goto unlock; } } else ret = -EIO; unlock: spin_unlock(ptl); out: return ret; } /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: * 0 - pages are placed on the right node or queued successfully. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already * on a node that does not follow the policy. */ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct page *page; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; int ret; bool has_unmovable = false; pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); if (ret != 2) return ret; } /* THP was split, fall through to pte walk */ if (pmd_trans_unstable(pmd)) return 0; mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); if (!page) continue; /* * vm_normal_page() filters out zero pages, but there might * still be PageReserved pages to skip, perhaps in a VDSO. */ if (PageReserved(page)) continue; if (!queue_pages_required(page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { /* MPOL_MF_STRICT must be specified if we get here */ if (!vma_migratable(vma)) { has_unmovable = true; break; } /* * Do not abort immediately since there may be * temporary off LRU pages in the range. Still * need migrate other LRU pages. */ if (migrate_page_add(page, qp->pagelist, flags)) has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); if (has_unmovable) return 1; return addr != end ? -EIO : 0; } static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { int ret = 0; #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = (qp->flags & MPOL_MF_VALID); struct page *page; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(pte); if (!pte_present(entry)) goto unlock; page = pte_page(entry); if (!queue_pages_required(page, qp)) goto unlock; if (flags == MPOL_MF_STRICT) { /* * STRICT alone means only detecting misplaced page and no * need to further check other vma. */ ret = -EIO; goto unlock; } if (!vma_migratable(walk->vma)) { /* * Must be STRICT with MOVE*, otherwise .test_walk() have * stopped walking current vma. * Detecting misplaced page but allow migrating pages which * have been queued. */ ret = 1; goto unlock; } /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate page but allow migrating pages * which have been queued. */ ret = 1; } unlock: spin_unlock(ptl); #else BUG(); #endif return ret; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { int nr_updated; nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); return nr_updated; } #else static unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA((vma->vm_start > start) || (vma->vm_end < end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!vma->vm_next || vma->vm_end < vma->vm_next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; if (endvma > end) endvma = end; if (flags & MPOL_MF_LAZY) { /* Similar to task_numa_work, skip inaccessible VMAs */ if (!is_vm_hugetlb_page(vma) && vma_is_accessible(vma) && !(vma->vm_flags & VM_MIXEDMAP)) change_prot_numa(vma, start, endvma); return 1; } /* queue pages from current vma */ if (flags & MPOL_MF_VALID) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_pages_hugetlb, .pmd_entry = queue_pages_pte_range, .test_walk = queue_pages_test_walk, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are on a set of nodes (determined by * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private. * * queue_pages_range() has three possible return values: * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or * memory range specified by nodemask and maxnode points outside * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n", vma->vm_start, vma->vm_end, vma->vm_pgoff, vma->vm_ops, vma->vm_file, vma->vm_ops ? vma->vm_ops->set_policy : NULL); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Step 2: apply policy to a range and do splits. */ static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct mempolicy *new_pol) { struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; pgoff_t pgoff; unsigned long vmstart; unsigned long vmend; vma = find_vma(mm, start); VM_BUG_ON(!vma); prev = vma->vm_prev; if (start > vma->vm_start) prev = vma; for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) { vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); if (mpol_equal(vma_policy(vma), new_pol)) continue; pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, new_pol, vma->vm_userfaultfd_ctx); if (prev) { vma = prev; goto replace; } if (vma->vm_start != vmstart) { err = split_vma(vma->vm_mm, vma, vmstart, 1); if (err) goto out; } if (vma->vm_end != vmend) { err = split_vma(vma->vm_mm, vma, vmend, 0); if (err) goto out; } replace: err = vma_replace_policy(vma, new_pol); if (err) goto out; } out: return err; } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { mpol_put(new); goto out; } task_lock(current); old = current->mempolicy; current->mempolicy = new; if (new && new->mode == MPOL_INTERLEAVE) current->il_prev = MAX_NUMNODES-1; task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) { nodes_clear(*nodes); if (p == &default_policy) return; switch (p->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: *nodes = p->v.nodes; break; case MPOL_PREFERRED: if (!(p->flags & MPOL_F_LOCAL)) node_set(p->v.preferred_node, *nodes); /* else return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int err; int locked = 1; err = get_user_pages_locked(addr & PAGE_MASK, 1, 0, &p, &locked); if (err > 0) { err = page_to_nid(p); put_page(p); } if (locked) mmap_read_unlock(mm); return err; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = find_vma_intersection(mm, addr, addr+1); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } if (vma->vm_ops && vma->vm_ops->get_policy) pol = vma->vm_ops->get_policy(vma, addr); else pol = vma->vm_policy; } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, lookup_node() * wil drop the mmap_lock, so after calling * lookup_node() only "pol" remains valid, "vma" * is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->v.nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION /* * page migration, thp tail pages can be passed. */ static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { struct page *head = compound_head(page); /* * Avoid migrating a page that is shared with others. */ if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) { if (!isolate_lru_page(head)) { list_add_tail(&head->lru, pagelist); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_lru(head), thp_nr_pages(head)); } else if (flags & MPOL_MF_STRICT) { /* * Non-movable page may reach here. And, there may be * temporary off LRU pages or non-LRU movable pages. * Treat them as unmovable pages since they can't be * isolated, so they can't be moved at the moment. It * should return -EIO for this case too. */ return -EIO; } } return 0; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, }; nodes_clear(nmask); node_set(source, nmask); /* * This does not "check" the range but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. */ VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); } return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { int busy = 0; int err; nodemask_t tmp; err = migrate_prep(); if (err) return err; mmap_read_lock(mm); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s,d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) busy += err; if (err < 0) break; } mmap_read_unlock(mm); if (err < 0) return err; return busy; } /* * Allocate a new page for page migration based on vma policy. * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ static struct page *new_page(struct page *page, unsigned long start) { struct vm_area_struct *vma; unsigned long address; vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) break; vma = vma->vm_next; } if (PageHuge(page)) { return alloc_huge_page_vma(page_hstate(compound_head(page)), vma, address); } else if (PageTransHuge(page)) { struct page *thp; thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, HPAGE_PMD_ORDER); if (!thp) return NULL; prep_transhuge_page(thp); return thp; } /* * if !vma, alloc_page_vma() will use task or system default policy */ return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, vma, address); } #else static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { return -EIO; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct page *new_page(struct page *page, unsigned long start) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; int err; int ret; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = (len + PAGE_SIZE - 1) & PAGE_MASK; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); if (flags & MPOL_MF_LAZY) new->flags |= MPOL_F_MOF; /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", start, start + len, mode, mode_flags, nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { err = migrate_prep(); if (err) goto mpol_out; } { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; ret = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { err = ret; goto up_out; } err = mbind_range(mm, start, end, new); if (!err) { int nr_failed = 0; if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_page, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; } else { up_out: if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); } mmap_write_unlock(mm); mpol_out: mpol_put(new); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long k; unsigned long t; unsigned long nlongs; unsigned long endmask; --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; nlongs = BITS_TO_LONGS(maxnode); if ((maxnode % BITS_PER_LONG) == 0) endmask = ~0UL; else endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; /* * When the user specified more nodes than supported just check * if the non supported part is all zero. * * If maxnode have more longs than MAX_NUMNODES, check * the bits in that area first. And then go through to * check the rest bits which equal or bigger than MAX_NUMNODES. * Otherwise, just check bits [MAX_NUMNODES, maxnode). */ if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { if (get_user(t, nmask + k)) return -EFAULT; if (k == nlongs - 1) { if (t & endmask) return -EINVAL; } else if (t) return -EINVAL; } nlongs = BITS_TO_LONGS(MAX_NUMNODES); endmask = ~0UL; } if (maxnode > MAX_NUMNODES && MAX_NUMNODES % BITS_PER_LONG != 0) { unsigned long valid_mask = endmask; valid_mask &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); if (get_user(t, nmask + nlongs - 1)) return -EFAULT; if (t & valid_mask) return -EINVAL; } if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long))) return -EFAULT; nodes_addr(*nodes)[nlongs-1] &= endmask; return 0; } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; } return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { nodemask_t nodes; int err; unsigned short mode_flags; start = untagged_addr(start); mode_flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if (mode >= MPOL_MAX) return -EINVAL; if ((mode_flags & MPOL_F_STATIC_NODES) && (mode_flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, mode, mode_flags, &nodes, flags); } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { int err; nodemask_t nodes; unsigned short flags; flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)mode >= MPOL_MAX) return -EINVAL; if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(mode, flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, addr, compat_ulong_t, flags) { long err; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) nm = compat_alloc_user_space(alloc_size); err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags); if (!err && nmask) { unsigned long copy_size; copy_size = min_t(unsigned long, sizeof(bm), alloc_size); err = copy_from_user(bm, nm, copy_size); /* ensure entire bitmap is zeroed */ err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); err |= compat_put_bitmap(nmask, bm, nr_bits); } return err; } COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { if (compat_get_bitmap(bm, nmask, nr_bits)) return -EFAULT; nm = compat_alloc_user_space(alloc_size); if (copy_to_user(nm, bm, alloc_size)) return -EFAULT; } return kernel_set_mempolicy(mode, nm, nr_bits+1); } COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) return -EFAULT; nm = compat_alloc_user_space(alloc_size); if (copy_to_user(nm, nodes_addr(bm), alloc_size)) return -EFAULT; } return kernel_mbind(start, len, mode, nm, nr_bits+1, flags); } COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, compat_ulong_t, maxnode, const compat_ulong_t __user *, old_nodes, const compat_ulong_t __user *, new_nodes) { unsigned long __user *old = NULL; unsigned long __user *new = NULL; nodemask_t tmp_mask; unsigned long nr_bits; unsigned long size; nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES); size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (old_nodes) { if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits)) return -EFAULT; old = compat_alloc_user_space(new_nodes ? size * 2 : size); if (new_nodes) new = old + size / sizeof(unsigned long); if (copy_to_user(old, nodes_addr(tmp_mask), size)) return -EFAULT; } if (new_nodes) { if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits)) return -EFAULT; if (new == NULL) new = compat_alloc_user_space(size); if (copy_to_user(new, nodes_addr(tmp_mask), size)) return -EFAULT; } return kernel_migrate_pages(pid, nr_bits + 1, old, new); } #endif /* CONFIG_COMPAT */ bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = NULL; if (vma) { if (vma->vm_ops && vma->vm_ops->get_policy) { pol = vma->vm_ops->get_policy(vma, addr); } else if (vma->vm_policy) { pol = vma->vm_policy; /* * shmem_alloc_page() passes MPOL_F_SHARED policy with * a pseudo vma whose vma->vm_ops=NULL. Take a reference * count on these policies which will be dropped by * mpol_cond_put() later */ if (mpol_needs_cond_ref(pol)) mpol_get(pol); } } return pol; } /* * get_vma_policy(@vma, @addr) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); if (!pol) pol = get_task_policy(current); return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pol = vma->vm_ops->get_policy(vma, vma->vm_start); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->v.nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->v.nodes is intersect with node_states[N_MEMORY]. * so if the following test faile, it implies * policy->v.nodes has movable memory only. */ if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation */ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) { /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && apply_policy_zone(policy, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) return &policy->v.nodes; return NULL; } /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) nd = policy->v.preferred_node; else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); } return nd; } /* Do dynamic interleaving for a process */ static unsigned interleave_nodes(struct mempolicy *policy) { unsigned next; struct task_struct *me = current; next = next_node_in(me->il_prev, policy->v.nodes); if (next < MAX_NUMNODES) me->il_prev = next; return next; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (in_interrupt()) return node; policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) return node; switch (policy->mode) { case MPOL_PREFERRED: /* * handled MPOL_F_LOCAL above */ return policy->v.preferred_node; case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_BIND: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes); return z->zone ? zone_to_nid(z->zone) : node; } default: BUG(); } } /* * Do static interleaving for a VMA with known offset @n. Returns the n'th * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the * number of present nodes. */ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) { unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; int i; int nid; if (!nnodes) return numa_node_id(); target = (unsigned int)n % nnodes; nid = first_node(pol->v.nodes); for (i = 0; i < target; i++) nid = next_node(nid, pol->v.nodes); return nid; } /* Determine a node number for interleave */ static inline unsigned interleave_nid(struct mempolicy *pol, struct vm_area_struct *vma, unsigned long addr, int shift) { if (vma) { unsigned long off; /* * for small pages, there is no difference between * shift and PAGE_SHIFT, so the bit-shift is safe. * for huge pages, since vm_pgoff is in units of small * pages, we need to shift off the always 0 bits to get * a useful offset. */ BUG_ON(shift < PAGE_SHIFT); off = vma->vm_pgoff >> (shift - PAGE_SHIFT); off += (addr - vma->vm_start) >> shift; return offset_il_node(pol, off); } else return interleave_nodes(pol); } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * * Must be protected by read_mems_allowed_begin() */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { int nid; *mpol = get_vma_policy(vma, addr); *nodemask = NULL; /* assume !MPOL_BIND */ if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { nid = interleave_nid(*mpol, vma, addr, huge_page_shift(hstate_vma(vma))); } else { nid = policy_node(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) *nodemask = &(*mpol)->v.nodes; } return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; int nid; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: if (mempolicy->flags & MPOL_F_LOCAL) nid = numa_node_id(); else nid = mempolicy->v.preferred_node; init_nodemask_of_node(mask, nid); break; case MPOL_BIND: case MPOL_INTERLEAVE: *mask = mempolicy->v.nodes; break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_nodemask_intersects * * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default * policy. Otherwise, check for intersection between mask and the policy * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' * policy, always return true since it may allocate elsewhere on fallback. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_nodemask_intersects(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (!mempolicy) goto out; switch (mempolicy->mode) { case MPOL_PREFERRED: /* * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to * allocate from, they may fallback to other nodes when oom. * Thus, it's possible for tsk to have allocated memory from * nodes in mask. */ break; case MPOL_BIND: case MPOL_INTERLEAVE: ret = nodes_intersects(mempolicy->v.nodes, *mask); break; default: BUG(); } out: task_unlock(tsk); return ret; } /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, unsigned nid) { struct page *page; page = __alloc_pages(gfp, order, nid); /* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */ if (!static_branch_likely(&vm_numa_stat_key)) return page; if (page && page_to_nid(page) == nid) { preempt_disable(); __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } return page; } /** * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. * %GFP_KERNEL kernel allocations, * %GFP_HIGHMEM highmem/user allocations, * %GFP_FS allocation should not call back into a file system. * %GFP_ATOMIC don't sleep. * * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. * When VMA is not NULL caller must read-lock the mmap_lock of the * mm_struct of the VMA to prevent it from going away. Should be used for * all allocations for pages that will be mapped into user space. Returns * NULL when no page can be allocated. */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; int preferred_nid; nodemask_t *nmask; pol = get_vma_policy(vma, addr); if (pol->mode == MPOL_INTERLEAVE) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); goto out; } if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { int hpage_node = node; /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) hpage_node = pol->v.preferred_node; nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node(hpage_node, gfp | __GFP_THISNODE | __GFP_NORETRY, order); /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ if (!page && (gfp & __GFP_DIRECT_RECLAIM)) page = __alloc_pages_nodemask(gfp, order, hpage_node, nmask); goto out; } } nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); mpol_cond_put(pol); out: return page; } EXPORT_SYMBOL(alloc_pages_vma); /** * alloc_pages_current - Allocate pages. * * @gfp: * %GFP_USER user allocation, * %GFP_KERNEL kernel allocation, * %GFP_HIGHMEM highmem allocation, * %GFP_FS don't call back into a file system. * %GFP_ATOMIC don't sleep. * @order: Power of two of allocation size in pages. 0 is a single page. * * Allocate a page from the kernel page pool. When not in * interrupt context and apply the current process NUMA policy. * Returns NULL when no page can be allocated. */ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; struct page *page; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (pol->mode == MPOL_INTERLEAVE) page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, policy_node(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); return page; } EXPORT_SYMBOL(alloc_pages_current); int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: /* a's ->flags is the same as b's */ if (a->flags & MPOL_F_LOCAL) return true; return a->v.preferred_node == b->v.preferred_node; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node * sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); pr_debug("inserting %lx-%lx: %d\n", new->start, new->end, new->policy ? new->policy->mode : 0); } /* Find shared policy intersecting idx */ struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current page node is valid in policy * * @page: page to be checked * @vma: vm area where page mapped * @addr: virtual address where page mapped * * Lookup current policy node id for vma,addr and "compare to" page's * node id. * * Returns: * -1 - not misplaced, page is in the right node * node - node id where the page should be * * Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. */ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; struct zoneref *z; int curnid = page_to_nid(page); unsigned long pgoff; int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); int polnid = NUMA_NO_NODE; int ret = -1; pol = get_vma_policy(vma, addr); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: pgoff = vma->vm_pgoff; pgoff += (addr - vma->vm_start) >> PAGE_SHIFT; polnid = offset_il_node(pol, pgoff); break; case MPOL_PREFERRED: if (pol->flags & MPOL_F_LOCAL) polnid = numa_node_id(); else polnid = pol->v.preferred_node; break; case MPOL_BIND: /* * allows binding to multiple nodes. * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->v.nodes)) goto out; z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->v.nodes); polnid = zone_to_nid(z->zone); break; default: BUG(); } /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, unsigned long start, unsigned long end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct vm_area_struct pvma; struct mempolicy *new; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy */ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(new)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_new; /* Create pseudo-vma that contains just the policy */ vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ put_new: mpol_put(new); /* drop initial ref */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *npol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n", vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); if (!new) return -ENOMEM; } err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *p) { struct sp_node *n; struct rb_node *next; if (!p->root.rb_node) return; write_lock(&p->lock); next = rb_first(&p->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(p, n); } write_unlock(&p->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ /* assumes fs == KERNEL_DS */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .v = { .preferred_node = nid, }, }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ /* * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_LOCAL] = "local", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * On success, returns 0, else 1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) new->v.nodes = nodes; else if (nodelist) new->v.preferred_node = first_node(nodes); else new->flags |= MPOL_F_LOCAL; /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the * longest flag, "relative", and to display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: break; case MPOL_PREFERRED: if (flags & MPOL_F_LOCAL) mode = MPOL_LOCAL; else node_set(pol->v.preferred_node, nodes); break; case MPOL_BIND: case MPOL_INTERLEAVE: nodes = pol->v.nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Currently, the only defined flags are mutually exclusive */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Kernel Probes (KProbes) * kernel/kprobes.c * * Copyright (C) IBM Corporation, 2002, 2004 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation (includes suggestions from * Rusty Russell). * 2004-Aug Updated by Prasanna S Panchamukhi <prasanna@in.ibm.com> with * hlists and exceptions notifier as suggested by Andi Kleen. * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes * interface to access function arguments. * 2004-Sep Prasanna S Panchamukhi <prasanna@in.ibm.com> Changed Kprobes * exceptions notifier to be first on the priority list. * 2005-May Hien Nguyen <hien@us.ibm.com>, Jim Keniston * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ #include <linux/kprobes.h> #include <linux/hash.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/export.h> #include <linux/moduleloader.h> #include <linux/kallsyms.h> #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/sysctl.h> #include <linux/kdebug.h> #include <linux/memory.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/jump_label.h> #include <linux/perf_event.h> #include <linux/static_call.h> #include <asm/sections.h> #include <asm/cacheflush.h> #include <asm/errno.h> #include <linux/uaccess.h> #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) static int kprobes_initialized; /* kprobe_table can be accessed by * - Normal hlist traversal and RCU add/del under kprobe_mutex is held. * Or * - RCU hlist traversal under disabling preempt (breakpoint handlers) */ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; /* NOTE: change this value only with kprobe_mutex held */ static bool kprobes_all_disarmed; /* This protects kprobe_table and optimizing_list */ static DEFINE_MUTEX(kprobe_mutex); static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { raw_spinlock_t lock ____cacheline_aligned_in_smp; } kretprobe_table_locks[KPROBE_TABLE_SIZE]; kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, unsigned int __unused) { return ((kprobe_opcode_t *)(kallsyms_lookup_name(name))); } static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) { return &(kretprobe_table_locks[hash].lock); } /* Blacklist -- list of struct kprobe_blacklist_entry */ static LIST_HEAD(kprobe_blacklist); #ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* * kprobe->ainsn.insn points to the copy of the instruction to be * single-stepped. x86_64, POWER4 and above have no-exec support and * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster */ struct kprobe_insn_page { struct list_head list; kprobe_opcode_t *insns; /* Page of instruction slots */ struct kprobe_insn_cache *cache; int nused; int ngarbage; char slot_used[]; }; #define KPROBE_INSN_PAGE_SIZE(slots) \ (offsetof(struct kprobe_insn_page, slot_used) + \ (sizeof(char) * (slots))) static int slots_per_page(struct kprobe_insn_cache *c) { return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t)); } enum kprobe_slot_state { SLOT_CLEAN = 0, SLOT_DIRTY = 1, SLOT_USED = 2, }; void __weak *alloc_insn_page(void) { return module_alloc(PAGE_SIZE); } void __weak free_insn_page(void *page) { module_memfree(page); } struct kprobe_insn_cache kprobe_insn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, .sym = KPROBE_INSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), .insn_size = MAX_INSN_SIZE, .nr_garbage = 0, }; static int collect_garbage_slots(struct kprobe_insn_cache *c); /** * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; kprobe_opcode_t *slot = NULL; /* Since the slot array is not protected by rcu, we need a mutex */ mutex_lock(&c->mutex); retry: rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if (kip->nused < slots_per_page(c)) { int i; for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; kip->nused++; slot = kip->insns + (i * c->insn_size); rcu_read_unlock(); goto out; } } /* kip->nused is broken. Fix it. */ kip->nused = slots_per_page(c); WARN_ON(1); } } rcu_read_unlock(); /* If there are any garbage slots, collect it and try again. */ if (c->nr_garbage && collect_garbage_slots(c) == 0) goto retry; /* All out of space. Need to allocate a new page. */ kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL); if (!kip) goto out; /* * Use module_alloc so this page is within +/- 2GB of where the * kernel image and loaded module images reside. This is required * so x86_64 can correctly handle the %rip-relative fixups. */ kip->insns = c->alloc(); if (!kip->insns) { kfree(kip); goto out; } INIT_LIST_HEAD(&kip->list); memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); kip->slot_used[0] = SLOT_USED; kip->nused = 1; kip->ngarbage = 0; kip->cache = c; list_add_rcu(&kip->list, &c->pages); slot = kip->insns; /* Record the perf ksymbol register event after adding the page */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, false, c->sym); out: mutex_unlock(&c->mutex); return slot; } /* Return 1 if all garbages are collected, otherwise 0. */ static int collect_one_slot(struct kprobe_insn_page *kip, int idx) { kip->slot_used[idx] = SLOT_CLEAN; kip->nused--; if (kip->nused == 0) { /* * Page is no longer in use. Free it unless * it's the last one. We keep the last one * so as not to have to set it up again the * next time somebody inserts a probe. */ if (!list_is_singular(&kip->list)) { /* * Record perf ksymbol unregister event before removing * the page. */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, true, kip->cache->sym); list_del_rcu(&kip->list); synchronize_rcu(); kip->cache->free(kip->insns); kfree(kip); } return 1; } return 0; } static int collect_garbage_slots(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip, *next; /* Ensure no-one is interrupted on the garbages */ synchronize_rcu(); list_for_each_entry_safe(kip, next, &c->pages, list) { int i; if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i)) break; } } c->nr_garbage = 0; return 0; } void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; long idx; mutex_lock(&c->mutex); rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { idx = ((long)slot - (long)kip->insns) / (c->insn_size * sizeof(kprobe_opcode_t)); if (idx >= 0 && idx < slots_per_page(c)) goto out; } /* Could not find this slot. */ WARN_ON(1); kip = NULL; out: rcu_read_unlock(); /* Mark and sweep: this may sleep */ if (kip) { /* Check double free */ WARN_ON(kip->slot_used[idx] != SLOT_USED); if (dirty) { kip->slot_used[idx] = SLOT_DIRTY; kip->ngarbage++; if (++c->nr_garbage > slots_per_page(c)) collect_garbage_slots(c); } else { collect_one_slot(kip, idx); } } mutex_unlock(&c->mutex); } /* * Check given address is on the page of kprobe instruction slots. * This will be used for checking whether the address on a stack * is on a text area or not. */ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr) { struct kprobe_insn_page *kip; bool ret = false; rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if (addr >= (unsigned long)kip->insns && addr < (unsigned long)kip->insns + PAGE_SIZE) { ret = true; break; } } rcu_read_unlock(); return ret; } int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, unsigned long *value, char *type, char *sym) { struct kprobe_insn_page *kip; int ret = -ERANGE; rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if ((*symnum)--) continue; strlcpy(sym, c->sym, KSYM_NAME_LEN); *type = 't'; *value = (unsigned long)kip->insns; ret = 0; break; } rcu_read_unlock(); return ret; } #ifdef CONFIG_OPTPROBES /* For optimized_kprobe buffer */ struct kprobe_insn_cache kprobe_optinsn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, .sym = KPROBE_OPTINSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), /* .insn_size is initialized later */ .nr_garbage = 0, }; #endif #endif /* We have preemption disabled.. so it is safe to use __ versions */ static inline void set_kprobe_instance(struct kprobe *kp) { __this_cpu_write(kprobe_instance, kp); } static inline void reset_kprobe_instance(void) { __this_cpu_write(kprobe_instance, NULL); } /* * This routine is called either: * - under the kprobe_mutex - during kprobe_[un]register() * OR * - with preemption disabled - from arch/xxx/kernel/kprobes.c */ struct kprobe *get_kprobe(void *addr) { struct hlist_head *head; struct kprobe *p; head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; hlist_for_each_entry_rcu(p, head, hlist, lockdep_is_held(&kprobe_mutex)) { if (p->addr == addr) return p; } return NULL; } NOKPROBE_SYMBOL(get_kprobe); static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); /* Return true if the kprobe is an aggregator */ static inline int kprobe_aggrprobe(struct kprobe *p) { return p->pre_handler == aggr_pre_handler; } /* Return true(!0) if the kprobe is unused */ static inline int kprobe_unused(struct kprobe *p) { return kprobe_aggrprobe(p) && kprobe_disabled(p) && list_empty(&p->list); } /* * Keep all fields in the kprobe consistent */ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) { memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t)); memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn)); } #ifdef CONFIG_OPTPROBES /* NOTE: change this value only with kprobe_mutex held */ static bool kprobes_allow_optimization; /* * Call all pre_handler on the list, but ignores its return value. * This must be called from arch-dep optimized caller. */ void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->pre_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); kp->pre_handler(kp, regs); } reset_kprobe_instance(); } } NOKPROBE_SYMBOL(opt_pre_handler); /* Free optimized instructions and optimized_kprobe */ static void free_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); arch_remove_optimized_kprobe(op); arch_remove_kprobe(p); kfree(op); } /* Return true(!0) if the kprobe is ready for optimization. */ static inline int kprobe_optready(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); return arch_prepared_optinsn(&op->optinsn); } return 0; } /* Return true if the kprobe is disarmed. Note: p must be on hash list */ bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; /* If kprobe is not aggr/opt probe, just return kprobe is disabled */ if (!kprobe_aggrprobe(p)) return kprobe_disabled(p); op = container_of(p, struct optimized_kprobe, kp); return kprobe_disabled(p) && list_empty(&op->list); } /* Return true(!0) if the probe is queued on (un)optimizing lists */ static int kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) return 1; } return 0; } /* * Return an optimized kprobe whose optimizing code replaces * instructions including addr (exclude breakpoint). */ static struct kprobe *get_optimized_kprobe(unsigned long addr) { int i; struct kprobe *p = NULL; struct optimized_kprobe *op; /* Don't check i == 0, since that is a breakpoint case. */ for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) p = get_kprobe((void *)(addr - i)); if (p && kprobe_optready(p)) { op = container_of(p, struct optimized_kprobe, kp); if (arch_within_optimized_kprobe(op, addr)) return p; } return NULL; } /* Optimization staging list, protected by kprobe_mutex */ static LIST_HEAD(optimizing_list); static LIST_HEAD(unoptimizing_list); static LIST_HEAD(freeing_list); static void kprobe_optimizer(struct work_struct *work); static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); #define OPTIMIZE_DELAY 5 /* * Optimize (replace a breakpoint with a jump) kprobes listed on * optimizing_list. */ static void do_optimize_kprobes(void) { lockdep_assert_held(&text_mutex); /* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus. * And same time, text_mutex will be held in cpu-hotplug and here. * This combination can cause a deadlock (cpu-hotplug try to lock * text_mutex but stop_machine can not be done because online_cpus * has been changed) * To avoid this deadlock, caller must have locked cpu hotplug * for preventing cpu-hotplug outside of text_mutex locking. */ lockdep_assert_cpus_held(); /* Optimization never be done when disarmed */ if (kprobes_all_disarmed || !kprobes_allow_optimization || list_empty(&optimizing_list)) return; arch_optimize_kprobes(&optimizing_list); } /* * Unoptimize (replace a jump with a breakpoint and remove the breakpoint * if need) kprobes listed on unoptimizing_list. */ static void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; lockdep_assert_held(&text_mutex); /* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held(); if (!list_empty(&unoptimizing_list)) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop on 'freeing_list' for disarming and removing from kprobe hash list */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { /* Switching from detour code to origin */ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled and not gone */ if (kprobe_disabled(&op->kp) && !kprobe_gone(&op->kp)) arch_disarm_kprobe(&op->kp); if (kprobe_unused(&op->kp)) { /* * Remove unused probes from hash list. After waiting * for synchronization, these probes are reclaimed. * (reclaiming is done by do_free_cleaned_kprobes.) */ hlist_del_rcu(&op->kp.hlist); } else list_del_init(&op->list); } } /* Reclaim all kprobes on the free_list */ static void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; list_for_each_entry_safe(op, tmp, &freeing_list, list) { list_del_init(&op->list); if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) { /* * This must not happen, but if there is a kprobe * still in use, keep it on kprobes hash list. */ continue; } free_aggr_kprobe(&op->kp); } } /* Start optimizer after OPTIMIZE_DELAY passed */ static void kick_kprobe_optimizer(void) { schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); } /* Kprobe jump optimizer */ static void kprobe_optimizer(struct work_struct *work) { mutex_lock(&kprobe_mutex); cpus_read_lock(); mutex_lock(&text_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) * kprobes before waiting for quiesence period. */ do_unoptimize_kprobes(); /* * Step 2: Wait for quiesence period to ensure all potentially * preempted tasks to have normally scheduled. Because optprobe * may modify multiple instructions, there is a chance that Nth * instruction is preempted. In that case, such tasks can return * to 2nd-Nth byte of jump instruction. This wait is for avoiding it. * Note that on non-preemptive kernel, this is transparently converted * to synchronoze_sched() to wait for all interrupts to have completed. */ synchronize_rcu_tasks(); /* Step 3: Optimize kprobes after quiesence period */ do_optimize_kprobes(); /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(); mutex_unlock(&text_mutex); cpus_read_unlock(); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { mutex_unlock(&kprobe_mutex); /* this will also make optimizing_work execute immmediately */ flush_delayed_work(&optimizing_work); /* @optimizing_work might not have been queued yet, relax */ cpu_relax(); mutex_lock(&kprobe_mutex); } mutex_unlock(&kprobe_mutex); } bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; list_for_each_entry(_op, &unoptimizing_list, list) { if (op == _op) return true; } return false; } /* Optimize kprobe if p is ready to be optimized */ static void optimize_kprobe(struct kprobe *p) { struct optimized_kprobe *op; /* Check if the kprobe is disabled or not ready for optimization. */ if (!kprobe_optready(p) || !kprobes_allow_optimization || (kprobe_disabled(p) || kprobes_all_disarmed)) return; /* kprobes with post_handler can not be optimized */ if (p->post_handler) return; op = container_of(p, struct optimized_kprobe, kp); /* Check there is no other kprobes at the optimized instructions */ if (arch_check_optimized_kprobe(op) < 0) return; /* Check if it is already optimized. */ if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) { if (optprobe_queued_unopt(op)) { /* This is under unoptimizing. Just dequeue the probe */ list_del_init(&op->list); } return; } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ if (WARN_ON_ONCE(!list_empty(&op->list))) return; list_add(&op->list, &optimizing_list); kick_kprobe_optimizer(); } /* Short cut to direct unoptimizing */ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; } /* Unoptimize a kprobe if p is optimized */ static void unoptimize_kprobe(struct kprobe *p, bool force) { struct optimized_kprobe *op; if (!kprobe_aggrprobe(p) || kprobe_disarmed(p)) return; /* This is not an optprobe nor optimized */ op = container_of(p, struct optimized_kprobe, kp); if (!kprobe_optimized(p)) return; if (!list_empty(&op->list)) { if (optprobe_queued_unopt(op)) { /* Queued in unoptimizing queue */ if (force) { /* * Forcibly unoptimize the kprobe here, and queue it * in the freeing list for release afterwards. */ force_unoptimize_kprobe(op); list_move(&op->list, &freeing_list); } } else { /* Dequeue from the optimizing queue */ list_del_init(&op->list); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; } return; } /* Optimized kprobe case */ if (force) { /* Forcibly update the code: this is a special case */ force_unoptimize_kprobe(op); } else { list_add(&op->list, &unoptimizing_list); kick_kprobe_optimizer(); } } /* Cancel unoptimizing for reusing */ static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means * there is still a relative jump) and disabled. */ op = container_of(ap, struct optimized_kprobe, kp); WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ if (!kprobe_optready(ap)) return -EINVAL; optimize_kprobe(ap); return 0; } /* Remove optimized instructions */ static void kill_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) /* Dequeue from the (un)optimization queue */ list_del_init(&op->list); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_unused(p)) { /* * Unused kprobe is on unoptimizing or freeing list. We move it * to freeing_list and let the kprobe_optimizer() remove it from * the kprobe hash list and free it. */ if (optprobe_queued_unopt(op)) list_move(&op->list, &freeing_list); } /* Don't touch the code, because it is already freed. */ arch_remove_optimized_kprobe(op); } static inline void __prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) { if (!kprobe_ftrace(p)) arch_prepare_optimized_kprobe(op, p); } /* Try to prepare optimized instructions */ static void prepare_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); __prepare_optimized_kprobe(op, p); } /* Allocate new optimized_kprobe and try to prepare optimized instructions */ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); if (!op) return NULL; INIT_LIST_HEAD(&op->list); op->kp.addr = p->addr; __prepare_optimized_kprobe(op, p); return &op->kp; } static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); /* * Prepare an optimized_kprobe and optimize it * NOTE: p must be a normal registered kprobe */ static void try_to_optimize_kprobe(struct kprobe *p) { struct kprobe *ap; struct optimized_kprobe *op; /* Impossible to optimize ftrace-based kprobe */ if (kprobe_ftrace(p)) return; /* For preparing optimization, jump_label_text_reserved() is called */ cpus_read_lock(); jump_label_lock(); mutex_lock(&text_mutex); ap = alloc_aggr_kprobe(p); if (!ap) goto out; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe */ arch_remove_optimized_kprobe(op); kfree(op); goto out; } init_aggr_kprobe(ap, p); optimize_kprobe(ap); /* This just kicks optimizer thread */ out: mutex_unlock(&text_mutex); jump_label_unlock(); cpus_read_unlock(); } static void optimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; mutex_lock(&kprobe_mutex); /* If optimization is already allowed, just return */ if (kprobes_allow_optimization) goto out; cpus_read_lock(); kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) if (!kprobe_disabled(p)) optimize_kprobe(p); } cpus_read_unlock(); printk(KERN_INFO "Kprobes globally optimized\n"); out: mutex_unlock(&kprobe_mutex); } #ifdef CONFIG_SYSCTL static void unoptimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; mutex_lock(&kprobe_mutex); /* If optimization is already prohibited, just return */ if (!kprobes_allow_optimization) { mutex_unlock(&kprobe_mutex); return; } cpus_read_lock(); kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) unoptimize_kprobe(p, false); } } cpus_read_unlock(); mutex_unlock(&kprobe_mutex); /* Wait for unoptimizing completion */ wait_for_kprobe_optimizer(); printk(KERN_INFO "Kprobes globally unoptimized\n"); } static DEFINE_MUTEX(kprobe_sysctl_mutex); int sysctl_kprobes_optimization; int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; mutex_lock(&kprobe_sysctl_mutex); sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (sysctl_kprobes_optimization) optimize_all_kprobes(); else unoptimize_all_kprobes(); mutex_unlock(&kprobe_sysctl_mutex); return ret; } #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. Must be called with text_mutex locked */ static void __arm_kprobe(struct kprobe *p) { struct kprobe *_p; /* Check collision with other optimized kprobes */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p)) /* Fallback to unoptimized kprobe */ unoptimize_kprobe(_p, true); arch_arm_kprobe(p); optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ } /* Remove the breakpoint of a probe. Must be called with text_mutex locked */ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; /* Try to unoptimize */ unoptimize_kprobe(p, kprobes_all_disarmed); if (!kprobe_queued(p)) { arch_disarm_kprobe(p); /* If another kprobe was blocked, optimize it. */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p) && reopt) optimize_kprobe(_p); } /* TODO: reoptimize others after unoptimized this probe */ } #else /* !CONFIG_OPTPROBES */ #define optimize_kprobe(p) do {} while (0) #define unoptimize_kprobe(p, f) do {} while (0) #define kill_optimized_kprobe(p) do {} while (0) #define prepare_optimized_kprobe(p) do {} while (0) #define try_to_optimize_kprobe(p) do {} while (0) #define __arm_kprobe(p) arch_arm_kprobe(p) #define __disarm_kprobe(p, o) arch_disarm_kprobe(p) #define kprobe_disarmed(p) kprobe_disabled(p) #define wait_for_kprobe_optimizer() do {} while (0) static int reuse_unused_kprobe(struct kprobe *ap) { /* * If the optimized kprobe is NOT supported, the aggr kprobe is * released at the same time that the last aggregated kprobe is * unregistered. * Thus there should be no chance to reuse unused kprobe. */ printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); return -EINVAL; } static void free_aggr_kprobe(struct kprobe *p) { arch_remove_kprobe(p); kfree(p); } static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { return kzalloc(sizeof(struct kprobe), GFP_KERNEL); } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS, }; static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_IPMODIFY, }; static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; /* Must ensure p->addr is really on ftrace */ static int prepare_kprobe(struct kprobe *p) { if (!kprobe_ftrace(p)) return arch_prepare_kprobe(p); return arch_prepare_kprobe_ftrace(p); } /* Caller must lock kprobe_mutex */ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); if (ret) { pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", p->addr, ret); return ret; } if (*cnt == 0) { ret = register_ftrace_function(ops); if (ret) { pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); goto err_ftrace; } } (*cnt)++; return ret; err_ftrace: /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. */ ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); return ret; } static int arm_kprobe_ftrace(struct kprobe *p) { bool ipmodify = (p->post_handler != NULL); return __arm_kprobe_ftrace(p, ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } /* Caller must lock kprobe_mutex */ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; if (*cnt == 1) { ret = unregister_ftrace_function(ops); if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) return ret; } (*cnt)--; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", p->addr, ret); return ret; } static int disarm_kprobe_ftrace(struct kprobe *p) { bool ipmodify = (p->post_handler != NULL); return __disarm_kprobe_ftrace(p, ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ static inline int prepare_kprobe(struct kprobe *p) { return arch_prepare_kprobe(p); } static inline int arm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; } static inline int disarm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; } #endif /* Arm a kprobe with text_mutex */ static int arm_kprobe(struct kprobe *kp) { if (unlikely(kprobe_ftrace(kp))) return arm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); return 0; } /* Disarm a kprobe with text_mutex */ static int disarm_kprobe(struct kprobe *kp, bool reopt) { if (unlikely(kprobe_ftrace(kp))) return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); return 0; } /* * Aggregate handlers for multiple kprobes support - these handlers * take care of invoking the individual kprobe handlers on p->list */ static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->pre_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); if (kp->pre_handler(kp, regs)) return 1; } reset_kprobe_instance(); } return 0; } NOKPROBE_SYMBOL(aggr_pre_handler); static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, unsigned long flags) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->post_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); kp->post_handler(kp, regs, flags); reset_kprobe_instance(); } } } NOKPROBE_SYMBOL(aggr_post_handler); static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr) { struct kprobe *cur = __this_cpu_read(kprobe_instance); /* * if we faulted "during" the execution of a user specified * probe handler, invoke just that probe's fault handler */ if (cur && cur->fault_handler) { if (cur->fault_handler(cur, regs, trapnr)) return 1; } return 0; } NOKPROBE_SYMBOL(aggr_fault_handler); /* Walks the list and increments nmissed count for multiprobe case */ void kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) kp->nmissed++; } return; } NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); static void recycle_rp_inst(struct kretprobe_instance *ri) { struct kretprobe *rp = ri->rp; /* remove rp inst off the rprobe_inst_table */ hlist_del(&ri->hlist); INIT_HLIST_NODE(&ri->hlist); if (likely(rp)) { raw_spin_lock(&rp->lock); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock(&rp->lock); } else kfree_rcu(ri, rcu); } NOKPROBE_SYMBOL(recycle_rp_inst); static void kretprobe_hash_lock(struct task_struct *tsk, struct hlist_head **head, unsigned long *flags) __acquires(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); raw_spinlock_t *hlist_lock; *head = &kretprobe_inst_table[hash]; hlist_lock = kretprobe_table_lock_ptr(hash); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. * Differentiate when it is taken in NMI context. */ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_hash_lock); static void kretprobe_table_lock(unsigned long hash, unsigned long *flags) __acquires(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. * Differentiate when it is taken in NMI context. */ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_table_lock); static void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags) __releases(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); raw_spinlock_t *hlist_lock; hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } NOKPROBE_SYMBOL(kretprobe_hash_unlock); static void kretprobe_table_unlock(unsigned long hash, unsigned long *flags) __releases(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } NOKPROBE_SYMBOL(kretprobe_table_unlock); static struct kprobe kprobe_busy = { .addr = (void *) get_kprobe, }; void kprobe_busy_begin(void) { struct kprobe_ctlblk *kcb; preempt_disable(); __this_cpu_write(current_kprobe, &kprobe_busy); kcb = get_kprobe_ctlblk(); kcb->kprobe_status = KPROBE_HIT_ACTIVE; } void kprobe_busy_end(void) { __this_cpu_write(current_kprobe, NULL); preempt_enable(); } /* * This function is called from finish_task_switch when task tk becomes dead, * so that we can recycle any function-return probe instances associated * with this task. These left over instances represent probed functions * that have been called but will never return. */ void kprobe_flush_task(struct task_struct *tk) { struct kretprobe_instance *ri; struct hlist_head *head; struct hlist_node *tmp; unsigned long hash, flags = 0; if (unlikely(!kprobes_initialized)) /* Early boot. kretprobe_table_locks not yet initialized. */ return; kprobe_busy_begin(); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task == tk) recycle_rp_inst(ri); } kretprobe_table_unlock(hash, &flags); kprobe_busy_end(); } NOKPROBE_SYMBOL(kprobe_flush_task); static inline void free_rp_inst(struct kretprobe *rp) { struct kretprobe_instance *ri; struct hlist_node *next; hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) { hlist_del(&ri->hlist); kfree(ri); } } static void cleanup_rp_inst(struct kretprobe *rp) { unsigned long flags, hash; struct kretprobe_instance *ri; struct hlist_node *next; struct hlist_head *head; /* To avoid recursive kretprobe by NMI, set kprobe busy here */ kprobe_busy_begin(); for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) { kretprobe_table_lock(hash, &flags); head = &kretprobe_inst_table[hash]; hlist_for_each_entry_safe(ri, next, head, hlist) { if (ri->rp == rp) ri->rp = NULL; } kretprobe_table_unlock(hash, &flags); } kprobe_busy_end(); free_rp_inst(rp); } NOKPROBE_SYMBOL(cleanup_rp_inst); /* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ list_add_rcu(&p->list, &ap->list); if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; return 0; } /* * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { /* Copy p's insn slot to ap */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; INIT_LIST_HEAD(&ap->list); INIT_HLIST_NODE(&ap->hlist); list_add_rcu(&p->list, &ap->list); hlist_replace_rcu(&p->hlist, &ap->hlist); } /* * This is the second or subsequent kprobe at the address - handle * the intricacies */ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) { int ret = 0; struct kprobe *ap = orig_p; cpus_read_lock(); /* For preparing optimization, jump_label_text_reserved() is called */ jump_label_lock(); mutex_lock(&text_mutex); if (!kprobe_aggrprobe(orig_p)) { /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ ap = alloc_aggr_kprobe(orig_p); if (!ap) { ret = -ENOMEM; goto out; } init_aggr_kprobe(ap, orig_p); } else if (kprobe_unused(ap)) { /* This probe is going to die. Rescue it */ ret = reuse_unused_kprobe(ap); if (ret) goto out; } if (kprobe_gone(ap)) { /* * Attempting to insert new probe at the same location that * had a probe in the module vaddr area which already * freed. So, the instruction slot has already been * released. We need a new slot for the new probe. */ ret = arch_prepare_kprobe(ap); if (ret) /* * Even if fail to allocate new slot, don't need to * free aggr_probe. It will be used next time, or * freed by unregister_kprobe. */ goto out; /* Prepare optimized instructions if possible. */ prepare_optimized_kprobe(ap); /* * Clear gone flag to prevent allocating new slot again, and * set disabled flag because it is not armed yet. */ ap->flags = (ap->flags & ~KPROBE_FLAG_GONE) | KPROBE_FLAG_DISABLED; } /* Copy ap's insn slot to p */ copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); out: mutex_unlock(&text_mutex); jump_label_unlock(); cpus_read_unlock(); if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ ret = arm_kprobe(ap); if (ret) { ap->flags |= KPROBE_FLAG_DISABLED; list_del_rcu(&p->list); synchronize_rcu(); } } } return ret; } bool __weak arch_within_kprobe_blacklist(unsigned long addr) { /* The __kprobes marked functions and entry code must not be probed */ return addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end; } static bool __within_kprobe_blacklist(unsigned long addr) { struct kprobe_blacklist_entry *ent; if (arch_within_kprobe_blacklist(addr)) return true; /* * If there exists a kprobe_blacklist, verify and * fail any probe registration in the prohibited area */ list_for_each_entry(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) return true; } return false; } bool within_kprobe_blacklist(unsigned long addr) { char symname[KSYM_NAME_LEN], *p; if (__within_kprobe_blacklist(addr)) return true; /* Check if the address is on a suffixed-symbol */ if (!lookup_symbol_name(addr, symname)) { p = strchr(symname, '.'); if (!p) return false; *p = '\0'; addr = (unsigned long)kprobe_lookup_name(symname, 0); if (addr) return __within_kprobe_blacklist(addr); } return false; } /* * If we have a symbol_name argument, look it up and add the offset field * to it. This way, we can specify a relative address to a symbol. * This returns encoded errors if it fails to look up symbol or invalid * combination of parameters. */ static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name, unsigned int offset) { if ((symbol_name && addr) || (!symbol_name && !addr)) goto invalid; if (symbol_name) { addr = kprobe_lookup_name(symbol_name, offset); if (!addr) return ERR_PTR(-ENOENT); } addr = (kprobe_opcode_t *)(((char *)addr) + offset); if (addr) return addr; invalid: return ERR_PTR(-EINVAL); } static kprobe_opcode_t *kprobe_addr(struct kprobe *p) { return _kprobe_addr(p->addr, p->symbol_name, p->offset); } /* Check passed kprobe is valid and return kprobe in kprobe_table. */ static struct kprobe *__get_valid_kprobe(struct kprobe *p) { struct kprobe *ap, *list_p; lockdep_assert_held(&kprobe_mutex); ap = get_kprobe(p->addr); if (unlikely(!ap)) return NULL; if (p != ap) { list_for_each_entry(list_p, &ap->list, list) if (list_p == p) /* kprobe p is a valid probe */ goto valid; return NULL; } valid: return ap; } /* Return error if the kprobe is being re-registered */ static inline int check_kprobe_rereg(struct kprobe *p) { int ret = 0; mutex_lock(&kprobe_mutex); if (__get_valid_kprobe(p)) ret = -EINVAL; mutex_unlock(&kprobe_mutex); return ret; } int __weak arch_check_ftrace_location(struct kprobe *p) { unsigned long ftrace_addr; ftrace_addr = ftrace_location((unsigned long)p->addr); if (ftrace_addr) { #ifdef CONFIG_KPROBES_ON_FTRACE /* Given address is not on the instruction boundary */ if ((unsigned long)p->addr != ftrace_addr) return -EILSEQ; p->flags |= KPROBE_FLAG_FTRACE; #else /* !CONFIG_KPROBES_ON_FTRACE */ return -EINVAL; #endif } return 0; } static bool is_cfi_preamble_symbol(unsigned long addr) { char symbuf[KSYM_NAME_LEN]; if (lookup_symbol_name(addr, symbuf)) return false; return str_has_prefix("__cfi_", symbuf) || str_has_prefix("__pfx_", symbuf); } static int check_kprobe_address_safe(struct kprobe *p, struct module **probed_mod) { int ret; ret = arch_check_ftrace_location(p); if (ret) return ret; jump_label_lock(); preempt_disable(); /* Ensure it is not in reserved area nor out of text */ if (!(core_kernel_text((unsigned long) p->addr) || is_module_text_address((unsigned long) p->addr)) || in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || find_bug((unsigned long)p->addr) || is_cfi_preamble_symbol((unsigned long)p->addr)) { ret = -EINVAL; goto out; } /* Check if are we probing a module */ *probed_mod = __module_text_address((unsigned long) p->addr); if (*probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ if (unlikely(!try_module_get(*probed_mod))) { ret = -ENOENT; goto out; } /* * If the module freed .init.text, we couldn't insert * kprobes in there. */ if (within_module_init((unsigned long)p->addr, *probed_mod) && (*probed_mod)->state != MODULE_STATE_COMING) { module_put(*probed_mod); *probed_mod = NULL; ret = -ENOENT; } } out: preempt_enable(); jump_label_unlock(); return ret; } int register_kprobe(struct kprobe *p) { int ret; struct kprobe *old_p; struct module *probed_mod; kprobe_opcode_t *addr; /* Adjust probe address from symbol */ addr = kprobe_addr(p); if (IS_ERR(addr)) return PTR_ERR(addr); p->addr = addr; ret = check_kprobe_rereg(p); if (ret) return ret; /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; p->nmissed = 0; INIT_LIST_HEAD(&p->list); ret = check_kprobe_address_safe(p, &probed_mod); if (ret) return ret; mutex_lock(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { /* Since this may unoptimize old_p, locking text_mutex. */ ret = register_aggr_kprobe(old_p, p); goto out; } cpus_read_lock(); /* Prevent text modification */ mutex_lock(&text_mutex); ret = prepare_kprobe(p); mutex_unlock(&text_mutex); cpus_read_unlock(); if (ret) goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) { ret = arm_kprobe(p); if (ret) { hlist_del_rcu(&p->hlist); synchronize_rcu(); goto out; } } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); out: mutex_unlock(&kprobe_mutex); if (probed_mod) module_put(probed_mod); return ret; } EXPORT_SYMBOL_GPL(register_kprobe); /* Check if all probes on the aggrprobe are disabled */ static int aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; lockdep_assert_held(&kprobe_mutex); list_for_each_entry(kp, &ap->list, list) if (!kprobe_disabled(kp)) /* * There is an active probe on the list. * We can't disable this ap. */ return 0; return 1; } /* Disable one kprobe: Make sure called under kprobe_mutex is locked */ static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ if (p != orig_p) p->flags |= KPROBE_FLAG_DISABLED; /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* * Don't be lazy here. Even if 'kprobes_all_disarmed' * is false, 'orig_p' might not have been armed yet. * Note arm_all_kprobes() __tries__ to arm all kprobes * on the best effort basis. */ if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; return ERR_PTR(ret); } } orig_p->flags |= KPROBE_FLAG_DISABLED; } } return orig_p; } /* * Unregister a kprobe without a scheduler synchronization. */ static int __unregister_kprobe_top(struct kprobe *p) { struct kprobe *ap, *list_p; /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); if (IS_ERR(ap)) return PTR_ERR(ap); if (ap == p) /* * This probe is an independent(and non-optimized) kprobe * (not an aggrprobe). Remove from the hash list. */ goto disarmed; /* Following process expects this probe is an aggrprobe */ WARN_ON(!kprobe_aggrprobe(ap)); if (list_is_singular(&ap->list) && kprobe_disarmed(ap)) /* * !disarmed could be happen if the probe is under delayed * unoptimizing. */ goto disarmed; else { /* If disabling probe has special handlers, update aggrprobe */ if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) goto noclean; } /* * For the kprobe-on-ftrace case, we keep the * post_handler setting to identify this aggrprobe * armed with kprobe_ipmodify_ops. */ if (!kprobe_ftrace(ap)) ap->post_handler = NULL; } noclean: /* * Remove from the aggrprobe: this path will do nothing in * __unregister_kprobe_bottom(). */ list_del_rcu(&p->list); if (!kprobe_disabled(ap) && !kprobes_all_disarmed) /* * Try to optimize this probe again, because post * handler may have been changed. */ optimize_kprobe(ap); } return 0; disarmed: hlist_del_rcu(&ap->hlist); return 0; } static void __unregister_kprobe_bottom(struct kprobe *p) { struct kprobe *ap; if (list_empty(&p->list)) /* This is an independent kprobe */ arch_remove_kprobe(p); else if (list_is_singular(&p->list)) { /* This is the last child of an aggrprobe */ ap = list_entry(p->list.next, struct kprobe, list); list_del(&p->list); free_aggr_kprobe(ap); } /* Otherwise, do nothing. */ } int register_kprobes(struct kprobe **kps, int num) { int i, ret = 0; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { ret = register_kprobe(kps[i]); if (ret < 0) { if (i > 0) unregister_kprobes(kps, i); break; } } return ret; } EXPORT_SYMBOL_GPL(register_kprobes); void unregister_kprobe(struct kprobe *p) { unregister_kprobes(&p, 1); } EXPORT_SYMBOL_GPL(unregister_kprobe); void unregister_kprobes(struct kprobe **kps, int num) { int i; if (num <= 0) return; mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) if (__unregister_kprobe_top(kps[i]) < 0) kps[i]->addr = NULL; mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) if (kps[i]->addr) __unregister_kprobe_bottom(kps[i]); } EXPORT_SYMBOL_GPL(unregister_kprobes); int __weak kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { return NOTIFY_DONE; } NOKPROBE_SYMBOL(kprobe_exceptions_notify); static struct notifier_block kprobe_exceptions_nb = { .notifier_call = kprobe_exceptions_notify, .priority = 0x7fffffff /* we need to be notified first */ }; unsigned long __weak arch_deref_entry_point(void *entry) { return (unsigned long)entry; } #ifdef CONFIG_KRETPROBES unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer) { struct kretprobe_instance *ri = NULL, *last = NULL; struct hlist_head *head; struct hlist_node *tmp; unsigned long flags; kprobe_opcode_t *correct_ret_addr = NULL; bool skipped = false; kretprobe_hash_lock(current, &head, &flags); /* * It is possible to have multiple instances associated with a given * task either because multiple functions in the call path have * return probes installed on them, and/or more than one * return probe was registered for a target function. * * We can handle this because: * - instances are always pushed into the head of the list * - when multiple return probes are registered for the same * function, the (chronologically) first instance's ret_addr * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; /* * Return probes must be pushed on this hash list correct * order (same as return order) so that it can be popped * correctly. However, if we find it is pushed it incorrect * order, this means we find a function which should not be * probed, because the wrong order entry is pushed on the * path of processing other kretprobe itself. */ if (ri->fp != frame_pointer) { if (!skipped) pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); skipped = true; continue; } correct_ret_addr = ri->ret_addr; if (skipped) pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", ri->rp->kp.addr); if (correct_ret_addr != trampoline_address) /* * This is the real return address. Any other * instances associated with this task are for * other calls deeper on the call stack */ break; } BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address)); last = ri; hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; if (ri->fp != frame_pointer) continue; if (ri->rp && ri->rp->handler) { struct kprobe *prev = kprobe_running(); __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); __this_cpu_write(current_kprobe, prev); } recycle_rp_inst(ri); if (ri == last) break; } kretprobe_hash_unlock(current, &flags); return (unsigned long)correct_ret_addr; } NOKPROBE_SYMBOL(__kretprobe_trampoline_handler) /* * This kprobe pre_handler is registered with every kretprobe. When probe * hits it will set up the return probe. */ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { struct kretprobe *rp = container_of(p, struct kretprobe, kp); unsigned long hash, flags = 0; struct kretprobe_instance *ri; /* TODO: consider to only swap the RA after the last pre_handler fired */ hash = hash_ptr(current, KPROBE_HASH_BITS); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. */ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); if (!hlist_empty(&rp->free_instances)) { ri = hlist_entry(rp->free_instances.first, struct kretprobe_instance, hlist); hlist_del(&ri->hlist); raw_spin_unlock_irqrestore(&rp->lock, flags); ri->rp = rp; ri->task = current; if (rp->entry_handler && rp->entry_handler(ri, regs)) { raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock_irqrestore(&rp->lock, flags); return 0; } arch_prepare_kretprobe(ri, regs); /* XXX(hch): why is there no hlist_move_head? */ INIT_HLIST_NODE(&ri->hlist); kretprobe_table_lock(hash, &flags); hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]); kretprobe_table_unlock(hash, &flags); } else { rp->nmissed++; raw_spin_unlock_irqrestore(&rp->lock, flags); } return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); bool __weak arch_kprobe_on_func_entry(unsigned long offset) { return !offset; } /** * kprobe_on_func_entry() -- check whether given address is function entry * @addr: Target address * @sym: Target symbol name * @offset: The offset from the symbol or the address * * This checks whether the given @addr+@offset or @sym+@offset is on the * function entry address or not. * This returns 0 if it is the function entry, or -EINVAL if it is not. * And also it returns -ENOENT if it fails the symbol or address lookup. * Caller must pass @addr or @sym (either one must be NULL), or this * returns -EINVAL. */ int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); if (IS_ERR(kp_addr)) return PTR_ERR(kp_addr); if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset)) return -ENOENT; if (!arch_kprobe_on_func_entry(offset)) return -EINVAL; return 0; } int register_kretprobe(struct kretprobe *rp) { int ret; struct kretprobe_instance *inst; int i; void *addr; ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset); if (ret) return ret; /* If only rp->kp.addr is specified, check reregistering kprobes */ if (rp->kp.addr && check_kprobe_rereg(&rp->kp)) return -EINVAL; if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); if (IS_ERR(addr)) return PTR_ERR(addr); for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { if (kretprobe_blacklist[i].addr == addr) return -EINVAL; } } if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) return -E2BIG; rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; rp->kp.fault_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { #ifdef CONFIG_PREEMPTION rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); #else rp->maxactive = num_possible_cpus(); #endif } raw_spin_lock_init(&rp->lock); INIT_HLIST_HEAD(&rp->free_instances); for (i = 0; i < rp->maxactive; i++) { inst = kmalloc(sizeof(struct kretprobe_instance) + rp->data_size, GFP_KERNEL); if (inst == NULL) { free_rp_inst(rp); return -ENOMEM; } INIT_HLIST_NODE(&inst->hlist); hlist_add_head(&inst->hlist, &rp->free_instances); } rp->nmissed = 0; /* Establish function entry probe point */ ret = register_kprobe(&rp->kp); if (ret != 0) free_rp_inst(rp); return ret; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { int ret = 0, i; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { ret = register_kretprobe(rps[i]); if (ret < 0) { if (i > 0) unregister_kretprobes(rps, i); break; } } return ret; } EXPORT_SYMBOL_GPL(register_kretprobes); void unregister_kretprobe(struct kretprobe *rp) { unregister_kretprobes(&rp, 1); } EXPORT_SYMBOL_GPL(unregister_kretprobe); void unregister_kretprobes(struct kretprobe **rps, int num) { int i; if (num <= 0) return; mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) if (__unregister_kprobe_top(&rps[i]->kp) < 0) rps[i]->kp.addr = NULL; mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) { if (rps[i]->kp.addr) { __unregister_kprobe_bottom(&rps[i]->kp); cleanup_rp_inst(rps[i]); } } } EXPORT_SYMBOL_GPL(unregister_kretprobes); #else /* CONFIG_KRETPROBES */ int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobes); void unregister_kretprobe(struct kretprobe *rp) { } EXPORT_SYMBOL_GPL(unregister_kretprobe); void unregister_kretprobes(struct kretprobe **rps, int num) { } EXPORT_SYMBOL_GPL(unregister_kretprobes); static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); #endif /* CONFIG_KRETPROBES */ /* Set the kprobe gone and remove its instruction buffer. */ static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; lockdep_assert_held(&kprobe_mutex); if (WARN_ON_ONCE(kprobe_gone(p))) return; p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. */ list_for_each_entry(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; kill_optimized_kprobe(p); } /* * Here, we can remove insn_slot safely, because no thread calls * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); /* * The module is going away. We should disarm the kprobe which * is using ftrace, because ftrace framework is still available at * MODULE_STATE_GOING notification. */ if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); } /* Disable one kprobe */ int disable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ p = __disable_kprobe(kp); if (IS_ERR(p)) ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(disable_kprobe); /* Enable one kprobe */ int enable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; mutex_lock(&kprobe_mutex); /* Check whether specified probe is valid. */ p = __get_valid_kprobe(kp); if (unlikely(p == NULL)) { ret = -EINVAL; goto out; } if (kprobe_gone(kp)) { /* This kprobe has gone, we couldn't enable it. */ ret = -EINVAL; goto out; } if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); if (ret) { p->flags |= KPROBE_FLAG_DISABLED; if (p != kp) kp->flags |= KPROBE_FLAG_DISABLED; } } out: mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(enable_kprobe); /* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { pr_err("Dumping kprobe:\n"); pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); int kprobe_add_ksym_blacklist(unsigned long entry) { struct kprobe_blacklist_entry *ent; unsigned long offset = 0, size = 0; if (!kernel_text_address(entry) || !kallsyms_lookup_size_offset(entry, &size, &offset)) return -EINVAL; ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return -ENOMEM; ent->start_addr = entry; ent->end_addr = entry + size; INIT_LIST_HEAD(&ent->list); list_add_tail(&ent->list, &kprobe_blacklist); return (int)size; } /* Add all symbols in given area into kprobe blacklist */ int kprobe_add_area_blacklist(unsigned long start, unsigned long end) { unsigned long entry; int ret = 0; for (entry = start; entry < end; entry += ret) { ret = kprobe_add_ksym_blacklist(entry); if (ret < 0) return ret; if (ret == 0) /* In case of alias symbol */ ret = 1; } return 0; } /* Remove all symbols in given area from kprobe blacklist */ static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) { struct kprobe_blacklist_entry *ent, *n; list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { if (ent->start_addr < start || ent->start_addr >= end) continue; list_del(&ent->list); kfree(ent); } } static void kprobe_remove_ksym_blacklist(unsigned long entry) { kprobe_remove_area_blacklist(entry, entry + 1); } int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { #ifdef __ARCH_WANT_KPROBES_INSN_SLOT if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym)) return 0; #ifdef CONFIG_OPTPROBES if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym)) return 0; #endif #endif if (!arch_kprobe_get_kallsym(&symnum, value, type, sym)) return 0; return -ERANGE; } int __init __weak arch_populate_kprobe_blacklist(void) { return 0; } /* * Lookup and populate the kprobe_blacklist. * * Unlike the kretprobe blacklist, we'll need to determine * the range of addresses that belong to the said functions, * since a kprobe need not necessarily be at the beginning * of a function. */ static int __init populate_kprobe_blacklist(unsigned long *start, unsigned long *end) { unsigned long entry; unsigned long *iter; int ret; for (iter = start; iter < end; iter++) { entry = arch_deref_entry_point((void *)*iter); ret = kprobe_add_ksym_blacklist(entry); if (ret == -EINVAL) continue; if (ret < 0) return ret; } /* Symbols in __kprobes_text are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start, (unsigned long)__kprobes_text_end); if (ret) return ret; /* Symbols in noinstr section are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start, (unsigned long)__noinstr_text_end); return ret ? : arch_populate_kprobe_blacklist(); } static void add_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; int i; if (mod->kprobe_blacklist) { for (i = 0; i < mod->num_kprobe_blacklist; i++) kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]); } start = (unsigned long)mod->kprobes_text_start; if (start) { end = start + mod->kprobes_text_size; kprobe_add_area_blacklist(start, end); } start = (unsigned long)mod->noinstr_text_start; if (start) { end = start + mod->noinstr_text_size; kprobe_add_area_blacklist(start, end); } } static void remove_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; int i; if (mod->kprobe_blacklist) { for (i = 0; i < mod->num_kprobe_blacklist; i++) kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]); } start = (unsigned long)mod->kprobes_text_start; if (start) { end = start + mod->kprobes_text_size; kprobe_remove_area_blacklist(start, end); } start = (unsigned long)mod->noinstr_text_start; if (start) { end = start + mod->noinstr_text_size; kprobe_remove_area_blacklist(start, end); } } /* Module notifier call back, checking kprobes on the module */ static int kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) { struct module *mod = data; struct hlist_head *head; struct kprobe *p; unsigned int i; int checkcore = (val == MODULE_STATE_GOING); if (val == MODULE_STATE_COMING) { mutex_lock(&kprobe_mutex); add_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); } if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; /* * When MODULE_STATE_GOING was notified, both of module .text and * .init.text sections would be freed. When MODULE_STATE_LIVE was * notified, only .init.text section would be freed. We need to * disable kprobes which have been inserted in the sections. */ mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (kprobe_gone(p)) continue; if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { /* * The vaddr this probe is installed will soon * be vfreed buy not synced to disk. Hence, * disarming the breakpoint isn't needed. * * Note, this will also move any optimized probes * that are pending to be removed from their * corresponding lists to the freeing_list and * will not be touched by the delayed * kprobe_optimizer work handler. */ kill_kprobe(p); } } } if (val == MODULE_STATE_GOING) remove_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; } static struct notifier_block kprobe_module_nb = { .notifier_call = kprobes_module_callback, .priority = 0 }; /* Markers of _kprobe_blacklist section */ extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; void kprobe_free_init_mem(void) { void *start = (void *)(&__init_begin); void *end = (void *)(&__init_end); struct hlist_head *head; struct kprobe *p; int i; mutex_lock(&kprobe_mutex); /* Kill all kprobes on initmem */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (start <= (void *)p->addr && (void *)p->addr < end) kill_kprobe(p); } } mutex_unlock(&kprobe_mutex); } static int __init init_kprobes(void) { int i, err = 0; /* FIXME allocate the probe table, currently defined statically */ /* initialize all list heads */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { INIT_HLIST_HEAD(&kprobe_table[i]); INIT_HLIST_HEAD(&kretprobe_inst_table[i]); raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); } err = populate_kprobe_blacklist(__start_kprobe_blacklist, __stop_kprobe_blacklist); if (err) { pr_err("kprobes: failed to populate blacklist: %d\n", err); pr_err("Please take care of using kprobes.\n"); } if (kretprobe_blacklist_size) { /* lookup the function address from its name */ for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { kretprobe_blacklist[i].addr = kprobe_lookup_name(kretprobe_blacklist[i].name, 0); if (!kretprobe_blacklist[i].addr) printk("kretprobe: lookup failed: %s\n", kretprobe_blacklist[i].name); } } /* By default, kprobes are armed */ kprobes_all_disarmed = false; #if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) /* Init kprobe_optinsn_slots for allocation */ kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; #endif err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); if (!err) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); if (!err) init_test_probes(); return err; } early_initcall(init_kprobes); #if defined(CONFIG_OPTPROBES) static int __init init_optprobes(void) { /* * Enable kprobe optimization - this kicks the optimizer which * depends on synchronize_rcu_tasks() and ksoftirqd, that is * not spawned in early initcall. So delay the optimization. */ optimize_all_kprobes(); return 0; } subsys_initcall(init_optprobes); #endif #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; void *addr = p->addr; if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; else kprobe_type = "k"; if (!kallsyms_show_value(pi->file->f_cred)) addr = NULL; if (sym) seq_printf(pi, "%px %s %s+0x%x %s ", addr, kprobe_type, sym, offset, (modname ? modname : " ")); else /* try to use %pS */ seq_printf(pi, "%px %s %pS ", addr, kprobe_type, p->addr); if (!pp) pp = p; seq_printf(pi, "%s%s%s%s\n", (kprobe_gone(p) ? "[GONE]" : ""), ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } static void *kprobe_seq_start(struct seq_file *f, loff_t *pos) { return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL; } static void *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) { (*pos)++; if (*pos >= KPROBE_TABLE_SIZE) return NULL; return pos; } static void kprobe_seq_stop(struct seq_file *f, void *v) { /* Nothing to do */ } static int show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; struct kprobe *p, *kp; const char *sym = NULL; unsigned int i = *(loff_t *) v; unsigned long offset = 0; char *modname, namebuf[KSYM_NAME_LEN]; head = &kprobe_table[i]; preempt_disable(); hlist_for_each_entry_rcu(p, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); if (kprobe_aggrprobe(p)) { list_for_each_entry_rcu(kp, &p->list, list) report_probe(pi, kp, sym, offset, modname, p); } else report_probe(pi, p, sym, offset, modname, NULL); } preempt_enable(); return 0; } static const struct seq_operations kprobes_sops = { .start = kprobe_seq_start, .next = kprobe_seq_next, .stop = kprobe_seq_stop, .show = show_kprobe_addr }; DEFINE_SEQ_ATTRIBUTE(kprobes); /* kprobes/blacklist -- shows which functions can not be probed */ static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos) { mutex_lock(&kprobe_mutex); return seq_list_start(&kprobe_blacklist, *pos); } static void *kprobe_blacklist_seq_next(struct seq_file *m, void *v, loff_t *pos) { return seq_list_next(v, &kprobe_blacklist, pos); } static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) { struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); /* * If /proc/kallsyms is not showing kernel address, we won't * show them here either. */ if (!kallsyms_show_value(m->file->f_cred)) seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, (void *)ent->start_addr); else seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, (void *)ent->end_addr, (void *)ent->start_addr); return 0; } static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v) { mutex_unlock(&kprobe_mutex); } static const struct seq_operations kprobe_blacklist_sops = { .start = kprobe_blacklist_seq_start, .next = kprobe_blacklist_seq_next, .stop = kprobe_blacklist_seq_stop, .show = kprobe_blacklist_seq_show, }; DEFINE_SEQ_ATTRIBUTE(kprobe_blacklist); static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i, total = 0, errors = 0; int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are armed, just return */ if (!kprobes_all_disarmed) goto already_enabled; /* * optimize_kprobe() called by arm_kprobe() checks * kprobes_all_disarmed, so set kprobes_all_disarmed before * arm_kprobe. */ kprobes_all_disarmed = false; /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Arm all kprobes on a best-effort basis */ hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) { err = arm_kprobe(p); if (err) { errors++; ret = err; } total++; } } } if (errors) pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", errors, total); else pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); return ret; } static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i, total = 0, errors = 0; int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); return 0; } kprobes_all_disarmed = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry(p, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { err = disarm_kprobe(p, false); if (err) { errors++; ret = err; } total++; } } } if (errors) pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", errors, total); else pr_info("Kprobes globally disabled\n"); mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); return ret; } /* * XXX: The debugfs bool file interface doesn't allow for callbacks * when the bool state is switched. We can reuse that facility when * available */ static ssize_t read_enabled_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[3]; if (!kprobes_all_disarmed) buf[0] = '1'; else buf[0] = '0'; buf[1] = '\n'; buf[2] = 0x00; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t write_enabled_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { char buf[32]; size_t buf_size; int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; buf[buf_size] = '\0'; switch (buf[0]) { case 'y': case 'Y': case '1': ret = arm_all_kprobes(); break; case 'n': case 'N': case '0': ret = disarm_all_kprobes(); break; default: return -EINVAL; } if (ret) return ret; return count; } static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, .llseek = default_llseek, }; static int __init debugfs_kprobe_init(void) { struct dentry *dir; dir = debugfs_create_dir("kprobes", NULL); debugfs_create_file("list", 0400, dir, NULL, &kprobes_fops); debugfs_create_file("enabled", 0600, dir, NULL, &fops_kp); debugfs_create_file("blacklist", 0400, dir, NULL, &kprobe_blacklist_fops); return 0; } late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ |
| 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 | /* 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. */ #define MAX_STACK_ALLOC 832 #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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/spinlock_types.h> struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts * @refs: atomic_t counter field * * The counter saturates at REFCOUNT_SATURATED and will not move once * there. This avoids wrapping the counter and causing 'spurious' * use-after-free bugs. */ typedef struct refcount_struct { atomic_t refs; } refcount_t; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old < 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: fully on the stack (when can't do frame-checking) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { WARN_ONCE(1, "Bad or missing usercopy whitelist? Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); } void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } /* Checks for allocs that are marked in some way as spanning multiple pages. */ static inline void check_page_span(const void *ptr, unsigned long n, struct page *page, bool to_user) { #ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN const void *end = ptr + n - 1; struct page *endpage; bool is_reserved, is_cma; /* * Sometimes the kernel data regions are not marked Reserved (see * check below). And sometimes [_sdata,_edata) does not cover * rodata and/or bss, so check each range explicitly. */ /* Allow reads of kernel rodata region (if not marked as Reserved). */ if (ptr >= (const void *)__start_rodata && end <= (const void *)__end_rodata) { if (!to_user) usercopy_abort("rodata", NULL, to_user, 0, n); return; } /* Allow kernel data region (if not marked as Reserved). */ if (ptr >= (const void *)_sdata && end <= (const void *)_edata) return; /* Allow kernel bss region (if not marked as Reserved). */ if (ptr >= (const void *)__bss_start && end <= (const void *)__bss_stop) return; /* Is the object wholly within one base page? */ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == ((unsigned long)end & (unsigned long)PAGE_MASK))) return; /* Allow if fully inside the same compound (__GFP_COMP) page. */ endpage = virt_to_head_page(end); if (likely(endpage == page)) return; /* * Reject if range is entirely either Reserved (i.e. special or * device memory), or CMA. Otherwise, reject since the object spans * several independently allocated pages. */ is_reserved = PageReserved(page); is_cma = is_migrate_cma_page(page); if (!is_reserved && !is_cma) usercopy_abort("spans multiple pages", NULL, to_user, 0, n); for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { page = virt_to_head_page(ptr); if (is_reserved && !PageReserved(page)) usercopy_abort("spans Reserved and non-Reserved pages", NULL, to_user, 0, n); if (is_cma && !is_migrate_cma_page(page)) usercopy_abort("spans CMA and non-CMA pages", NULL, to_user, 0, n); } #endif } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { struct page *page; if (!virt_addr_valid(ptr)) return; /* * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the * highmem page or fallback to virt_to_page(). The following * is effectively a highmem-aware virt_to_head_page(). */ page = compound_head(kmap_to_page((void *)ptr)); if (PageSlab(page)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, page, to_user); } else { /* Verify object does not incorrectly span multiple pages. */ check_page_span(ptr, n, page, to_user); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, 0, n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { if (strtobool(str, &enable_checks)) pr_warn("Invalid option string for hardened_usercopy: '%s'\n", str); return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> #include "internal.h" unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". * * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied * by that "1024/sizeof(ptr)" before, we already know there are sufficient * clear low bits. Clang seems to realize that, gcc ends up being confused. * * On a 128-bit machine, the ALIGN() would actually matter. In the meantime, * let's consider it documentation (and maybe a test-case for gcc to improve * its code generation ;) */ static struct fdtable * alloc_fdtable(unsigned int nr) { struct fdtable *fdt; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. */ nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); nr = ALIGN(nr, BITS_PER_LONG); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. Deal * with that in caller, it's cheaper that way. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return NULL; } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr); /* make sure all __fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (!new_fdt) return -ENOMEM; /* * extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { __free_fdtable(new_fdt); return -EMFILE; } cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in __fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); *errorp = -EMFILE; goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } struct files_struct *get_files_struct(struct task_struct *task) { struct files_struct *files; task_lock(task); files = task->files; if (files) atomic_inc(&files->count); task_unlock(task); return files; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void reset_files_struct(struct files_struct *files) { struct task_struct *tsk = current; struct files_struct *old; old = tsk->files; task_lock(tsk); tsk->files = files; task_unlock(tsk); put_files_struct(old); } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit > maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags) { unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } static int alloc_fd(unsigned start, unsigned flags) { return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags); } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return __alloc_fd(current->files, 0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * NOTE: __fd_install() variant is really, really low-level; don't * use it unless you are forced to by truly lousy API shoved down * your throat. 'files' *MUST* be either current->files or obtained * by get_files_struct(current) done by whoever had given it to you, * or really bad things will happen. Normally you want to use * fd_install() instead. */ void __fd_install(struct files_struct *files, unsigned int fd, struct file *file) { struct fdtable *fdt; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } /* * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { __fd_install(current->files, fd, file); } EXPORT_SYMBOL(fd_install); static struct file *pick_file(struct files_struct *files, unsigned fd) { struct file *file = NULL; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); out_unlock: spin_unlock(&files->file_lock); return file; } /* * The same warnings as for __alloc_fd()/__fd_install() apply here... */ int __close_fd(struct files_struct *files, unsigned fd) { struct file *file; file = pick_file(files, fd); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(__close_fd); /* for ksys_close() */ /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { unsigned int cur_max; struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~CLOSE_RANGE_UNSHARE) return -EINVAL; if (fd > max_fd) return -EINVAL; rcu_read_lock(); cur_max = files_fdtable(cur_fds)->max_fds; rcu_read_unlock(); /* cap to last valid index into fdtable */ cur_max--; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the requested range is greater than the current maximum, * we're closing everything so only copy all file descriptors * beneath the lowest file descriptor. */ if (max_fd >= cur_max) max_unshare_fds = fd; ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } max_fd = min(max_fd, cur_max); while (fd <= max_fd) { struct file *file; file = pick_file(cur_fds, fd++); if (!file) continue; filp_close(file, cur_fds); cond_resched(); } if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /* * See close_fd_get_file() below, this variant assumes current->files->file_lock * is held. */ int __close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; struct fdtable *fdt; fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_err; file = fdt->fd[fd]; if (!file) goto out_err; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); get_file(file); *res = file; return 0; out_err: *res = NULL; return -ENOENT; } /* * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then * an fput(). */ int close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; int ret; spin_lock(&files->file_lock); ret = __close_fd_get_file(fd, res); spin_unlock(&files->file_lock); return ret; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; if (unlikely(fd >= fdt->max_fds)) return NULL; fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); file = rcu_dereference_raw(*fdentry); if (unlikely(!file)) return NULL; if (unlikely(file->f_mode & mask)) return NULL; /* * Ok, we have a file pointer. However, because we do * this all locklessly under RCU, we may be racing with * that file being closed. * * Such a race can take two forms: * * (a) the file ref already went down to zero, * and get_file_rcu_many() fails. Just try * again: */ if (unlikely(!get_file_rcu_many(file, refs))) continue; /* * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our refs and try again. */ if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || unlikely(rcu_dereference_raw(*fdentry) != file)) { fput_many(file, refs); continue; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask, refs); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) { return __fget_files(current->files, fd, mask, refs); } struct file *fget_many(unsigned int fd, unsigned int refs) { return __fget(fd, FMODE_PATH, refs); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH, 1); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0, 1); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0, 1); task_unlock(task); return file; } /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; if (atomic_read(&files->count) == 1) { file = __fcheck_files(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget(fd, mask, 1); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || S_ISDIR(file_inode(file)->i_mode)); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return __close_fd(files, fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * __receive_fd() - Install received file into file descriptor table * * @fd: fd to install into (if negative, a new fd will be allocated) * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; if (fd < 0) { new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; } else { new_fd = fd; } if (ufd) { error = put_user(new_fd, ufd); if (error) { if (fd < 0) put_unused_fd(new_fd); return error; } } if (fd < 0) { fd_install(new_fd, get_file(file)); } else { error = replace_fd(new_fd, file, o_flags); if (error) return error; } /* Bump the sock usage counts, if any. */ __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = fcheck(oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; int retval = oldfd; rcu_read_lock(); if (!fcheck_files(files, oldfd)) retval = -EBADF; rcu_read_unlock(); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; if (from >= rlimit(RLIMIT_NOFILE)) return -EINVAL; err = alloc_fd(from, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H #include <asm/page_64_types.h> #ifndef __ASSEMBLY__ #include <asm/alternative.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; static inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); return x; } #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); extern unsigned long __phys_addr_symbol(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #define __phys_addr_symbol(x) \ ((unsigned long)(x) - __START_KERNEL_map + phys_base) #endif #define __phys_reloc_hide(x) (x) #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) ((pfn) < max_pfn) #endif void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); static inline void clear_page(void *page) { alternative_call_2(clear_page_orig, clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, "=D" (page), "0" (page) : "cc", "memory", "rax", "rcx"); } void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION # define __HAVE_ARCH_GATE_AREA 1 #endif #endif /* _ASM_X86_PAGE_64_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/ima.h> #include <linux/swap.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; static void file_free_rcu(struct rcu_head *head) { struct file *f = container_of(head, struct file, f_u.fu_rcuhead); put_cred(f->f_cred); kmem_cache_free(filp_cachep, f); } static inline void file_free(struct file *f) { security_file_free(f); if (!(f->f_mode & FMODE_NOACCOUNT)) percpu_counter_dec(&nr_files); call_rcu(&f->f_u.fu_rcuhead, file_free_rcu); } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); /* * Handle nr_files sysctl */ #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } #endif static struct file *__alloc_file(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { file_free_rcu(&f->f_u.fu_rcuhead); return ERR_PTR(error); } atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); eventpoll_init_file(f); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ return f; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = __alloc_file(flags, cred); if (!IS_ERR(f)) percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * Should not be used unless there's a very good reason to do so. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f = __alloc_file(flags, cred); if (!IS_ERR(f)) f->f_mode |= FMODE_NOACCOUNT; return f; } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (IS_ERR(file)) return file; file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); return file; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct qstr this = QSTR_INIT(name, strlen(name)); struct path path; struct file *file; path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this); if (!path.dentry) return ERR_PTR(-ENOMEM); if (!mnt->mnt_sb->s_d_op) d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(mnt); d_instantiate(path.dentry, inode); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); } return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); ima_file_free(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); put_pid(file->f_owner.pid); if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); if (mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(mnt); } dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_u.fu_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_u.fu_rcuhead)); } /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); void fput_many(struct file *file, unsigned int refs) { if (atomic_long_sub_and_test(refs, &file->f_count)) { struct task_struct *task = current; if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_u.fu_rcuhead, ____fput); if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_u.fu_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } } void fput(struct file *file) { fput_many(file, 1); } /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; BUG_ON(!(task->flags & PF_KTHREAD)); __fput(file); } } EXPORT_SYMBOL(fput); EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ #include <stdarg.h> #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); extern void *memdup_user(const void __user *, size_t); extern void *vmemdup_user(const void __user *, size_t); extern void *memdup_user_nul(const void __user *, size_t); /* * Include machine specific inline routines */ #include <asm/string.h> #ifndef __HAVE_ARCH_STRCPY extern char * strcpy(char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCPY extern char * strncpy(char *,const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCPY size_t strlcpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRSCPY ssize_t strscpy(char *, const char *, size_t); #endif /* Wraps calls to strscpy()/memset(), no arch specific code required */ ssize_t strscpy_pad(char *dest, const char *src, size_t count); #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif #ifndef __HAVE_ARCH_STRNCAT extern char * strncat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCAT extern size_t strlcat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCMP extern int strcmp(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCMP extern int strncmp(const char *,const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCASECMP extern int strcasecmp(const char *s1, const char *s2); #endif #ifndef __HAVE_ARCH_STRNCASECMP extern int strncasecmp(const char *s1, const char *s2, size_t n); #endif #ifndef __HAVE_ARCH_STRCHR extern char * strchr(const char *,int); #endif #ifndef __HAVE_ARCH_STRCHRNUL extern char * strchrnul(const char *,int); #endif extern char * strnchrnul(const char *, size_t, int); #ifndef __HAVE_ARCH_STRNCHR extern char * strnchr(const char *, size_t, int); #endif #ifndef __HAVE_ARCH_STRRCHR extern char * strrchr(const char *,int); #endif extern char * __must_check skip_spaces(const char *); extern char *strim(char *); static inline __must_check char *strstrip(char *str) { return strim(str); } #ifndef __HAVE_ARCH_STRSTR extern char * strstr(const char *, const char *); #endif #ifndef __HAVE_ARCH_STRNSTR extern char * strnstr(const char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRLEN extern __kernel_size_t strlen(const char *); #endif #ifndef __HAVE_ARCH_STRNLEN extern __kernel_size_t strnlen(const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRPBRK extern char * strpbrk(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRSEP extern char * strsep(char **,const char *); #endif #ifndef __HAVE_ARCH_STRSPN extern __kernel_size_t strspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRCSPN extern __kernel_size_t strcspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET16 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET32 extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET64 extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); #endif static inline void *memset_l(unsigned long *p, unsigned long v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, v, n); else return memset64((uint64_t *)p, v, n); } static inline void *memset_p(void **p, void *v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, (uintptr_t)v, n); else return memset64((uint64_t *)p, (uintptr_t)v, n); } extern void **__memcat_p(void **a, void **b); #define memcat_p(a, b) ({ \ BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ "type mismatch in memcat_p()"); \ (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ }) #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMMOVE extern void * memmove(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSCAN extern void * memscan(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_BCMP extern int bcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); } #endif void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); /** * sysfs_match_string - matches given string in an array * @_a: array of strings * @_s: string to match with * * Helper for __sysfs_match_string(). Calculates the size of @a automatically. */ #define sysfs_match_string(_a, _s) __sysfs_match_string(_a, ARRAY_SIZE(_a), _s) #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); int ptr_to_hashval(const void *ptr, unsigned long *hashval_out); /** * strstarts - does @str start with @prefix? * @str: string to examine * @prefix: prefix to look for. */ static inline bool strstarts(const char *str, const char *prefix) { return strncmp(str, prefix, strlen(prefix)) == 0; } size_t memweight(const void *ptr, size_t bytes); /** * memzero_explicit - Fill a region of memory (e.g. sensitive * keying data) with 0s. * @s: Pointer to the start of the area. * @count: The size of the area. * * Note: usually using memset() is just fine (!), but in cases * where clearing out _local_ data at the end of a scope is * necessary, memzero_explicit() should be used instead in * order to prevent the compiler from optimising away zeroing. * * memzero_explicit() doesn't need an arch-specific version as * it just invokes the one of memset() implicitly. */ static inline void memzero_explicit(void *s, size_t count) { memset(s, 0, count); barrier_data(s); } /** * kbasename - return the last part of a pathname. * * @path: path to extract the filename from. */ static inline const char *kbasename(const char *path) { const char *tail = strrchr(path, '/'); return tail ? tail + 1 : path; } #define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #ifdef CONFIG_KASAN extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else #define __underlying_memchr __builtin_memchr #define __underlying_memcmp __builtin_memcmp #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy #endif __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_strncpy(p, q, size); } __FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; } __FORTIFY_INLINE __kernel_size_t strlen(const char *p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 0); /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); return ret; } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 0); __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(__func__); return ret; } /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) { size_t ret; size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __real_strlcpy(p, q, size); ret = strlen(q); if (size) { size_t len = (ret >= size) ? size - 1 : ret; if (__builtin_constant_p(len) && len >= p_size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; } /* defined after fortified strlen and strnlen to reuse them */ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_memset(p, c, size); } __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __write_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memcpy(p, q, size); } __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __write_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memmove(p, q, size); } extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memscan(p, c, size); } __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __read_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memchr_inv(p, c, size); } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_kmemdup(p, size, gfp); } /* defined after fortified strlen and memcpy to reuse them */ __FORTIFY_INLINE char *strcpy(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp #undef __underlying_memcpy #undef __underlying_memmove #undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy #endif /** * memcpy_and_pad - Copy one buffer to another with padding * @dest: Where to copy to * @dest_len: The destination buffer size * @src: Where to copy from * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ static inline void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad) { if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); } else memcpy(dest, src, dest_len); } /** * str_has_prefix - Test if a string has a given prefix * @str: The string to test * @prefix: The string to see if @str starts with * * A common way to test a prefix of a string is to do: * strncmp(str, prefix, sizeof(prefix) - 1) * * But this can lead to bugs due to typos, or if prefix is a pointer * and not a constant. Instead use str_has_prefix(). * * Returns: * * strlen(@prefix) if @str starts with @prefix * * 0 if @str does not start with @prefix */ static __always_inline size_t str_has_prefix(const char *str, const char *prefix) { size_t len = strlen(prefix); return strncmp(str, prefix, len) == 0 ? len : 0; } #endif /* _LINUX_STRING_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); static inline void copy_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __compiletime_object_size(addr); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TASK_WORK_H #define _LINUX_TASK_WORK_H #include <linux/list.h> #include <linux/sched.h> typedef void (*task_work_func_t)(struct callback_head *); static inline void init_task_work(struct callback_head *twork, task_work_func_t func) { twork->func = func; } enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, }; int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) { task_work_run(); } #endif /* _LINUX_TASK_WORK_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LLIST_H #define LLIST_H /* * Lock-less NULL terminated single linked list * * Cases where locking is not needed: * If there are multiple producers and multiple consumers, llist_add can be * used in producers and llist_del_all can be used in consumers simultaneously * without locking. Also a single consumer can use llist_del_first while * multiple producers simultaneously use llist_add, without any locking. * * Cases where locking is needed: * If we have multiple consumers with llist_del_first used in one consumer, and * llist_del_first or llist_del_all used in other consumers, then a lock is * needed. This is because llist_del_first depends on list->first->next not * changing, but without lock protection, there's no way to be sure about that * if a preemption happens in the middle of the delete operation and on being * preempted back, the list->first is the same as before causing the cmpxchg in * llist_del_first to succeed. For example, while a llist_del_first operation * is in progress in one consumer, then a llist_del_first, llist_add, * llist_add (or llist_del_all, llist_add, llist_add) sequence in another * consumer may cause violations. * * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * * Where, a particular row's operation can happen concurrently with a column's * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list * entries can not be traversed safely before deleted from the list. * The order of deleted entries is from the newest to the oldest added * one. If you want to traverse from the oldest to the newest, you * must reverse the order by yourself before traversing. * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/atomic.h> #include <linux/kernel.h> struct llist_head { struct llist_node *first; }; struct llist_node { struct llist_node *next; }; #define LLIST_HEAD_INIT(name) { NULL } #define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) /** * init_llist_head - initialize lock-less list head * @head: the head for your lock-less list */ static inline void init_llist_head(struct llist_head *list) { list->first = NULL; } /** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. * @member: the name of the llist_node within the struct. */ #define llist_entry(ptr, type, member) \ container_of(ptr, type, member) /** * member_address_is_nonnull - check whether the member address is not NULL * @ptr: the object pointer (struct type * that contains the llist_node) * @member: the name of the llist_node within the struct. * * This macro is conceptually the same as * &ptr->member != NULL * but it works around the fact that compilers can decide that taking a member * address is never a NULL pointer. * * Real objects that start at a high address and have a member at NULL are * unlikely to exist, but such pointers may be returned e.g. by the * container_of() macro. */ #define member_address_is_nonnull(ptr, member) \ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) /** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each(pos, node) \ for ((pos) = (node); pos; (pos) = (pos)->next) /** * llist_for_each_safe - iterate over some deleted entries of a lock-less list * safe against removal of list entry * @pos: the &struct llist_node to use as a loop cursor * @n: another &struct llist_node to use as temporary storage * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_safe(pos, n, node) \ for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) /** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type * safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @node: the first entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * * Not guaranteed to be accurate or up to date. Just a quick way to * test whether the list is empty without deleting something from the * list. */ static inline bool llist_empty(const struct llist_head *head) { return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) { return node->next; } extern bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head); /** * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list * * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { return llist_add_batch(new, new, head); } /** * llist_del_all - delete all entries from lock-less list * @head: the head of lock-less list to delete all entries * * If list is empty, return NULL, otherwise, delete all entries and * return the pointer to the first entry. The order of entries * deleted is from the newest to the oldest added one. */ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } extern struct llist_node *llist_del_first(struct llist_head *head); struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline void fsnotify_name(struct inode *dir, __u32 mask, struct inode *child, const struct qstr *name, u32 cookie) { fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path = &file->f_path; if (file->f_mode & FMODE_NONOTIFY) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } /* Simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { int ret; __u32 fsnotify_mask = 0; if (!(mask & (MAY_READ | MAY_OPEN))) return 0; if (mask & MAY_OPEN) { fsnotify_mask = FS_OPEN_PERM; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } } else if (mask & MAY_READ) { fsnotify_mask = FS_ACCESS_PERM; } return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; const struct qstr *new_name = &moved->d_name; if (old_dir == new_dir) old_dir_mask |= FS_DN_RENAME; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; } fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in */ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) { audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(inode, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(dir, mask, inode, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created */ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) { audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } #endif /* _LINUX_FS_NOTIFY_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 | /* 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> #include <asm/alternative.h> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" #define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ #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__ */ #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 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/kernel.h> /* * This is largely generic for little-endian machines, but the * optimal byte mask counting is probably going to be something * that is architecture-specific. If you have a reliably fast * bit count instruction, that might be better than the multiply * and shift, for example. */ struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } #ifdef CONFIG_64BIT /* * Jan Achrenius on G+: microoptimized version of * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" * that works for the bytemasks without having to * mask them first. */ static inline long count_masked_bytes(unsigned long mask) { return mask*0x0001020304050608ul >> 56; } #else /* 32-bit case */ /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline long count_masked_bytes(long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) static inline unsigned long find_zero(unsigned long mask) { return count_masked_bytes(mask); } /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret, dummy; asm( "1:\tmov %2,%0\n" "2:\n" ".section .fixup,\"ax\"\n" "3:\t" "lea %2,%1\n\t" "and %3,%1\n\t" "mov (%1),%0\n\t" "leal %2,%%ecx\n\t" "andl %4,%%ecx\n\t" "shll $3,%%ecx\n\t" "shr %%cl,%0\n\t" "jmp 2b\n" ".previous\n" _ASM_EXTABLE(1b, 3b) :"=&r" (ret),"=&c" (dummy) :"m" (*(unsigned long *)addr), "i" (-sizeof(unsigned long)), "i" (sizeof(unsigned long)-1)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); if (IS_ERR(dir)) return PTR_ERR(dir); return 0; } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 | // SPDX-License-Identifier: GPL-2.0 /* * Shared application/kernel submission and completion ring pairs, for * supporting fast/efficient IO. * * A note on the read/write ordering memory barriers that are matched between * the application and kernel side. * * After the application reads the CQ ring tail, it must use an * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses * before writing the tail (using smp_load_acquire to read the tail will * do). It also needs a smp_mb() before updating CQ head (ordering the * entry load(s) with the head store), pairing with an implicit barrier * through a control-dependency in io_get_cqe (smp_store_release to * store head will do). Failure to do so could lead to reading invalid * CQ entries. * * Likewise, the application must use an appropriate smp_wmb() before * writing the SQ tail (ordering SQ entry stores with the tail store), * which pairs with smp_load_acquire in io_get_sqring (smp_store_release * to store the tail will do). And it needs a barrier ordering the SQ * head load before writing new SQ entries (smp_load_acquire to read * head will do). * * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* * updating the SQ tail; a full memory barrier smp_mb() is needed * between. * * Also see the examples in the liburing library: * * git://git.kernel.dk/liburing * * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens * from data shared between the kernel and application. This is done both * for ordering purposes, but also to ensure that once a value is loaded from * data that the application could potentially modify, it remains stable. * * Copyright (C) 2018-2019 Jens Axboe * Copyright (c) 2018-2019 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <net/compat.h> #include <linux/refcount.h> #include <linux/uio.h> #include <linux/bits.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/bvec.h> #include <linux/net.h> #include <net/sock.h> #include <net/af_unix.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include <linux/sizes.h> #include <linux/hugetlb.h> #include <linux/highmem.h> #include <linux/namei.h> #include <linux/fsnotify.h> #include <linux/fadvise.h> #include <linux/eventpoll.h> #include <linux/splice.h> #include <linux/task_work.h> #include <linux/pagemap.h> #include <linux/io_uring.h> #include <linux/tracehook.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> #include <uapi/linux/io_uring.h> #include "../fs/internal.h" #include "io-wq.h" #define IORING_MAX_ENTRIES 32768 #define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 /* only define max */ #define IORING_MAX_FIXED_FILES (1U << 15) #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) #define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) #define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) #define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) #define IORING_MAX_REG_BUFFERS (1U << 14) #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ IOSQE_BUFFER_SELECT) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS) #define IO_TCTX_REFS_CACHE_NR (1U << 10) struct io_uring { u32 head ____cacheline_aligned_in_smp; u32 tail ____cacheline_aligned_in_smp; }; /* * This data is shared with the application through the mmap at offsets * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING. * * The offsets to the member fields are published through struct * io_sqring_offsets when calling io_uring_setup. */ struct io_rings { /* * Head and tail offsets into the ring; the offsets need to be * masked to get valid indices. * * The kernel controls head of the sq ring and the tail of the cq ring, * and the application controls tail of the sq ring and the head of the * cq ring. */ struct io_uring sq, cq; /* * Bitmasks to apply to head and tail offsets (constant, equals * ring_entries - 1) */ u32 sq_ring_mask, cq_ring_mask; /* Ring sizes (constant, power of 2) */ u32 sq_ring_entries, cq_ring_entries; /* * Number of invalid entries dropped by the kernel due to * invalid index stored in array * * Written by the kernel, shouldn't be modified by the * application (i.e. get number of "new events" by comparing to * cached value). * * After a new SQ head value was read by the application this * counter includes all submissions that were dropped reaching * the new SQ head (and possibly more). */ u32 sq_dropped; /* * Runtime SQ flags * * Written by the kernel, shouldn't be modified by the * application. * * The application needs a full memory barrier before checking * for IORING_SQ_NEED_WAKEUP after updating the sq tail. */ u32 sq_flags; /* * Runtime CQ flags * * Written by the application, shouldn't be modified by the * kernel. */ u32 cq_flags; /* * Number of completion events lost because the queue was full; * this should be avoided by the application by making sure * there are not more requests pending than there is space in * the completion queue. * * Written by the kernel, shouldn't be modified by the * application (i.e. get number of "new events" by comparing to * cached value). * * As completion events come in out of order this counter is not * ordered with any other data. */ u32 cq_overflow; /* * Ring buffer of completion events. * * The kernel writes completion events fresh every time they are * produced, so the application is allowed to modify pending * entries. */ struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp; }; enum io_uring_cmd_flags { IO_URING_F_NONBLOCK = 1, IO_URING_F_COMPLETE_DEFER = 2, }; struct io_mapped_ubuf { u64 ubuf; u64 ubuf_end; unsigned int nr_bvecs; unsigned long acct_pages; struct bio_vec bvec[]; }; struct io_ring_ctx; struct io_overflow_cqe { struct io_uring_cqe cqe; struct list_head list; }; struct io_fixed_file { /* file * with additional FFS_* flags */ unsigned long file_ptr; }; struct io_rsrc_put { struct list_head list; u64 tag; union { void *rsrc; struct file *file; struct io_mapped_ubuf *buf; }; }; struct io_file_table { struct io_fixed_file *files; }; struct io_rsrc_node { struct percpu_ref refs; struct list_head node; struct list_head rsrc_list; struct io_rsrc_data *rsrc_data; struct llist_node llist; bool done; }; typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); struct io_rsrc_data { struct io_ring_ctx *ctx; u64 **tags; unsigned int nr; rsrc_put_fn *do_put; atomic_t refs; struct completion done; bool quiesce; }; struct io_buffer { struct list_head list; __u64 addr; __u32 len; __u16 bid; }; struct io_restriction { DECLARE_BITMAP(register_op, IORING_REGISTER_LAST); DECLARE_BITMAP(sqe_op, IORING_OP_LAST); u8 sqe_flags_allowed; u8 sqe_flags_required; bool registered; }; enum { IO_SQ_THREAD_SHOULD_STOP = 0, IO_SQ_THREAD_SHOULD_PARK, }; struct io_sq_data { refcount_t refs; atomic_t park_pending; struct mutex lock; /* ctx's that are using this sqd */ struct list_head ctx_list; struct task_struct *thread; struct wait_queue_head wait; unsigned sq_thread_idle; int sq_cpu; pid_t task_pid; pid_t task_tgid; unsigned long state; struct completion exited; }; #define IO_COMPL_BATCH 32 #define IO_REQ_CACHE_SIZE 32 #define IO_REQ_ALLOC_BATCH 8 struct io_submit_link { struct io_kiocb *head; struct io_kiocb *last; }; struct io_submit_state { struct blk_plug plug; struct io_submit_link link; /* * io_kiocb alloc cache */ void *reqs[IO_REQ_CACHE_SIZE]; unsigned int free_reqs; bool plug_started; /* * Batch completion logic */ struct io_kiocb *compl_reqs[IO_COMPL_BATCH]; unsigned int compl_nr; /* inline/task_work completion list, under ->uring_lock */ struct list_head free_list; unsigned int ios_left; }; struct io_ring_ctx { /* const or read-mostly hot data */ struct { struct percpu_ref refs; struct io_rings *rings; unsigned int flags; unsigned int compat: 1; unsigned int drain_next: 1; unsigned int eventfd_async: 1; unsigned int restricted: 1; unsigned int off_timeout_used: 1; unsigned int drain_active: 1; } ____cacheline_aligned_in_smp; /* submission data */ struct { struct mutex uring_lock; /* * Ring buffer of indices into array of io_uring_sqe, which is * mmapped by the application using the IORING_OFF_SQES offset. * * This indirection could e.g. be used to assign fixed * io_uring_sqe entries to operations and only submit them to * the queue when needed. * * The kernel modifies neither the indices array nor the entries * array. */ u32 *sq_array; struct io_uring_sqe *sq_sqes; unsigned cached_sq_head; unsigned sq_entries; struct list_head defer_list; /* * Fixed resources fast path, should be accessed only under * uring_lock, and updated through io_uring_register(2) */ struct io_rsrc_node *rsrc_node; struct io_file_table file_table; unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; struct io_submit_state submit_state; struct list_head timeout_list; struct list_head ltimeout_list; struct list_head cq_overflow_list; struct xarray io_buffers; struct xarray personalities; u32 pers_next; unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; /* IRQ completion list, under ->completion_lock */ struct list_head locked_free_list; unsigned int locked_free_nr; const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ struct wait_queue_head sqo_sq_wait; struct list_head sqd_list; unsigned long check_cq_overflow; struct { unsigned cached_cq_tail; unsigned cq_entries; struct eventfd_ctx *cq_ev_fd; struct wait_queue_head poll_wait; struct wait_queue_head cq_wait; unsigned cq_extra; atomic_t cq_timeouts; unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; struct { spinlock_t completion_lock; spinlock_t timeout_lock; /* * ->iopoll_list is protected by the ctx->uring_lock for * io_uring instances that don't use IORING_SETUP_SQPOLL. * For SQPOLL, only the single threaded io_sq_thread() will * manipulate the list, hence no extra locking is needed there. */ struct list_head iopoll_list; struct hlist_head *cancel_hash; unsigned cancel_hash_bits; bool poll_multi_queue; } ____cacheline_aligned_in_smp; struct io_restriction restrictions; /* slow path rsrc auxilary data, used by update/register */ struct { struct io_rsrc_node *rsrc_backup_node; struct io_mapped_ubuf *dummy_ubuf; struct io_rsrc_data *file_data; struct io_rsrc_data *buf_data; struct delayed_work rsrc_put_work; struct llist_head rsrc_put_llist; struct list_head rsrc_ref_list; spinlock_t rsrc_ref_lock; }; /* Keep this last, we don't need it for the fast path */ struct { /* hashed buffered write serialization */ struct io_wq_hash *hash_map; /* Only used for accounting purposes */ struct user_struct *user; struct mm_struct *mm_account; /* ctx exit and cancelation */ struct llist_head fallback_llist; struct delayed_work fallback_work; struct work_struct exit_work; struct list_head tctx_list; struct completion ref_comp; u32 iowq_limits[2]; bool iowq_limits_set; }; }; struct io_uring_task { /* submission side */ int cached_refs; struct xarray xa; struct wait_queue_head wait; const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; struct io_wq_work_list task_list; struct callback_head task_work; bool task_running; }; /* * First field must be the file pointer in all the * iocb unions! See also 'struct kiocb' in <linux/fs.h> */ struct io_poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; int retries; struct wait_queue_entry wait; }; struct io_poll_update { struct file *file; u64 old_user_data; u64 new_user_data; __poll_t events; bool update_events; bool update_user_data; }; struct io_close { struct file *file; int fd; u32 file_slot; }; struct io_timeout_data { struct io_kiocb *req; struct hrtimer timer; struct timespec64 ts; enum hrtimer_mode mode; u32 flags; }; struct io_accept { struct file *file; struct sockaddr __user *addr; int __user *addr_len; int flags; u32 file_slot; unsigned long nofile; }; struct io_sync { struct file *file; loff_t len; loff_t off; int flags; int mode; }; struct io_cancel { struct file *file; u64 addr; }; struct io_timeout { struct file *file; u32 off; u32 target_seq; struct list_head list; /* head of the link, used by linked timeouts only */ struct io_kiocb *head; /* for linked completions */ struct io_kiocb *prev; }; struct io_timeout_rem { struct file *file; u64 addr; /* timeout update */ struct timespec64 ts; u32 flags; bool ltimeout; }; struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; u64 len; }; struct io_connect { struct file *file; struct sockaddr __user *addr; int addr_len; }; struct io_sr_msg { struct file *file; union { struct compat_msghdr __user *umsg_compat; struct user_msghdr __user *umsg; void __user *buf; }; int msg_flags; int bgid; size_t len; size_t done_io; struct io_buffer *kbuf; void __user *msg_control; }; struct io_open { struct file *file; int dfd; u32 file_slot; struct filename *filename; struct open_how how; unsigned long nofile; }; struct io_rsrc_update { struct file *file; u64 arg; u32 nr_args; u32 offset; }; struct io_fadvise { struct file *file; u64 offset; u32 len; u32 advice; }; struct io_madvise { struct file *file; u64 addr; u32 len; u32 advice; }; struct io_epoll { struct file *file; int epfd; int op; int fd; struct epoll_event event; }; struct io_splice { struct file *file_out; loff_t off_out; loff_t off_in; u64 len; int splice_fd_in; unsigned int flags; }; struct io_provide_buf { struct file *file; __u64 addr; __u32 len; __u32 bgid; __u16 nbufs; __u16 bid; }; struct io_statx { struct file *file; int dfd; unsigned int mask; unsigned int flags; const char __user *filename; struct statx __user *buffer; }; struct io_shutdown { struct file *file; int how; }; struct io_rename { struct file *file; int old_dfd; int new_dfd; struct filename *oldpath; struct filename *newpath; int flags; }; struct io_unlink { struct file *file; int dfd; int flags; struct filename *filename; }; struct io_mkdir { struct file *file; int dfd; umode_t mode; struct filename *filename; }; struct io_symlink { struct file *file; int new_dfd; struct filename *oldpath; struct filename *newpath; }; struct io_hardlink { struct file *file; int old_dfd; int new_dfd; struct filename *oldpath; struct filename *newpath; int flags; }; struct io_completion { struct file *file; u32 cflags; }; struct io_async_connect { struct sockaddr_storage address; }; struct io_async_msghdr { struct iovec fast_iov[UIO_FASTIOV]; /* points to an allocated iov, if NULL we use fast_iov instead */ struct iovec *free_iov; struct sockaddr __user *uaddr; struct msghdr msg; struct sockaddr_storage addr; }; struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; const struct iovec *free_iovec; struct iov_iter iter; struct iov_iter_state iter_state; size_t bytes_done; struct wait_page_queue wpq; }; enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT, REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT, REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT, REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, /* first byte is taken by user flags, shift it to not overlap */ REQ_F_FAIL_BIT = 8, REQ_F_INFLIGHT_BIT, REQ_F_CUR_POS_BIT, REQ_F_NOWAIT_BIT, REQ_F_LINK_TIMEOUT_BIT, REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_COMPLETE_INLINE_BIT, REQ_F_REISSUE_BIT, REQ_F_CREDS_BIT, REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, REQ_F_PARTIAL_IO_BIT, /* keep async read/write and isreg together and in order */ REQ_F_NOWAIT_READ_BIT, REQ_F_NOWAIT_WRITE_BIT, REQ_F_ISREG_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, }; enum { /* ctx owns file */ REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT), /* drain existing IO first */ REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT), /* linked sqes */ REQ_F_LINK = BIT(REQ_F_LINK_BIT), /* doesn't sever on completion < 0 */ REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT), /* IOSQE_ASYNC */ REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT), /* IOSQE_BUFFER_SELECT */ REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), /* fail rest of links */ REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), /* on inflight list, should be cancelled and waited on exit reliably */ REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), /* read/write uses file position */ REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT), /* must not punt to workers */ REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT), /* has or had linked timeout */ REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), /* completion is deferred through io_comp_state */ REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), /* caller should reissue async */ REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), /* supports async reads */ REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), /* supports async writes */ REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT), /* regular file */ REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), /* has creds assigned */ REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), /* skip refcounting if not set */ REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), /* there is a linked timeout that has to be armed */ REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), /* request has already done partial IO */ REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT), }; struct async_poll { struct io_poll_iocb poll; struct io_poll_iocb *double_poll; }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked); struct io_task_work { union { struct io_wq_work_node node; struct llist_node fallback_node; }; io_req_tw_func_t func; }; enum { IORING_RSRC_FILE = 0, IORING_RSRC_BUFFER = 1, }; /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can * access the file pointer through any of the sub-structs, * or directly as just 'ki_filp' in this struct. */ struct io_kiocb { union { struct file *file; struct io_rw rw; struct io_poll_iocb poll; struct io_poll_update poll_update; struct io_accept accept; struct io_sync sync; struct io_cancel cancel; struct io_timeout timeout; struct io_timeout_rem timeout_rem; struct io_connect connect; struct io_sr_msg sr_msg; struct io_open open; struct io_close close; struct io_rsrc_update rsrc_update; struct io_fadvise fadvise; struct io_madvise madvise; struct io_epoll epoll; struct io_splice splice; struct io_provide_buf pbuf; struct io_statx statx; struct io_shutdown shutdown; struct io_rename rename; struct io_unlink unlink; struct io_mkdir mkdir; struct io_symlink symlink; struct io_hardlink hardlink; /* use only after cleaning per-op data, see io_clean_op() */ struct io_completion compl; }; /* opcode allocated if it needs to store data for async defer */ void *async_data; u8 opcode; /* polled IO has completed */ u8 iopoll_completed; u16 buf_index; u32 result; struct io_ring_ctx *ctx; unsigned int flags; atomic_t refs; struct task_struct *task; u64 user_data; struct io_kiocb *link; struct percpu_ref *fixed_rsrc_refs; /* used with ctx->iopoll_list with reads/writes */ struct list_head inflight_entry; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; struct async_poll *apoll; struct io_wq_work work; const struct cred *creds; /* store used ubuf, so we can prevent reloading */ struct io_mapped_ubuf *imu; /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ struct io_buffer *kbuf; atomic_t poll_refs; }; struct io_tctx_node { struct list_head ctx_node; struct task_struct *task; struct io_ring_ctx *ctx; }; struct io_defer_entry { struct list_head list; struct io_kiocb *req; u32 seq; }; struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ unsigned unbound_nonreg_file : 1; /* opcode is not supported by this kernel */ unsigned not_supported : 1; /* set if opcode supports polled "wait" */ unsigned pollin : 1; unsigned pollout : 1; /* op supports buffer selection */ unsigned buffer_select : 1; /* do prep async if is going to be punted */ unsigned needs_async_setup : 1; /* should block plug */ unsigned plug : 1; /* size of async data needed, if any */ unsigned short async_size; }; static const struct io_op_def io_op_defs[] = { [IORING_OP_NOP] = {}, [IORING_OP_READV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .needs_async_setup = 1, .plug = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITEV] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .needs_async_setup = 1, .plug = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FSYNC] = { .needs_file = 1, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .plug = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE_FIXED] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_POLL_ADD] = { .needs_file = 1, .unbound_nonreg_file = 1, }, [IORING_OP_POLL_REMOVE] = {}, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, }, [IORING_OP_SENDMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .needs_async_setup = 1, .async_size = sizeof(struct io_async_msghdr), }, [IORING_OP_RECVMSG] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .needs_async_setup = 1, .async_size = sizeof(struct io_async_msghdr), }, [IORING_OP_TIMEOUT] = { .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_TIMEOUT_REMOVE] = { /* used by timeout updates' prep() */ }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, }, [IORING_OP_ASYNC_CANCEL] = {}, [IORING_OP_LINK_TIMEOUT] = { .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_CONNECT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .needs_async_setup = 1, .async_size = sizeof(struct io_async_connect), }, [IORING_OP_FALLOCATE] = { .needs_file = 1, }, [IORING_OP_OPENAT] = {}, [IORING_OP_CLOSE] = {}, [IORING_OP_FILES_UPDATE] = {}, [IORING_OP_STATX] = {}, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .plug = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FADVISE] = { .needs_file = 1, }, [IORING_OP_MADVISE] = {}, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, }, [IORING_OP_OPENAT2] = { }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, }, [IORING_OP_PROVIDE_BUFFERS] = {}, [IORING_OP_REMOVE_BUFFERS] = {}, [IORING_OP_TEE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, }, [IORING_OP_SHUTDOWN] = { .needs_file = 1, }, [IORING_OP_RENAMEAT] = {}, [IORING_OP_UNLINKAT] = {}, }; /* requests with any of those set should undergo io_disarm_next() */ #define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL) static bool io_disarm_next(struct io_kiocb *req); static void io_uring_del_tctx_node(unsigned long index); static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all); static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags); static void io_put_req(struct io_kiocb *req); static void io_put_req_deferred(struct io_kiocb *req); static void io_dismantle_req(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_ring_ctx *ctx, struct io_kiocb *req, int fd, bool fixed, unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); static void io_req_task_queue(struct io_kiocb *req); static void io_submit_flush_completions(struct io_ring_ctx *ctx); static int io_req_prep_async(struct io_kiocb *req); static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index); static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); static struct kmem_cache *req_cachep; static const struct file_operations io_uring_fops; static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) { if (!*locked) { mutex_lock(&ctx->uring_lock); *locked = true; } } #define io_for_each_link(pos, head) \ for (pos = (head); pos; pos = pos->link) /* * Shamelessly stolen from the mm implementation of page reference checking, * see commit f958d7b528b1 for details. */ #define req_ref_zero_or_close_to_overflow(req) \ ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u) static inline bool req_ref_inc_not_zero(struct io_kiocb *req) { WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); return atomic_inc_not_zero(&req->refs); } static inline bool req_ref_put_and_test(struct io_kiocb *req) { if (likely(!(req->flags & REQ_F_REFCOUNT))) return true; WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); return atomic_dec_and_test(&req->refs); } static inline void req_ref_get(struct io_kiocb *req) { WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT)); WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); atomic_inc(&req->refs); } static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) { if (!(req->flags & REQ_F_REFCOUNT)) { req->flags |= REQ_F_REFCOUNT; atomic_set(&req->refs, nr); } } static inline void io_req_set_refcount(struct io_kiocb *req) { __io_req_set_refcount(req, 1); } static inline void io_req_set_rsrc_node(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; percpu_ref_get(req->fixed_rsrc_refs); } } static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) { bool got = percpu_ref_tryget(ref); /* already at zero, wait for ->release() */ if (!got) wait_for_completion(compl); percpu_ref_resurrect(ref); if (got) percpu_ref_put(ref); } static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { struct io_kiocb *req; if (task && head->task != task) return false; if (cancel_all) return true; io_for_each_link(req, head) { if (req->flags & REQ_F_INFLIGHT) return true; } return false; } static bool io_match_linked(struct io_kiocb *head) { struct io_kiocb *req; io_for_each_link(req, head) { if (req->flags & REQ_F_INFLIGHT) return true; } return false; } /* * As io_match_task() but protected against racing with linked timeouts. * User must not hold timeout_lock. */ static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { bool matched; if (task && head->task != task) return false; if (cancel_all) return true; if (head->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = head->ctx; /* protect against races with linked timeouts */ spin_lock_irq(&ctx->timeout_lock); matched = io_match_linked(head); spin_unlock_irq(&ctx->timeout_lock); } else { matched = io_match_linked(head); } return matched; } static inline void req_set_fail(struct io_kiocb *req) { req->flags |= REQ_F_FAIL; } static inline void req_fail_link_node(struct io_kiocb *req, int res) { req_set_fail(req); req->result = res; } static void io_ring_ctx_ref_free(struct percpu_ref *ref) { struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); complete(&ctx->ref_comp); } static inline bool io_is_timeout_noseq(struct io_kiocb *req) { return !req->timeout.off; } static void io_fallback_req_func(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, fallback_work.work); struct llist_node *node = llist_del_all(&ctx->fallback_llist); struct io_kiocb *req, *tmp; bool locked = false; percpu_ref_get(&ctx->refs); llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node) req->io_task_work.func(req, &locked); if (locked) { if (ctx->submit_state.compl_nr) io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); } percpu_ref_put(&ctx->refs); } static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; int hash_bits; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; /* * Use 5 bits less than the max cq entries, that should give us around * 32 entries per hash list if totally full and uniformly spread. */ hash_bits = ilog2(p->cq_entries); hash_bits -= 5; if (hash_bits <= 0) hash_bits = 1; ctx->cancel_hash_bits = hash_bits; ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head), GFP_KERNEL); if (!ctx->cancel_hash) goto err; __hash_init(ctx->cancel_hash, 1U << hash_bits); ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL); if (!ctx->dummy_ubuf) goto err; /* set invalid range, so io_import_fixed() fails meeting it */ ctx->dummy_ubuf->ubuf = -1UL; if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) goto err; ctx->flags = p->flags; init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); init_waitqueue_head(&ctx->poll_wait); INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->ref_comp); xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->cq_wait); spin_lock_init(&ctx->completion_lock); spin_lock_init(&ctx->timeout_lock); INIT_LIST_HEAD(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); INIT_LIST_HEAD(&ctx->ltimeout_list); spin_lock_init(&ctx->rsrc_ref_lock); INIT_LIST_HEAD(&ctx->rsrc_ref_list); INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); init_llist_head(&ctx->rsrc_put_llist); INIT_LIST_HEAD(&ctx->tctx_list); INIT_LIST_HEAD(&ctx->submit_state.free_list); INIT_LIST_HEAD(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); return ctx; err: kfree(ctx->dummy_ubuf); kfree(ctx->cancel_hash); kfree(ctx); return NULL; } static void io_account_cq_overflow(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); ctx->cq_extra--; } static bool req_need_defer(struct io_kiocb *req, u32 seq) { if (unlikely(req->flags & REQ_F_IO_DRAIN)) { struct io_ring_ctx *ctx = req->ctx; return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; } return false; } #define FFS_ASYNC_READ 0x1UL #define FFS_ASYNC_WRITE 0x2UL #ifdef CONFIG_64BIT #define FFS_ISREG 0x4UL #else #define FFS_ISREG 0x0UL #endif #define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG) static inline bool io_req_ffs_set(struct io_kiocb *req) { return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE); } static void io_req_track_inflight(struct io_kiocb *req) { if (!(req->flags & REQ_F_INFLIGHT)) { req->flags |= REQ_F_INFLIGHT; atomic_inc(&req->task->io_uring->inflight_tracked); } } static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) return NULL; req->flags &= ~REQ_F_ARM_LTIMEOUT; req->flags |= REQ_F_LINK_TIMEOUT; /* linked timeouts should have two refs once prep'ed */ io_req_set_refcount(req); __io_req_set_refcount(req->link, 2); return req->link; } static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) { if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) return NULL; return __io_prep_linked_timeout(req); } static void io_prep_async_work(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; if (!(req->flags & REQ_F_CREDS)) { req->flags |= REQ_F_CREDS; req->creds = get_current_cred(); } req->work.list.next = NULL; req->work.flags = 0; if (req->flags & REQ_F_FORCE_ASYNC) req->work.flags |= IO_WQ_WORK_CONCURRENT; if (req->flags & REQ_F_ISREG) { if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } } static void io_prep_async_link(struct io_kiocb *req) { struct io_kiocb *cur; if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); } } static void io_queue_async_work(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->task->io_uring; /* must not take the lock, NULL it as a precaution */ locked = NULL; BUG_ON(!tctx); BUG_ON(!tctx->io_wq); /* init ->work of the whole link before punting */ io_prep_async_link(req); /* * Not expected to happen, but if we do have a bug where this _can_ * happen, catch it here and ensure the request is marked as * canceled. That will make io-wq go through the usual work cancel * procedure rather than attempt to run this request (or create a new * worker for it). */ if (WARN_ON_ONCE(!same_thread_group(req->task, current))) req->work.flags |= IO_WQ_WORK_CANCEL; trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, &req->work, req->flags); io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); } static void io_kill_timeout(struct io_kiocb *req, int status) __must_hold(&req->ctx->completion_lock) __must_hold(&req->ctx->timeout_lock) { struct io_timeout_data *io = req->async_data; if (hrtimer_try_to_cancel(&io->timer) != -1) { if (status) req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); io_fill_cqe_req(req, status, 0); io_put_req_deferred(req); } } static void io_queue_deferred(struct io_ring_ctx *ctx) { lockdep_assert_held(&ctx->completion_lock); while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); if (req_need_defer(de->req, de->seq)) break; list_del_init(&de->list); io_req_task_queue(de->req); kfree(de); } } static void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); struct io_kiocb *req, *tmp; spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; if (io_is_timeout_noseq(req)) break; /* * Since seq can easily wrap around over time, subtract * the last seq at which timeouts were flushed before comparing. * Assuming not more than 2^31-1 events have happened since, * these subtractions won't have wrapped, so we can check if * target is in [last_seq, current_seq] by comparing the two. */ events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush; events_got = seq - ctx->cq_last_tm_flush; if (events_got < events_needed) break; io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; spin_unlock_irq(&ctx->timeout_lock); } static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) { if (ctx->off_timeout_used) io_flush_timeouts(ctx); if (ctx->drain_active) io_queue_deferred(ctx); } static inline bool io_commit_needs_flush(struct io_ring_ctx *ctx) { return ctx->off_timeout_used || ctx->drain_active; } static inline void __io_commit_cqring(struct io_ring_ctx *ctx) { /* order cqe stores with ring update */ smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); } static inline void io_commit_cqring(struct io_ring_ctx *ctx) { if (unlikely(io_commit_needs_flush(ctx))) __io_commit_cqring_flush(ctx); __io_commit_cqring(ctx); } static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; } static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) { return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); } static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; unsigned tail, mask = ctx->cq_entries - 1; /* * writes to the cq entry need to come after reading head; the * control dependency is enough as we're using WRITE_ONCE to * fill the cq entry */ if (__io_cqring_events(ctx) == ctx->cq_entries) return NULL; tail = ctx->cached_cq_tail++; return &rings->cqes[tail & mask]; } static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) { if (likely(!ctx->cq_ev_fd)) return false; if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED) return false; return !ctx->eventfd_async || io_wq_current_is_worker(); } /* * This should only get called when at least one event has been posted. * Some applications rely on the eventfd notification count only changing * IFF a new CQE has been added to the CQ ring. There's no depedency on * 1:1 relationship between how many times this function is called (and * hence the eventfd count) and number of CQEs posted to the CQ ring. */ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) { /* * wake_up_all() may seem excessive, but io_wake_function() and * io_should_wake() handle the termination of the loop and only * wake as many waiters as we need to. */ if (wq_has_sleeper(&ctx->cq_wait)) __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); if (waitqueue_active(&ctx->poll_wait)) __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) { /* see waitqueue_active() comment */ smp_mb(); if (ctx->flags & IORING_SETUP_SQPOLL) { if (waitqueue_active(&ctx->cq_wait)) __wake_up(&ctx->cq_wait, TASK_NORMAL, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } if (io_should_trigger_evfd(ctx)) eventfd_signal_mask(ctx->cq_ev_fd, 1, EPOLL_URING_WAKE); if (waitqueue_active(&ctx->poll_wait)) __wake_up(&ctx->poll_wait, TASK_INTERRUPTIBLE, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN)); } /* Returns true if there are no backlogged entries after the flush */ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { bool all_flushed, posted; if (!force && __io_cqring_events(ctx) == ctx->cq_entries) return false; posted = false; spin_lock(&ctx->completion_lock); while (!list_empty(&ctx->cq_overflow_list)) { struct io_uring_cqe *cqe = io_get_cqe(ctx); struct io_overflow_cqe *ocqe; if (!cqe && !force) break; ocqe = list_first_entry(&ctx->cq_overflow_list, struct io_overflow_cqe, list); if (cqe) memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); else io_account_cq_overflow(ctx); posted = true; list_del(&ocqe->list); kfree(ocqe); } all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { clear_bit(0, &ctx->check_cq_overflow); WRITE_ONCE(ctx->rings->sq_flags, ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); } if (posted) io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); return all_flushed; } static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx) { bool ret = true; if (test_bit(0, &ctx->check_cq_overflow)) { /* iopoll syncs against uring_lock, not completion_lock */ if (ctx->flags & IORING_SETUP_IOPOLL) mutex_lock(&ctx->uring_lock); ret = __io_cqring_overflow_flush(ctx, false); if (ctx->flags & IORING_SETUP_IOPOLL) mutex_unlock(&ctx->uring_lock); } return ret; } /* must to be called somewhat shortly after putting a request */ static inline void io_put_task(struct task_struct *task, int nr) { struct io_uring_task *tctx = task->io_uring; if (likely(task == current)) { tctx->cached_refs += nr; } else { percpu_counter_sub(&tctx->inflight, nr); if (unlikely(atomic_read(&tctx->in_idle))) wake_up(&tctx->wait); put_task_struct_many(task, nr); } } static void io_task_refs_refill(struct io_uring_task *tctx) { unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; percpu_counter_add(&tctx->inflight, refill); refcount_add(refill, ¤t->usage); tctx->cached_refs += refill; } static inline void io_get_task_refs(int nr) { struct io_uring_task *tctx = current->io_uring; tctx->cached_refs -= nr; if (unlikely(tctx->cached_refs < 0)) io_task_refs_refill(tctx); } static __cold void io_uring_drop_tctx_refs(struct task_struct *task) { struct io_uring_task *tctx = task->io_uring; unsigned int refs = tctx->cached_refs; if (refs) { tctx->cached_refs = 0; percpu_counter_sub(&tctx->inflight, refs); put_task_struct_many(task, refs); } } static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { struct io_overflow_cqe *ocqe; ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT); if (!ocqe) { /* * If we're in ring overflow flush mode, or in task cancel mode, * or cannot allocate an overflow entry, then we need to drop it * on the floor. */ io_account_cq_overflow(ctx); return false; } if (list_empty(&ctx->cq_overflow_list)) { set_bit(0, &ctx->check_cq_overflow); WRITE_ONCE(ctx->rings->sq_flags, ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); } ocqe->cqe.user_data = user_data; ocqe->cqe.res = res; ocqe->cqe.flags = cflags; list_add_tail(&ocqe->list, &ctx->cq_overflow_list); return true; } static inline bool __io_fill_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { struct io_uring_cqe *cqe; trace_io_uring_complete(ctx, user_data, res, cflags); /* * If we can't get a cq entry, userspace overflowed the * submission (by quite a lot). Increment the overflow count in * the ring. */ cqe = io_get_cqe(ctx); if (likely(cqe)) { WRITE_ONCE(cqe->user_data, user_data); WRITE_ONCE(cqe->res, res); WRITE_ONCE(cqe->flags, cflags); return true; } return io_cqring_event_overflow(ctx, user_data, res, cflags); } static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags) { __io_fill_cqe(req->ctx, req->user_data, res, cflags); } static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags) { ctx->cq_extra++; return __io_fill_cqe(ctx, user_data, res, cflags); } static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags) { struct io_ring_ctx *ctx = req->ctx; spin_lock(&ctx->completion_lock); __io_fill_cqe(ctx, req->user_data, res, cflags); /* * If we're the last reference to this request, add to our locked * free_list cache. */ if (req_ref_put_and_test(req)) { if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { if (req->flags & IO_DISARM_MASK) io_disarm_next(req); if (req->link) { io_req_task_queue(req->link); req->link = NULL; } } io_dismantle_req(req); io_put_task(req->task, 1); list_add(&req->inflight_entry, &ctx->locked_free_list); ctx->locked_free_nr++; } else { if (!percpu_ref_tryget(&ctx->refs)) req = NULL; } io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (req) { io_cqring_ev_posted(ctx); percpu_ref_put(&ctx->refs); } } static inline bool io_req_needs_clean(struct io_kiocb *req) { return req->flags & IO_REQ_CLEAN_FLAGS; } static inline void io_req_complete_state(struct io_kiocb *req, s32 res, u32 cflags) { if (io_req_needs_clean(req)) io_clean_op(req); req->result = res; req->compl.cflags = cflags; req->flags |= REQ_F_COMPLETE_INLINE; } static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, s32 res, u32 cflags) { if (issue_flags & IO_URING_F_COMPLETE_DEFER) io_req_complete_state(req, res, cflags); else io_req_complete_post(req, res, cflags); } static inline void io_req_complete(struct io_kiocb *req, s32 res) { __io_req_complete(req, 0, res, 0); } static void io_req_complete_failed(struct io_kiocb *req, s32 res) { req_set_fail(req); io_req_complete_post(req, res, 0); } static void io_req_complete_fail_submit(struct io_kiocb *req) { /* * We don't submit, fail them all, for that replace hardlinks with * normal links. Extra REQ_F_LINK is tolerated. */ req->flags &= ~REQ_F_HARDLINK; req->flags |= REQ_F_LINK; io_req_complete_failed(req, req->result); } /* * Don't initialise the fields below on every allocation, but do that in * advance and keep them valid across allocations. */ static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx) { req->ctx = ctx; req->link = NULL; req->async_data = NULL; /* not necessary, but safer to zero */ req->result = 0; } static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, struct io_submit_state *state) { spin_lock(&ctx->completion_lock); list_splice_init(&ctx->locked_free_list, &state->free_list); ctx->locked_free_nr = 0; spin_unlock(&ctx->completion_lock); } /* Returns true IFF there are requests in the cache */ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; int nr; /* * If we have more than a batch's worth of requests in our IRQ side * locked cache, grab the lock and move them over to our submission * side cache. */ if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) io_flush_cached_locked_reqs(ctx, state); nr = state->free_reqs; while (!list_empty(&state->free_list)) { struct io_kiocb *req = list_first_entry(&state->free_list, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); state->reqs[nr++] = req; if (nr == ARRAY_SIZE(state->reqs)) break; } state->free_reqs = nr; return nr != 0; } /* * A request might get retired back into the request caches even before opcode * handlers and io_issue_sqe() are done with it, e.g. inline completion path. * Because of that, io_alloc_req() should be called only under ->uring_lock * and with extra caution to not get a request that is still worked on. */ static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { struct io_submit_state *state = &ctx->submit_state; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; int ret, i; BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH); if (likely(state->free_reqs || io_flush_cached_reqs(ctx))) goto got_req; ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH, state->reqs); /* * Bulk alloc is all-or-nothing. If we fail to get a batch, * retry single alloc to be on the safe side. */ if (unlikely(ret <= 0)) { state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); if (!state->reqs[0]) return NULL; ret = 1; } for (i = 0; i < ret; i++) io_preinit_req(state->reqs[i], ctx); state->free_reqs = ret; got_req: state->free_reqs--; return state->reqs[state->free_reqs]; } static inline void io_put_file(struct file *file) { if (file) fput(file); } static void io_dismantle_req(struct io_kiocb *req) { unsigned int flags = req->flags; if (io_req_needs_clean(req)) io_clean_op(req); if (!(flags & REQ_F_FIXED_FILE)) io_put_file(req->file); if (req->fixed_rsrc_refs) percpu_ref_put(req->fixed_rsrc_refs); if (req->async_data) { kfree(req->async_data); req->async_data = NULL; } } static void __io_free_req(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; io_dismantle_req(req); io_put_task(req->task, 1); spin_lock(&ctx->completion_lock); list_add(&req->inflight_entry, &ctx->locked_free_list); ctx->locked_free_nr++; spin_unlock(&ctx->completion_lock); percpu_ref_put(&ctx->refs); } static inline void io_remove_next_linked(struct io_kiocb *req) { struct io_kiocb *nxt = req->link; req->link = nxt->link; nxt->link = NULL; } static bool io_kill_linked_timeout(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) __must_hold(&req->ctx->timeout_lock) { struct io_kiocb *link = req->link; if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { struct io_timeout_data *io = link->async_data; io_remove_next_linked(req); link->timeout.head = NULL; if (hrtimer_try_to_cancel(&io->timer) != -1) { list_del(&link->timeout.list); io_fill_cqe_req(link, -ECANCELED, 0); io_put_req_deferred(link); return true; } } return false; } static void io_fail_links(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) { struct io_kiocb *nxt, *link = req->link; req->link = NULL; while (link) { long res = -ECANCELED; if (link->flags & REQ_F_FAIL) res = link->result; nxt = link->link; link->link = NULL; trace_io_uring_fail_link(req, link); io_fill_cqe_req(link, res, 0); io_put_req_deferred(link); link = nxt; } } static bool io_disarm_next(struct io_kiocb *req) __must_hold(&req->ctx->completion_lock) { bool posted = false; if (req->flags & REQ_F_ARM_LTIMEOUT) { struct io_kiocb *link = req->link; req->flags &= ~REQ_F_ARM_LTIMEOUT; if (link && link->opcode == IORING_OP_LINK_TIMEOUT) { io_remove_next_linked(req); io_fill_cqe_req(link, -ECANCELED, 0); io_put_req_deferred(link); posted = true; } } else if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; spin_lock_irq(&ctx->timeout_lock); posted = io_kill_linked_timeout(req); spin_unlock_irq(&ctx->timeout_lock); } if (unlikely((req->flags & REQ_F_FAIL) && !(req->flags & REQ_F_HARDLINK))) { posted |= (req->link != NULL); io_fail_links(req); } return posted; } static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt; /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other * dependencies to the next request. In case of failure, fail the rest * of the chain. */ if (req->flags & IO_DISARM_MASK) { struct io_ring_ctx *ctx = req->ctx; bool posted; spin_lock(&ctx->completion_lock); posted = io_disarm_next(req); if (posted) io_commit_cqring(req->ctx); spin_unlock(&ctx->completion_lock); if (posted) io_cqring_ev_posted(ctx); } nxt = req->link; req->link = NULL; return nxt; } static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) return NULL; return __io_req_find_next(req); } static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) { if (!ctx) return; if (*locked) { if (ctx->submit_state.compl_nr) io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); *locked = false; } percpu_ref_put(&ctx->refs); } static void tctx_task_work(struct callback_head *cb) { bool locked = false; struct io_ring_ctx *ctx = NULL; struct io_uring_task *tctx = container_of(cb, struct io_uring_task, task_work); while (1) { struct io_wq_work_node *node; if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr) io_submit_flush_completions(ctx); spin_lock_irq(&tctx->task_lock); node = tctx->task_list.first; INIT_WQ_LIST(&tctx->task_list); if (!node) tctx->task_running = false; spin_unlock_irq(&tctx->task_lock); if (!node) break; do { struct io_wq_work_node *next = node->next; struct io_kiocb *req = container_of(node, struct io_kiocb, io_task_work.node); if (req->ctx != ctx) { ctx_flush_and_put(ctx, &locked); ctx = req->ctx; /* if not contended, grab and improve batching */ locked = mutex_trylock(&ctx->uring_lock); percpu_ref_get(&ctx->refs); } req->io_task_work.func(req, &locked); node = next; if (unlikely(need_resched())) { ctx_flush_and_put(ctx, &locked); ctx = NULL; cond_resched(); } } while (node); } ctx_flush_and_put(ctx, &locked); /* relaxed read is enough as only the task itself sets ->in_idle */ if (unlikely(atomic_read(&tctx->in_idle))) io_uring_drop_tctx_refs(current); } static void io_req_task_work_add(struct io_kiocb *req) { struct task_struct *tsk = req->task; struct io_uring_task *tctx = tsk->io_uring; enum task_work_notify_mode notify; struct io_wq_work_node *node; unsigned long flags; bool running; WARN_ON_ONCE(!tctx); spin_lock_irqsave(&tctx->task_lock, flags); wq_list_add_tail(&req->io_task_work.node, &tctx->task_list); running = tctx->task_running; if (!running) tctx->task_running = true; spin_unlock_irqrestore(&tctx->task_lock, flags); /* task_work already pending, we're done */ if (running) return; /* * SQPOLL kernel thread doesn't need notification, just a wakeup. For * all other cases, use TWA_SIGNAL unconditionally to ensure we're * processing task_work. There's no reliable way to tell if TWA_RESUME * will do the job. */ notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; if (!task_work_add(tsk, &tctx->task_work, notify)) { wake_up_process(tsk); return; } spin_lock_irqsave(&tctx->task_lock, flags); tctx->task_running = false; node = tctx->task_list.first; INIT_WQ_LIST(&tctx->task_list); spin_unlock_irqrestore(&tctx->task_lock, flags); while (node) { req = container_of(node, struct io_kiocb, io_task_work.node); node = node->next; if (llist_add(&req->io_task_work.fallback_node, &req->ctx->fallback_llist)) schedule_delayed_work(&req->ctx->fallback_work, 1); } } static void io_req_task_cancel(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; /* not needed for normal modes, but SQPOLL depends on it */ io_tw_lock(ctx, locked); io_req_complete_failed(req, req->result); } static void io_req_task_submit(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; io_tw_lock(ctx, locked); /* req->task == current here, checking PF_EXITING is safe */ if (likely(!(req->task->flags & PF_EXITING))) __io_queue_sqe(req); else io_req_complete_failed(req, -EFAULT); } static void io_req_task_queue_fail(struct io_kiocb *req, int ret) { req->result = ret; req->io_task_work.func = io_req_task_cancel; io_req_task_work_add(req); } static void io_req_task_queue(struct io_kiocb *req) { req->io_task_work.func = io_req_task_submit; io_req_task_work_add(req); } static void io_req_task_queue_reissue(struct io_kiocb *req) { req->io_task_work.func = io_queue_async_work; io_req_task_work_add(req); } static inline void io_queue_next(struct io_kiocb *req) { struct io_kiocb *nxt = io_req_find_next(req); if (nxt) io_req_task_queue(nxt); } static void io_free_req(struct io_kiocb *req) { io_queue_next(req); __io_free_req(req); } static void io_free_req_work(struct io_kiocb *req, bool *locked) { io_free_req(req); } struct req_batch { struct task_struct *task; int task_refs; int ctx_refs; }; static inline void io_init_req_batch(struct req_batch *rb) { rb->task_refs = 0; rb->ctx_refs = 0; rb->task = NULL; } static void io_req_free_batch_finish(struct io_ring_ctx *ctx, struct req_batch *rb) { if (rb->ctx_refs) percpu_ref_put_many(&ctx->refs, rb->ctx_refs); if (rb->task) io_put_task(rb->task, rb->task_refs); } static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, struct io_submit_state *state) { io_queue_next(req); io_dismantle_req(req); if (req->task != rb->task) { if (rb->task) io_put_task(rb->task, rb->task_refs); rb->task = req->task; rb->task_refs = 0; } rb->task_refs++; rb->ctx_refs++; if (state->free_reqs != ARRAY_SIZE(state->reqs)) state->reqs[state->free_reqs++] = req; else list_add(&req->inflight_entry, &state->free_list); } static void io_submit_flush_completions(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { struct io_submit_state *state = &ctx->submit_state; int i, nr = state->compl_nr; struct req_batch rb; spin_lock(&ctx->completion_lock); for (i = 0; i < nr; i++) { struct io_kiocb *req = state->compl_reqs[i]; __io_fill_cqe(ctx, req->user_data, req->result, req->compl.cflags); } io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); io_init_req_batch(&rb); for (i = 0; i < nr; i++) { struct io_kiocb *req = state->compl_reqs[i]; if (req_ref_put_and_test(req)) io_req_free_batch(&rb, req, &ctx->submit_state); } io_req_free_batch_finish(ctx, &rb); state->compl_nr = 0; } /* * Drop reference to request, return next in chain (if there is one) if this * was the last reference to this request. */ static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt = NULL; if (req_ref_put_and_test(req)) { nxt = io_req_find_next(req); __io_free_req(req); } return nxt; } static inline void io_put_req(struct io_kiocb *req) { if (req_ref_put_and_test(req)) io_free_req(req); } static inline void io_put_req_deferred(struct io_kiocb *req) { if (req_ref_put_and_test(req)) { req->io_task_work.func = io_free_req_work; io_req_task_work_add(req); } } static unsigned io_cqring_events(struct io_ring_ctx *ctx) { /* See comment at the top of this file */ smp_rmb(); return __io_cqring_events(ctx); } static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; /* make sure SQ entry isn't read before tail */ return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head; } static unsigned int io_put_kbuf(struct io_kiocb *req, struct io_buffer *kbuf) { unsigned int cflags; cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT; cflags |= IORING_CQE_F_BUFFER; req->flags &= ~REQ_F_BUFFER_SELECTED; kfree(kbuf); return cflags; } static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) { struct io_buffer *kbuf; if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) return 0; kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; return io_put_kbuf(req, kbuf); } static inline bool io_run_task_work(void) { /* * PF_IO_WORKER never returns to userspace, so check here if we have * notify work that needs processing. */ if (current->flags & PF_IO_WORKER && test_thread_flag(TIF_NOTIFY_RESUME)) { __set_current_state(TASK_RUNNING); tracehook_notify_resume(NULL); } if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); tracehook_notify_signal(); return true; } return false; } /* * Find and free completed poll iocbs */ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, struct list_head *done) { struct req_batch rb; struct io_kiocb *req; /* order with ->result store in io_complete_rw_iopoll() */ smp_rmb(); io_init_req_batch(&rb); while (!list_empty(done)) { struct io_uring_cqe *cqe; unsigned cflags; req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); cflags = io_put_rw_kbuf(req); (*nr_events)++; cqe = io_get_cqe(ctx); if (cqe) { WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, req->result); WRITE_ONCE(cqe->flags, cflags); } else { spin_lock(&ctx->completion_lock); io_cqring_event_overflow(ctx, req->user_data, req->result, cflags); spin_unlock(&ctx->completion_lock); } if (req_ref_put_and_test(req)) io_req_free_batch(&rb, req, &ctx->submit_state); } if (io_commit_needs_flush(ctx)) { spin_lock(&ctx->completion_lock); __io_commit_cqring_flush(ctx); spin_unlock(&ctx->completion_lock); } __io_commit_cqring(ctx); io_cqring_ev_posted_iopoll(ctx); io_req_free_batch_finish(ctx, &rb); } static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, long min) { struct io_kiocb *req, *tmp; LIST_HEAD(done); bool spin; /* * Only spin for completions if we don't have multiple devices hanging * off our complete list, and we're under the requested amount. */ spin = !ctx->poll_multi_queue && *nr_events < min; list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { struct kiocb *kiocb = &req->rw.kiocb; int ret; /* * Move completed and retryable entries to our local lists. * If we find a request that requires polling, break out * and complete those lists first, if we have entries there. */ if (READ_ONCE(req->iopoll_completed)) { list_move_tail(&req->inflight_entry, &done); continue; } if (!list_empty(&done)) break; ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); if (unlikely(ret < 0)) return ret; else if (ret) spin = false; /* iopoll may have completed current req */ if (READ_ONCE(req->iopoll_completed)) list_move_tail(&req->inflight_entry, &done); } if (!list_empty(&done)) io_iopoll_complete(ctx, nr_events, &done); return 0; } /* * We can't just wait for polled events to come to us, we have to actively * find and complete them. */ static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) { if (!(ctx->flags & IORING_SETUP_IOPOLL)) return; mutex_lock(&ctx->uring_lock); while (!list_empty(&ctx->iopoll_list)) { unsigned int nr_events = 0; io_do_iopoll(ctx, &nr_events, 0); /* let it sleep and repeat later if can't complete a request */ if (nr_events == 0) break; /* * Ensure we allow local-to-the-cpu processing to take place, * in this case we need to ensure that we reap all events. * Also let task_work, etc. to progress by releasing the mutex */ if (need_resched()) { mutex_unlock(&ctx->uring_lock); cond_resched(); mutex_lock(&ctx->uring_lock); } } mutex_unlock(&ctx->uring_lock); } static int io_iopoll_check(struct io_ring_ctx *ctx, long min) { unsigned int nr_events = 0; int ret = 0; /* * We disallow the app entering submit/complete with polling, but we * still need to lock the ring to prevent racing with polled issue * that got punted to a workqueue. */ mutex_lock(&ctx->uring_lock); /* * Don't enter poll loop if we already have events pending. * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ if (test_bit(0, &ctx->check_cq_overflow)) __io_cqring_overflow_flush(ctx, false); if (io_cqring_events(ctx)) goto out; do { /* * If a submit got punted to a workqueue, we can have the * application entering polling for a command before it gets * issued. That app will hold the uring_lock for the duration * of the poll right here, so we need to take a breather every * now and then to ensure that the issue has a chance to add * the poll to the issued list. Otherwise we can spin here * forever, while the workqueue is stuck trying to acquire the * very same mutex. */ if (list_empty(&ctx->iopoll_list)) { u32 tail = ctx->cached_cq_tail; mutex_unlock(&ctx->uring_lock); io_run_task_work(); mutex_lock(&ctx->uring_lock); /* some requests don't go through iopoll_list */ if (tail != ctx->cached_cq_tail || list_empty(&ctx->iopoll_list)) break; } ret = io_do_iopoll(ctx, &nr_events, min); if (task_sigpending(current)) { ret = -EINTR; goto out; } } while (!ret && nr_events < min && !need_resched()); out: mutex_unlock(&ctx->uring_lock); return ret; } static void kiocb_end_write(struct io_kiocb *req) { /* * Tell lockdep we inherited freeze protection from submission * thread. */ if (req->flags & REQ_F_ISREG) { struct super_block *sb = file_inode(req->file)->i_sb; __sb_writers_acquired(sb, SB_FREEZE_WRITE); sb_end_write(sb); } } #ifdef CONFIG_BLOCK static bool io_resubmit_prep(struct io_kiocb *req) { struct io_async_rw *rw = req->async_data; if (!rw) return !io_req_prep_async(req); iov_iter_restore(&rw->iter, &rw->iter_state); return true; } static bool io_rw_should_reissue(struct io_kiocb *req) { umode_t mode = file_inode(req->file)->i_mode; struct io_ring_ctx *ctx = req->ctx; if (!S_ISBLK(mode) && !S_ISREG(mode)) return false; if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() && !(ctx->flags & IORING_SETUP_IOPOLL))) return false; /* * If ref is dying, we might be running poll reap from the exit work. * Don't attempt to reissue from that path, just let it fail with * -EAGAIN. */ if (percpu_ref_is_dying(&ctx->refs)) return false; /* * Play it safe and assume not safe to re-import and reissue if we're * not in the original thread group (or in task context). */ if (!same_thread_group(req->task, current) || !in_task()) return false; return true; } #else static bool io_resubmit_prep(struct io_kiocb *req) { return false; } static bool io_rw_should_reissue(struct io_kiocb *req) { return false; } #endif /* * Trigger the notifications after having done some IO, and finish the write * accounting, if any. */ static void io_req_io_end(struct io_kiocb *req) { struct io_rw *rw = &req->rw; if (rw->kiocb.ki_flags & IOCB_WRITE) { kiocb_end_write(req); fsnotify_modify(req->file); } else { fsnotify_access(req->file); } } static bool __io_complete_rw_common(struct io_kiocb *req, long res) { if (res != req->result) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { /* * Reissue will start accounting again, finish the * current cycle. */ io_req_io_end(req); req->flags |= REQ_F_REISSUE; return true; } req_set_fail(req); req->result = res; } return false; } static inline int io_fixup_rw_res(struct io_kiocb *req, long res) { struct io_async_rw *io = req->async_data; /* add previously done IO, if any */ if (io && io->bytes_done > 0) { if (res < 0) res = io->bytes_done; else res += io->bytes_done; } return res; } static void io_req_task_complete(struct io_kiocb *req, bool *locked) { unsigned int cflags = io_put_rw_kbuf(req); int res = req->result; if (*locked) { struct io_ring_ctx *ctx = req->ctx; struct io_submit_state *state = &ctx->submit_state; io_req_complete_state(req, res, cflags); state->compl_reqs[state->compl_nr++] = req; if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) io_submit_flush_completions(ctx); } else { io_req_complete_post(req, res, cflags); } } static void io_req_rw_complete(struct io_kiocb *req, bool *locked) { io_req_io_end(req); io_req_task_complete(req, locked); } static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (__io_complete_rw_common(req, res)) return; req->result = io_fixup_rw_res(req, res); req->io_task_work.func = io_req_rw_complete; io_req_task_work_add(req); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); if (unlikely(res != req->result)) { if (res == -EAGAIN && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE; return; } } WRITE_ONCE(req->result, res); /* order with io_iopoll_complete() checking ->result */ smp_wmb(); WRITE_ONCE(req->iopoll_completed, 1); } /* * After the iocb has been issued, it's safe to be found on the poll list. * Adding the kiocb to the list AFTER submission ensures that we don't * find it from a io_do_iopoll() thread before the issuer is done * accessing the kiocb cookie. */ static void io_iopoll_req_issued(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; const bool in_async = io_wq_current_is_worker(); /* workqueue context doesn't hold uring_lock, grab it now */ if (unlikely(in_async)) mutex_lock(&ctx->uring_lock); /* * Track whether we have multiple files in our lists. This will impact * how we do polling eventually, not spinning if we're on potentially * different devices. */ if (list_empty(&ctx->iopoll_list)) { ctx->poll_multi_queue = false; } else if (!ctx->poll_multi_queue) { struct io_kiocb *list_req; unsigned int queue_num0, queue_num1; list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb, inflight_entry); if (list_req->file != req->file) { ctx->poll_multi_queue = true; } else { queue_num0 = blk_qc_t_to_queue_num(list_req->rw.kiocb.ki_cookie); queue_num1 = blk_qc_t_to_queue_num(req->rw.kiocb.ki_cookie); if (queue_num0 != queue_num1) ctx->poll_multi_queue = true; } } /* * For fast devices, IO may have already completed. If it has, add * it to the front so we find it first. */ if (READ_ONCE(req->iopoll_completed)) list_add(&req->inflight_entry, &ctx->iopoll_list); else list_add_tail(&req->inflight_entry, &ctx->iopoll_list); if (unlikely(in_async)) { /* * If IORING_SETUP_SQPOLL is enabled, sqes are either handle * in sq thread task context or in io worker task context. If * current task context is sq thread, we don't need to check * whether should wake up sq thread. */ if ((ctx->flags & IORING_SETUP_SQPOLL) && wq_has_sleeper(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); mutex_unlock(&ctx->uring_lock); } } static bool io_bdev_nowait(struct block_device *bdev) { return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); } /* * If we tracked the file through the SCM inflight mechanism, we could support * any file. For now, just ensure that anything potentially problematic is done * inline. */ static bool __io_file_supports_nowait(struct file *file, int rw) { umode_t mode = file_inode(file)->i_mode; if (S_ISBLK(mode)) { if (IS_ENABLED(CONFIG_BLOCK) && io_bdev_nowait(I_BDEV(file->f_mapping->host))) return true; return false; } if (S_ISSOCK(mode)) return true; if (S_ISREG(mode)) { if (IS_ENABLED(CONFIG_BLOCK) && io_bdev_nowait(file->f_inode->i_sb->s_bdev) && file->f_op != &io_uring_fops) return true; return false; } /* any ->read/write should understand O_NONBLOCK */ if (file->f_flags & O_NONBLOCK) return true; if (!(file->f_mode & FMODE_NOWAIT)) return false; if (rw == READ) return file->f_op->read_iter != NULL; return file->f_op->write_iter != NULL; } static bool io_file_supports_nowait(struct io_kiocb *req, int rw) { if (rw == READ && (req->flags & REQ_F_NOWAIT_READ)) return true; else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE)) return true; return __io_file_supports_nowait(req->file, rw); } static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, int rw) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; struct file *file = req->file; unsigned ioprio; int ret; if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode)) req->flags |= REQ_F_ISREG; kiocb->ki_pos = READ_ONCE(sqe->off); kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); if (unlikely(ret)) return ret; /* * If the file is marked O_NONBLOCK, still allow retry for it if it * supports async. Otherwise it's impossible to use O_NONBLOCK files * reliably. If not, or it IOCB_NOWAIT is set, don't retry. */ if ((kiocb->ki_flags & IOCB_NOWAIT) || ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) req->flags |= REQ_F_NOWAIT; ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { ret = ioprio_check_cap(ioprio); if (ret) return ret; kiocb->ki_ioprio = ioprio; } else kiocb->ki_ioprio = get_current_ioprio(); if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) return -EOPNOTSUPP; kiocb->ki_flags |= IOCB_HIPRI; kiocb->ki_complete = io_complete_rw_iopoll; req->iopoll_completed = 0; } else { if (kiocb->ki_flags & IOCB_HIPRI) return -EINVAL; kiocb->ki_complete = io_complete_rw; } /* used for fixed read/write too - just read unconditionally */ req->buf_index = READ_ONCE(sqe->buf_index); req->imu = NULL; if (req->opcode == IORING_OP_READ_FIXED || req->opcode == IORING_OP_WRITE_FIXED) { struct io_ring_ctx *ctx = req->ctx; u16 index; if (unlikely(req->buf_index >= ctx->nr_user_bufs)) return -EFAULT; index = array_index_nospec(req->buf_index, ctx->nr_user_bufs); req->imu = ctx->user_bufs[index]; io_req_set_rsrc_node(req); } req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); return 0; } static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) { switch (ret) { case -EIOCBQUEUED: break; case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTARTNOHAND: case -ERESTART_RESTARTBLOCK: /* * We can't just restart the syscall, since previously * submitted sqes may already be in progress. Just fail this * IO with EINTR. */ ret = -EINTR; fallthrough; default: kiocb->ki_complete(kiocb, ret, 0); } } static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; if (kiocb->ki_pos != -1) return &kiocb->ki_pos; if (!(req->file->f_mode & FMODE_STREAM)) { req->flags |= REQ_F_CUR_POS; kiocb->ki_pos = req->file->f_pos; return &kiocb->ki_pos; } kiocb->ki_pos = 0; return NULL; } static void kiocb_done(struct kiocb *kiocb, ssize_t ret, unsigned int issue_flags) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) { if (!__io_complete_rw_common(req, ret)) { /* * Safe to call io_end from here as we're inline * from the submission path. */ io_req_io_end(req); __io_req_complete(req, issue_flags, io_fixup_rw_res(req, ret), io_put_rw_kbuf(req)); } } else { io_rw_done(kiocb, ret); } if (req->flags & REQ_F_REISSUE) { req->flags &= ~REQ_F_REISSUE; if (io_resubmit_prep(req)) { io_req_task_queue_reissue(req); } else { unsigned int cflags = io_put_rw_kbuf(req); struct io_ring_ctx *ctx = req->ctx; ret = io_fixup_rw_res(req, ret); req_set_fail(req); if (!(issue_flags & IO_URING_F_NONBLOCK)) { mutex_lock(&ctx->uring_lock); __io_req_complete(req, issue_flags, ret, cflags); mutex_unlock(&ctx->uring_lock); } else { __io_req_complete(req, issue_flags, ret, cflags); } } } } static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, struct io_mapped_ubuf *imu) { size_t len = req->rw.len; u64 buf_end, buf_addr = req->rw.addr; size_t offset; if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end))) return -EFAULT; /* not inside the mapped region */ if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end)) return -EFAULT; /* * May not be a start of buffer, set size appropriately * and advance us to the beginning. */ offset = buf_addr - imu->ubuf; iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); if (offset) { /* * Don't use iov_iter_advance() here, as it's really slow for * using the latter parts of a big fixed buffer - it iterates * over each segment manually. We can cheat a bit here, because * we know that: * * 1) it's a BVEC iter, we set it up * 2) all bvecs are PAGE_SIZE in size, except potentially the * first and last bvec * * So just find our index, and adjust the iterator afterwards. * If the offset is within the first bvec (or the whole first * bvec, just use iov_iter_advance(). This makes it easier * since we can just skip the first segment, which may not * be PAGE_SIZE aligned. */ const struct bio_vec *bvec = imu->bvec; if (offset < bvec->bv_len) { iov_iter_advance(iter, offset); } else { unsigned long seg_skip; /* skip first vec */ offset -= bvec->bv_len; seg_skip = 1 + (offset >> PAGE_SHIFT); iter->bvec = bvec + seg_skip; iter->nr_segs -= seg_skip; iter->count -= bvec->bv_len + offset; iter->iov_offset = offset & ~PAGE_MASK; } } return 0; } static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { if (WARN_ON_ONCE(!req->imu)) return -EFAULT; return __io_import_fixed(req, rw, iter, req->imu); } static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock) { if (needs_lock) mutex_unlock(&ctx->uring_lock); } static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock) { /* * "Normal" inline submissions always hold the uring_lock, since we * grab it from the system call. Same is true for the SQPOLL offload. * The only exception is when we've detached the request and issue it * from an async worker thread, grab the lock for that case. */ if (needs_lock) mutex_lock(&ctx->uring_lock); } static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, int bgid, struct io_buffer *kbuf, bool needs_lock) { struct io_buffer *head; if (req->flags & REQ_F_BUFFER_SELECTED) return kbuf; io_ring_submit_lock(req->ctx, needs_lock); lockdep_assert_held(&req->ctx->uring_lock); head = xa_load(&req->ctx->io_buffers, bgid); if (head) { if (!list_empty(&head->list)) { kbuf = list_last_entry(&head->list, struct io_buffer, list); list_del(&kbuf->list); } else { kbuf = head; xa_erase(&req->ctx->io_buffers, bgid); } if (*len > kbuf->len) *len = kbuf->len; } else { kbuf = ERR_PTR(-ENOBUFS); } io_ring_submit_unlock(req->ctx, needs_lock); return kbuf; } static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len, bool needs_lock) { struct io_buffer *kbuf; u16 bgid; kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; bgid = req->buf_index; kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock); if (IS_ERR(kbuf)) return kbuf; req->rw.addr = (u64) (unsigned long) kbuf; req->flags |= REQ_F_BUFFER_SELECTED; return u64_to_user_ptr(kbuf->addr); } #ifdef CONFIG_COMPAT static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, bool needs_lock) { struct compat_iovec __user *uiov; compat_ssize_t clen; void __user *buf; ssize_t len; uiov = u64_to_user_ptr(req->rw.addr); if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(clen, &uiov->iov_len)) return -EFAULT; if (clen < 0) return -EINVAL; len = clen; buf = io_rw_buffer_select(req, &len, needs_lock); if (IS_ERR(buf)) return PTR_ERR(buf); iov[0].iov_base = buf; iov[0].iov_len = (compat_size_t) len; return 0; } #endif static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, bool needs_lock) { struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr); void __user *buf; ssize_t len; if (copy_from_user(iov, uiov, sizeof(*uiov))) return -EFAULT; len = iov[0].iov_len; if (len < 0) return -EINVAL; buf = io_rw_buffer_select(req, &len, needs_lock); if (IS_ERR(buf)) return PTR_ERR(buf); iov[0].iov_base = buf; iov[0].iov_len = len; return 0; } static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, bool needs_lock) { if (req->flags & REQ_F_BUFFER_SELECTED) { struct io_buffer *kbuf; kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; iov[0].iov_base = u64_to_user_ptr(kbuf->addr); iov[0].iov_len = kbuf->len; return 0; } if (req->rw.len != 1) return -EINVAL; #ifdef CONFIG_COMPAT if (req->ctx->compat) return io_compat_import(req, iov, needs_lock); #endif return __io_iov_buffer_select(req, iov, needs_lock); } static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter, bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; u8 opcode = req->opcode; ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; return io_import_fixed(req, rw, iter); } /* buffer index only valid with fixed read/write, or buffer select */ if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { if (req->flags & REQ_F_BUFFER_SELECT) { buf = io_rw_buffer_select(req, &sqe_len, needs_lock); if (IS_ERR(buf)) return PTR_ERR(buf); req->rw.len = sqe_len; } ret = import_single_range(rw, buf, sqe_len, *iovec, iter); *iovec = NULL; return ret; } if (req->flags & REQ_F_BUFFER_SELECT) { ret = io_iov_buffer_select(req, *iovec, needs_lock); if (!ret) iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len); *iovec = NULL; return ret; } return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter, req->ctx->compat); } static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) { return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos; } /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. */ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) { struct kiocb *kiocb = &req->rw.kiocb; struct file *file = req->file; ssize_t ret = 0; loff_t *ppos; /* * Don't support polled IO through this interface, and we can't * support non-blocking either. For the latter, this just causes * the kiocb to be handled from an async context. */ if (kiocb->ki_flags & IOCB_HIPRI) return -EOPNOTSUPP; if (kiocb->ki_flags & IOCB_NOWAIT) return -EAGAIN; ppos = io_kiocb_ppos(kiocb); while (iov_iter_count(iter)) { struct iovec iovec; ssize_t nr; if (!iov_iter_is_bvec(iter)) { iovec = iov_iter_iovec(iter); } else { iovec.iov_base = u64_to_user_ptr(req->rw.addr); iovec.iov_len = req->rw.len; } if (rw == READ) { nr = file->f_op->read(file, iovec.iov_base, iovec.iov_len, ppos); } else { nr = file->f_op->write(file, iovec.iov_base, iovec.iov_len, ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (!iov_iter_is_bvec(iter)) { iov_iter_advance(iter, nr); } else { req->rw.addr += nr; req->rw.len -= nr; if (!req->rw.len) break; } if (nr != iovec.iov_len) break; } return ret; } static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter) { struct io_async_rw *rw = req->async_data; memcpy(&rw->iter, iter, sizeof(*iter)); rw->free_iovec = iovec; rw->bytes_done = 0; /* can only be fixed buffers, no need to do anything */ if (iov_iter_is_bvec(iter)) return; if (!iovec) { unsigned iov_off = 0; rw->iter.iov = rw->fast_iov; if (iter->iov != fast_iov) { iov_off = iter->iov - fast_iov; rw->iter.iov += iov_off; } if (rw->fast_iov != fast_iov) memcpy(rw->fast_iov + iov_off, fast_iov + iov_off, sizeof(struct iovec) * iter->nr_segs); } else { req->flags |= REQ_F_NEED_CLEANUP; } } static inline int io_alloc_async_data(struct io_kiocb *req) { WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); return req->async_data == NULL; } static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force) { if (!force && !io_op_defs[req->opcode].needs_async_setup) return 0; if (!req->async_data) { struct io_async_rw *iorw; if (io_alloc_async_data(req)) { kfree(iovec); return -ENOMEM; } io_req_map_rw(req, iovec, fast_iov, iter); iorw = req->async_data; /* we've copied and mapped the iter, ensure state is saved */ iov_iter_save_state(&iorw->iter, &iorw->iter_state); } return 0; } static inline int io_rw_prep_async(struct io_kiocb *req, int rw) { struct io_async_rw *iorw = req->async_data; struct iovec *iov = iorw->fast_iov; int ret; iorw->bytes_done = 0; iorw->free_iovec = NULL; ret = io_import_iovec(rw, req, &iov, &iorw->iter, false); if (unlikely(ret < 0)) return ret; if (iov) { iorw->free_iovec = iov; req->flags |= REQ_F_NEED_CLEANUP; } iov_iter_save_state(&iorw->iter, &iorw->iter_state); return 0; } static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; return io_prep_rw(req, sqe, READ); } /* * This is our waitqueue callback handler, registered through lock_page_async() * when we initially tried to do the IO with the iocb armed our waitqueue. * This gets called when the page is unlocked, and we generally expect that to * happen when the page IO is completed and the page is now uptodate. This will * queue a task_work based retry of the operation, attempting to copy the data * again. If the latter fails because the page was NOT uptodate, then we will * do a thread based blocking retry of the operation. That's the unexpected * slow path. */ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, int sync, void *arg) { struct wait_page_queue *wpq; struct io_kiocb *req = wait->private; struct wait_page_key *key = arg; wpq = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wpq, key)) return 0; req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; list_del_init(&wait->entry); io_req_task_queue(req); return 1; } /* * This controls whether a given IO request should be armed for async page * based retry. If we return false here, the request is handed to the async * worker threads for retry. If we're doing buffered reads on a regular file, * we prepare a private wait_page_queue entry and retry the operation. This * will either succeed because the page is now uptodate and unlocked, or it * will register a callback when the page is unlocked at IO completion. Through * that callback, io_uring uses task_work to setup a retry of the operation. * That retry will attempt the buffered read again. The retry will generally * succeed, or in rare cases where it fails, we then fall back to using the * async worker threads for a blocking retry. */ static bool io_rw_should_retry(struct io_kiocb *req) { struct io_async_rw *rw = req->async_data; struct wait_page_queue *wait = &rw->wpq; struct kiocb *kiocb = &req->rw.kiocb; /* never retry for NOWAIT, we just complete with -EAGAIN */ if (req->flags & REQ_F_NOWAIT) return false; /* Only for buffered IO */ if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) return false; /* * just use poll if we can, and don't attempt if the fs doesn't * support callback based unlocks */ if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) return false; wait->wait.func = io_async_buf_func; wait->wait.private = req; wait->wait.flags = 0; INIT_LIST_HEAD(&wait->wait.entry); kiocb->ki_flags |= IOCB_WAITQ; kiocb->ki_flags &= ~IOCB_NOWAIT; kiocb->ki_waitq = wait; return true; } static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) { if (req->file->f_op->read_iter) return call_read_iter(req->file, &req->rw.kiocb, iter); else if (req->file->f_op->read) return loop_rw_iter(READ, req, iter); else return -EINVAL; } static bool need_read_all(struct io_kiocb *req) { return req->flags & REQ_F_ISREG || S_ISBLK(file_inode(req->file)->i_mode); } static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; struct iov_iter_state __state, *state; ssize_t ret, ret2; loff_t *ppos; if (rw) { iter = &rw->iter; state = &rw->iter_state; /* * We come here from an earlier attempt, restore our state to * match in case it doesn't. It's cheap enough that we don't * need to make this conditional. */ iov_iter_restore(iter, state); iovec = NULL; } else { ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; state = &__state; iov_iter_save_state(iter, state); } req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) kiocb->ki_flags &= ~IOCB_NOWAIT; else kiocb->ki_flags |= IOCB_NOWAIT; /* If the file doesn't support async, just async punt */ if (force_nonblock && !io_file_supports_nowait(req, READ)) { ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true); return ret ?: -EAGAIN; } ppos = io_kiocb_update_pos(req); ret = rw_verify_area(READ, req->file, ppos, req->result); if (unlikely(ret)) { kfree(iovec); return ret; } ret = io_iter_do_read(req, iter); if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { req->flags &= ~REQ_F_REISSUE; /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; /* no retry on NONBLOCK nor RWF_NOWAIT */ if (req->flags & REQ_F_NOWAIT) goto done; ret = 0; } else if (ret == -EIOCBQUEUED) { goto out_free; } else if (ret <= 0 || ret == req->result || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { /* read all, failed, already did sync or don't want to retry */ goto done; } /* * Don't depend on the iter state matching what was consumed, or being * untouched in case of error. Restore it and we'll advance it * manually if we need to. */ iov_iter_restore(iter, state); ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); if (ret2) return ret2; iovec = NULL; rw = req->async_data; /* * Now use our persistent iterator and state, if we aren't already. * We've restored and mapped the iter to match. */ if (iter != &rw->iter) { iter = &rw->iter; state = &rw->iter_state; } do { /* * We end up here because of a partial read, either from * above or inside this loop. Advance the iter by the bytes * that were consumed. */ iov_iter_advance(iter, ret); if (!iov_iter_count(iter)) break; rw->bytes_done += ret; iov_iter_save_state(iter, state); /* if we can retry, do so with the callbacks armed */ if (!io_rw_should_retry(req)) { kiocb->ki_flags &= ~IOCB_WAITQ; return -EAGAIN; } req->result = iov_iter_count(iter); /* * Now retry read with the IOCB_WAITQ parts set in the iocb. If * we get -EIOCBQUEUED, then we'll get a notification when the * desired page gets unlocked. We can also get a partial read * here, and if we do, then just retry at the new offset. */ ret = io_iter_do_read(req, iter); if (ret == -EIOCBQUEUED) return 0; /* we got some bytes, but not all. retry. */ kiocb->ki_flags &= ~IOCB_WAITQ; iov_iter_restore(iter, state); } while (ret > 0); done: kiocb_done(kiocb, ret, issue_flags); out_free: /* it's faster to check here then delegate to kfree */ if (iovec) kfree(iovec); return 0; } static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; return io_prep_rw(req, sqe, WRITE); } static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; struct iov_iter_state __state, *state; ssize_t ret, ret2; loff_t *ppos; if (rw) { iter = &rw->iter; state = &rw->iter_state; iov_iter_restore(iter, state); iovec = NULL; } else { ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; state = &__state; iov_iter_save_state(iter, state); } req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) kiocb->ki_flags &= ~IOCB_NOWAIT; else kiocb->ki_flags |= IOCB_NOWAIT; /* If the file doesn't support async, just async punt */ if (force_nonblock && !io_file_supports_nowait(req, WRITE)) goto copy_iov; /* file path doesn't support NOWAIT for non-direct_IO */ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && (req->flags & REQ_F_ISREG)) goto copy_iov; ppos = io_kiocb_update_pos(req); ret = rw_verify_area(WRITE, req->file, ppos, req->result); if (unlikely(ret)) goto out_free; /* * Open-code file_start_write here to grab freeze protection, * which will be released by another thread in * io_complete_rw(). Fool lockdep by telling it the lock got * released so that it doesn't complain about the held lock when * we return to userspace. */ if (req->flags & REQ_F_ISREG) { sb_start_write(file_inode(req->file)->i_sb); __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; if (req->file->f_op->write_iter) ret2 = call_write_iter(req->file, kiocb, iter); else if (req->file->f_op->write) ret2 = loop_rw_iter(WRITE, req, iter); else ret2 = -EINVAL; if (req->flags & REQ_F_REISSUE) { req->flags &= ~REQ_F_REISSUE; ret2 = -EAGAIN; } /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just * retry them without IOCB_NOWAIT. */ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT)) ret2 = -EAGAIN; /* no retry on NONBLOCK nor RWF_NOWAIT */ if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) goto done; if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) goto copy_iov; done: kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: iov_iter_restore(iter, state); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); if (!ret) { if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); return -EAGAIN; } return ret; } out_free: /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; } static int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_rename *ren = &req->rename; const char __user *oldf, *newf; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; ren->old_dfd = READ_ONCE(sqe->fd); oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); ren->new_dfd = READ_ONCE(sqe->len); ren->flags = READ_ONCE(sqe->rename_flags); ren->oldpath = getname(oldf); if (IS_ERR(ren->oldpath)) return PTR_ERR(ren->oldpath); ren->newpath = getname(newf); if (IS_ERR(ren->newpath)) { putname(ren->oldpath); return PTR_ERR(ren->newpath); } req->flags |= REQ_F_NEED_CLEANUP; return 0; } static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) { struct io_rename *ren = &req->rename; int ret; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, ren->newpath, ren->flags); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_unlink *un = &req->unlink; const char __user *fname; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; un->dfd = READ_ONCE(sqe->fd); un->flags = READ_ONCE(sqe->unlink_flags); if (un->flags & ~AT_REMOVEDIR) return -EINVAL; fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); un->filename = getname(fname); if (IS_ERR(un->filename)) return PTR_ERR(un->filename); req->flags |= REQ_F_NEED_CLEANUP; return 0; } static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_unlink *un = &req->unlink; int ret; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; if (un->flags & AT_REMOVEDIR) ret = do_rmdir(un->dfd, un->filename); else ret = do_unlinkat(un->dfd, un->filename); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->shutdown.how = READ_ONCE(sqe->len); return 0; #else return -EOPNOTSUPP; #endif } static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_NET) struct socket *sock; int ret; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; ret = __sys_shutdown_sock(sock, req->shutdown.how); if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; #else return -EOPNOTSUPP; #endif } static int __io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_splice *sp = &req->splice; unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } static int io_tee_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off)) return -EINVAL; return __io_splice_prep(req, sqe); } static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; } if (sp->len) ret = do_tee(in, out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_splice *sp = &req->splice; sp->off_in = READ_ONCE(sqe->splice_off_in); sp->off_out = READ_ONCE(sqe->off); return __io_splice_prep(req, sqe); } static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; } poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; if (sp->len) ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); return 0; } /* * IORING_OP_NOP just posts a completion event, nothing else. */ static int io_nop(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; __io_req_complete(req, issue_flags, 0, 0); return 0; } static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->sync.flags = READ_ONCE(sqe->fsync_flags); if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC)) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->len); return 0; } static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) { loff_t end = req->sync.off + req->sync.len; int ret; /* fsync always requires a blocking context */ if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (sqe->ioprio || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->addr); req->sync.mode = READ_ONCE(sqe->len); return 0; } static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* fallocate always requiring blocking context */ if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); if (ret < 0) req_set_fail(req); else fsnotify_modify(req->file); io_req_complete(req, ret); return 0; } static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { const char __user *fname; int ret; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->ioprio || sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; /* open.how should be already initialised */ if (!(req->open.how.flags & O_PATH) && force_o_largefile()) req->open.how.flags |= O_LARGEFILE; req->open.dfd = READ_ONCE(sqe->fd); fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); req->open.filename = getname(fname); if (IS_ERR(req->open.filename)) { ret = PTR_ERR(req->open.filename); req->open.filename = NULL; return ret; } req->open.file_slot = READ_ONCE(sqe->file_index); if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC)) return -EINVAL; req->open.nofile = rlimit(RLIMIT_NOFILE); req->flags |= REQ_F_NEED_CLEANUP; return 0; } static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { u64 mode = READ_ONCE(sqe->len); u64 flags = READ_ONCE(sqe->open_flags); req->open.how = build_open_how(flags, mode); return __io_openat_prep(req, sqe); } static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct open_how __user *how; size_t len; int ret; how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); len = READ_ONCE(sqe->len); if (len < OPEN_HOW_SIZE_VER0) return -EINVAL; ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how, len); if (ret) return ret; return __io_openat_prep(req, sqe); } static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) { struct open_flags op; struct file *file; bool resolve_nonblock, nonblock_set; bool fixed = !!req->open.file_slot; int ret; ret = build_open_flags(&req->open.how, &op); if (ret) goto err; nonblock_set = op.open_flag & O_NONBLOCK; resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED; if (issue_flags & IO_URING_F_NONBLOCK) { /* * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open, * it'll always -EAGAIN. Note that we test for __O_TMPFILE * because O_TMPFILE includes O_DIRECTORY, which isn't a flag * we need to force async for. */ if (req->open.how.flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; op.lookup_flags |= LOOKUP_CACHED; op.open_flag |= O_NONBLOCK; } if (!fixed) { ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile); if (ret < 0) goto err; } file = do_filp_open(req->open.dfd, req->open.filename, &op); if (IS_ERR(file)) { /* * We could hang on to this 'fd' on retrying, but seems like * marginal gain for something that is now known to be a slower * path. So just put it, and we'll get a new one when we retry. */ if (!fixed) put_unused_fd(ret); ret = PTR_ERR(file); /* only retry if RESOLVE_CACHED wasn't already set by application */ if (ret == -EAGAIN && (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) return -EAGAIN; goto err; } if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) file->f_flags &= ~O_NONBLOCK; fsnotify_open(file); if (!fixed) fd_install(ret, file); else ret = io_install_fixed_file(req, file, issue_flags, req->open.file_slot - 1); err: putname(req->open.filename); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_openat(struct io_kiocb *req, unsigned int issue_flags) { return io_openat2(req, issue_flags); } static int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_provide_buf *p = &req->pbuf; u64 tmp; if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off || sqe->splice_fd_in) return -EINVAL; tmp = READ_ONCE(sqe->fd); if (!tmp || tmp > USHRT_MAX) return -EINVAL; memset(p, 0, sizeof(*p)); p->nbufs = tmp; p->bgid = READ_ONCE(sqe->buf_group); return 0; } static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, int bgid, unsigned nbufs) { unsigned i = 0; /* shouldn't happen */ if (!nbufs) return 0; /* the head kbuf is the list itself */ while (!list_empty(&buf->list)) { struct io_buffer *nxt; nxt = list_first_entry(&buf->list, struct io_buffer, list); list_del(&nxt->list); kfree(nxt); if (++i == nbufs) return i; cond_resched(); } i++; kfree(buf); xa_erase(&ctx->io_buffers, bgid); return i; } static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head; int ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); lockdep_assert_held(&ctx->uring_lock); ret = -ENOENT; head = xa_load(&ctx->io_buffers, p->bgid); if (head) ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs); if (ret < 0) req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); io_ring_submit_unlock(ctx, !force_nonblock); return 0; } static int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { unsigned long size, tmp_check; struct io_provide_buf *p = &req->pbuf; u64 tmp; if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; tmp = READ_ONCE(sqe->fd); if (!tmp || tmp > USHRT_MAX) return -E2BIG; p->nbufs = tmp; p->addr = READ_ONCE(sqe->addr); p->len = READ_ONCE(sqe->len); if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs, &size)) return -EOVERFLOW; if (check_add_overflow((unsigned long)p->addr, size, &tmp_check)) return -EOVERFLOW; size = (unsigned long)p->len * p->nbufs; if (!access_ok(u64_to_user_ptr(p->addr), size)) return -EFAULT; p->bgid = READ_ONCE(sqe->buf_group); tmp = READ_ONCE(sqe->off); if (tmp > USHRT_MAX) return -E2BIG; p->bid = tmp; return 0; } static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head) { struct io_buffer *buf; u64 addr = pbuf->addr; int i, bid = pbuf->bid; for (i = 0; i < pbuf->nbufs; i++) { buf = kmalloc(sizeof(*buf), GFP_KERNEL_ACCOUNT); if (!buf) break; buf->addr = addr; buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT); buf->bid = bid; addr += pbuf->len; bid++; if (!*head) { INIT_LIST_HEAD(&buf->list); *head = buf; } else { list_add_tail(&buf->list, &(*head)->list); } cond_resched(); } return i ? i : -ENOMEM; } static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = &req->pbuf; struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head, *list; int ret = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; io_ring_submit_lock(ctx, !force_nonblock); lockdep_assert_held(&ctx->uring_lock); list = head = xa_load(&ctx->io_buffers, p->bgid); ret = io_add_buffers(p, &head); if (ret >= 0 && !list) { ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL_ACCOUNT); if (ret < 0) __io_remove_buffers(ctx, head, p->bgid, -1U); } if (ret < 0) req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); io_ring_submit_unlock(ctx, !force_nonblock); return 0; } static int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); req->epoll.op = READ_ONCE(sqe->len); req->epoll.fd = READ_ONCE(sqe->off); if (ep_op_has_event(req->epoll.op)) { struct epoll_event __user *ev; ev = u64_to_user_ptr(READ_ONCE(sqe->addr)); if (copy_from_user(&req->epoll.event, ev, sizeof(*ev))) return -EFAULT; } return 0; #else return -EOPNOTSUPP; #endif } static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_EPOLL) struct io_epoll *ie = &req->epoll; int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock); if (force_nonblock && ret == -EAGAIN) return -EAGAIN; if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; #else return -EOPNOTSUPP; #endif } static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->madvise.addr = READ_ONCE(sqe->addr); req->madvise.len = READ_ONCE(sqe->len); req->madvise.advice = READ_ONCE(sqe->fadvise_advice); return 0; #else return -EOPNOTSUPP; #endif } static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) { #if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU) struct io_madvise *ma = &req->madvise; int ret; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; #else return -EOPNOTSUPP; #endif } static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (sqe->ioprio || sqe->buf_index || sqe->addr || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->fadvise.offset = READ_ONCE(sqe->off); req->fadvise.len = READ_ONCE(sqe->len); req->fadvise.advice = READ_ONCE(sqe->fadvise_advice); return 0; } static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) { struct io_fadvise *fa = &req->fadvise; int ret; if (issue_flags & IO_URING_F_NONBLOCK) { switch (fa->advice) { case POSIX_FADV_NORMAL: case POSIX_FADV_RANDOM: case POSIX_FADV_SEQUENTIAL: break; default: return -EAGAIN; } } ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; req->statx.dfd = READ_ONCE(sqe->fd); req->statx.mask = READ_ONCE(sqe->len); req->statx.filename = u64_to_user_ptr(READ_ONCE(sqe->addr)); req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2)); req->statx.flags = READ_ONCE(sqe->statx_flags); return 0; } static int io_statx(struct io_kiocb *req, unsigned int issue_flags) { struct io_statx *ctx = &req->statx; int ret; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask, ctx->buffer); if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); req->close.file_slot = READ_ONCE(sqe->file_index); if (req->close.file_slot && req->close.fd) return -EINVAL; return 0; } static int io_close(struct io_kiocb *req, unsigned int issue_flags) { struct files_struct *files = current->files; struct io_close *close = &req->close; struct fdtable *fdt; struct file *file = NULL; int ret = -EBADF; if (req->close.file_slot) { ret = io_close_fixed(req, issue_flags); goto err; } spin_lock(&files->file_lock); fdt = files_fdtable(files); if (close->fd >= fdt->max_fds) { spin_unlock(&files->file_lock); goto err; } file = fdt->fd[close->fd]; if (!file || file->f_op == &io_uring_fops) { spin_unlock(&files->file_lock); file = NULL; goto err; } /* if the file has a flush method, be safe and punt to async */ if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) { spin_unlock(&files->file_lock); return -EAGAIN; } ret = __close_fd_get_file(close->fd, &file); spin_unlock(&files->file_lock); if (ret < 0) { if (ret == -ENOENT) ret = -EBADF; goto err; } /* No ->flush() or already async, safely close from here */ ret = filp_close(file, current->files); err: if (ret < 0) req_set_fail(req); if (file) fput(file); __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->len); req->sync.flags = READ_ONCE(sqe->sync_range_flags); return 0; } static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) { int ret; /* sync_file_range always requires a blocking context */ if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) req_set_fail(req); io_req_complete(req, ret); return 0; } #if defined(CONFIG_NET) static bool io_net_retry(struct socket *sock, int flags) { if (!(flags & MSG_WAITALL)) return false; return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET; } static int io_setup_async_msg(struct io_kiocb *req, struct io_async_msghdr *kmsg) { struct io_async_msghdr *async_msg = req->async_data; if (async_msg) return -EAGAIN; if (io_alloc_async_data(req)) { kfree(kmsg->free_iov); return -ENOMEM; } async_msg = req->async_data; req->flags |= REQ_F_NEED_CLEANUP; memcpy(async_msg, kmsg, sizeof(*kmsg)); if (async_msg->msg.msg_name) async_msg->msg.msg_name = &async_msg->addr; /* if were using fast_iov, set it to the new one */ if (!kmsg->free_iov) { size_t fast_idx = kmsg->msg.msg_iter.iov - kmsg->fast_iov; async_msg->msg.msg_iter.iov = &async_msg->fast_iov[fast_idx]; } return -EAGAIN; } static int io_sendmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { struct io_sr_msg *sr = &req->sr_msg; int ret; iomsg->msg.msg_name = &iomsg->addr; iomsg->free_iov = iomsg->fast_iov; ret = sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg, req->sr_msg.msg_flags, &iomsg->free_iov); /* save msg_control as sys_sendmsg() overwrites it */ sr->msg_control = iomsg->msg.msg_control; return ret; } static int io_sendmsg_prep_async(struct io_kiocb *req) { int ret; ret = io_sendmsg_copy_hdr(req, req->async_data); if (!ret) req->flags |= REQ_F_NEED_CLEANUP; return ret; } static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = &req->sr_msg; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr2 || sqe->file_index)) return -EINVAL; if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL; if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; #ifdef CONFIG_COMPAT if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif sr->done_io = 0; return 0; } static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; unsigned flags; int min_ret = 0; int ret; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; kmsg = req->async_data; if (!kmsg) { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) return ret; kmsg = &iomsg; } else { kmsg->msg.msg_control = sr->msg_control; } flags = req->sr_msg.msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); if (ret < min_ret) { if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_msg(req, kmsg); } req_set_fail(req); } /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret >= 0) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_send(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; struct iovec iov; struct socket *sock; unsigned flags; int min_ret = 0; int ret; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter); if (unlikely(ret)) return ret; msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; flags = req->sr_msg.msg_flags; if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); if (ret < min_ret) { if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { sr->len -= ret; sr->buf += ret; sr->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; return -EAGAIN; } req_set_fail(req); } if (ret >= 0) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; __io_req_complete(req, issue_flags, ret, 0); return 0; } static int __io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { struct io_sr_msg *sr = &req->sr_msg; struct iovec __user *uiov; size_t iov_len; int ret; ret = __copy_msghdr_from_user(&iomsg->msg, sr->umsg, &iomsg->uaddr, &uiov, &iov_len); if (ret) return ret; if (req->flags & REQ_F_BUFFER_SELECT) { if (iov_len > 1) return -EINVAL; if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov))) return -EFAULT; sr->len = iomsg->fast_iov[0].iov_len; iomsg->free_iov = NULL; } else { iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV, &iomsg->free_iov, &iomsg->msg.msg_iter, false); if (ret > 0) ret = 0; } return ret; } #ifdef CONFIG_COMPAT static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { struct io_sr_msg *sr = &req->sr_msg; struct compat_iovec __user *uiov; compat_uptr_t ptr; compat_size_t len; int ret; ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr, &ptr, &len); if (ret) return ret; uiov = compat_ptr(ptr); if (req->flags & REQ_F_BUFFER_SELECT) { compat_ssize_t clen; if (len > 1) return -EINVAL; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(clen, &uiov->iov_len)) return -EFAULT; if (clen < 0) return -EINVAL; sr->len = clen; iomsg->free_iov = NULL; } else { iomsg->free_iov = iomsg->fast_iov; ret = __import_iovec(READ, (struct iovec __user *)uiov, len, UIO_FASTIOV, &iomsg->free_iov, &iomsg->msg.msg_iter, true); if (ret < 0) return ret; } return 0; } #endif static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg) { iomsg->msg.msg_name = &iomsg->addr; #ifdef CONFIG_COMPAT if (req->ctx->compat) return __io_compat_recvmsg_copy_hdr(req, iomsg); #endif return __io_recvmsg_copy_hdr(req, iomsg); } static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req, bool needs_lock) { struct io_sr_msg *sr = &req->sr_msg; struct io_buffer *kbuf; kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock); if (IS_ERR(kbuf)) return kbuf; sr->kbuf = kbuf; req->flags |= REQ_F_BUFFER_SELECTED; return kbuf; } static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req) { return io_put_kbuf(req, req->sr_msg.kbuf); } static int io_recvmsg_prep_async(struct io_kiocb *req) { int ret; ret = io_recvmsg_copy_hdr(req, req->async_data); if (!ret) req->flags |= REQ_F_NEED_CLEANUP; return ret; } static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sr_msg *sr = &req->sr_msg; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr2 || sqe->file_index)) return -EINVAL; if (unlikely(sqe->addr2 || sqe->file_index || sqe->ioprio)) return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); sr->bgid = READ_ONCE(sqe->buf_group); sr->msg_flags = READ_ONCE(sqe->msg_flags); if (sr->msg_flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; #ifdef CONFIG_COMPAT if (req->ctx->compat) sr->msg_flags |= MSG_CMSG_COMPAT; #endif sr->done_io = 0; return 0; } static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr iomsg, *kmsg; struct io_sr_msg *sr = &req->sr_msg; struct socket *sock; struct io_buffer *kbuf; unsigned flags; int min_ret = 0; int ret, cflags = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; kmsg = req->async_data; if (!kmsg) { ret = io_recvmsg_copy_hdr(req, &iomsg); if (ret) return ret; kmsg = &iomsg; } if (req->flags & REQ_F_BUFFER_SELECT) { kbuf = io_recv_buffer_select(req, !force_nonblock); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); kmsg->fast_iov[0].iov_len = req->sr_msg.len; iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1, req->sr_msg.len); } flags = req->sr_msg.msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL && !kmsg->msg.msg_controllen) min_ret = iov_iter_count(&kmsg->msg.msg_iter); ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, kmsg->uaddr, flags); if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) return io_setup_async_msg(req, kmsg); if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { kmsg->msg.msg_controllen = 0; kmsg->msg.msg_control = NULL; sr->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; return io_setup_async_msg(req, kmsg); } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); /* fast path, check for non-NULL to avoid function call */ if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret >= 0) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; __io_req_complete(req, issue_flags, ret, cflags); return 0; } static int io_recv(struct io_kiocb *req, unsigned int issue_flags) { struct io_buffer *kbuf; struct io_sr_msg *sr = &req->sr_msg; struct msghdr msg; void __user *buf = sr->buf; struct socket *sock; struct iovec iov; unsigned flags; int min_ret = 0; int ret, cflags = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; sock = sock_from_file(req->file, &ret); if (unlikely(!sock)) return ret; if (req->flags & REQ_F_BUFFER_SELECT) { kbuf = io_recv_buffer_select(req, !force_nonblock); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); buf = u64_to_user_ptr(kbuf->addr); } ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter); if (unlikely(ret)) goto out_free; msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; msg.msg_iocb = NULL; msg.msg_flags = 0; flags = req->sr_msg.msg_flags; if (force_nonblock) flags |= MSG_DONTWAIT; if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); ret = sock_recvmsg(sock, &msg, flags); if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; if (ret > 0 && io_net_retry(sock, flags)) { sr->len -= ret; sr->buf += ret; sr->done_io += ret; req->flags |= REQ_F_PARTIAL_IO; return -EAGAIN; } req_set_fail(req); } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) { out_free: req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); if (ret >= 0) ret += sr->done_io; else if (sr->done_io) ret = sr->done_io; __io_req_complete(req, issue_flags, ret, cflags); return 0; } static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_accept *accept = &req->accept; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); accept->nofile = rlimit(RLIMIT_NOFILE); accept->file_slot = READ_ONCE(sqe->file_index); if (accept->file_slot && (accept->flags & SOCK_CLOEXEC)) return -EINVAL; if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK)) accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return 0; } static int io_accept(struct io_kiocb *req, unsigned int issue_flags) { struct io_accept *accept = &req->accept; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0; bool fixed = !!accept->file_slot; struct file *file; int ret, fd; if (!fixed) { fd = __get_unused_fd_flags(accept->flags, accept->nofile); if (unlikely(fd < 0)) return fd; } file = do_accept(req->file, file_flags, accept->addr, accept->addr_len, accept->flags); if (IS_ERR(file)) { if (!fixed) put_unused_fd(fd); ret = PTR_ERR(file); /* safe to retry */ req->flags |= REQ_F_PARTIAL_IO; if (ret == -EAGAIN && force_nonblock) return -EAGAIN; if (ret == -ERESTARTSYS) ret = -EINTR; req_set_fail(req); } else if (!fixed) { fd_install(fd, file); ret = fd; } else { ret = io_install_fixed_file(req, file, issue_flags, accept->file_slot - 1); } __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_connect_prep_async(struct io_kiocb *req) { struct io_async_connect *io = req->async_data; struct io_connect *conn = &req->connect; return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address); } static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_connect *conn = &req->connect; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); conn->addr_len = READ_ONCE(sqe->addr2); return 0; } static int io_connect(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_connect __io, *io; unsigned file_flags; int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; if (req->async_data) { io = req->async_data; } else { ret = move_addr_to_kernel(req->connect.addr, req->connect.addr_len, &__io.address); if (ret) goto out; io = &__io; } file_flags = force_nonblock ? O_NONBLOCK : 0; ret = __sys_connect_file(req->file, &io->address, req->connect.addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { if (req->async_data) return -EAGAIN; if (io_alloc_async_data(req)) { ret = -ENOMEM; goto out; } memcpy(req->async_data, &__io, sizeof(__io)); return -EAGAIN; } if (ret == -ERESTARTSYS) ret = -EINTR; out: if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } #else /* !CONFIG_NET */ #define IO_NETOP_FN(op) \ static int io_##op(struct io_kiocb *req, unsigned int issue_flags) \ { \ return -EOPNOTSUPP; \ } #define IO_NETOP_PREP(op) \ IO_NETOP_FN(op) \ static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \ { \ return -EOPNOTSUPP; \ } \ #define IO_NETOP_PREP_ASYNC(op) \ IO_NETOP_PREP(op) \ static int io_##op##_prep_async(struct io_kiocb *req) \ { \ return -EOPNOTSUPP; \ } IO_NETOP_PREP_ASYNC(sendmsg); IO_NETOP_PREP_ASYNC(recvmsg); IO_NETOP_PREP_ASYNC(connect); IO_NETOP_PREP(accept); IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; int nr_entries; int error; }; #define IO_POLL_CANCEL_FLAG BIT(31) #define IO_POLL_RETRY_FLAG BIT(30) #define IO_POLL_REF_MASK GENMASK(29, 0) /* * We usually have 1-2 refs taken, 128 is more than enough and we want to * maximise the margin between this amount and the moment when it overflows. */ #define IO_POLL_REF_BIAS 128 static bool io_poll_get_ownership_slowpath(struct io_kiocb *req) { int v; /* * poll_refs are already elevated and we don't have much hope for * grabbing the ownership. Instead of incrementing set a retry flag * to notify the loop that there might have been some change. */ v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs); if (v & IO_POLL_REF_MASK) return false; return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } /* * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can * bump it and acquire ownership. It's disallowed to modify requests while not * owning it, that prevents from races for enqueueing task_work's and b/w * arming poll and wakeups. */ static inline bool io_poll_get_ownership(struct io_kiocb *req) { if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS)) return io_poll_get_ownership_slowpath(req); return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } static void io_poll_mark_cancelled(struct io_kiocb *req) { atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs); } static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req) { /* pure poll stashes this in ->async_data, poll driven retry elsewhere */ if (req->opcode == IORING_OP_POLL_ADD) return req->async_data; return req->apoll->double_poll; } static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req) { if (req->opcode == IORING_OP_POLL_ADD) return &req->poll; return &req->apoll->poll; } static void io_poll_req_insert(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct hlist_head *list; list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)]; hlist_add_head(&req->hash_node, list); } static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events, wait_queue_func_t wake_func) { poll->head = NULL; #define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP) /* mask in events that we always want/need */ poll->events = events | IO_POLL_UNMASK; INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, wake_func); } static inline void io_poll_remove_entry(struct io_poll_iocb *poll) { struct wait_queue_head *head = smp_load_acquire(&poll->head); if (head) { spin_lock_irq(&head->lock); list_del_init(&poll->wait.entry); poll->head = NULL; spin_unlock_irq(&head->lock); } } static void io_poll_remove_entries(struct io_kiocb *req) { struct io_poll_iocb *poll = io_poll_get_single(req); struct io_poll_iocb *poll_double = io_poll_get_double(req); /* * While we hold the waitqueue lock and the waitqueue is nonempty, * wake_up_pollfree() will wait for us. However, taking the waitqueue * lock in the first place can race with the waitqueue being freed. * * We solve this as eventpoll does: by taking advantage of the fact that * all users of wake_up_pollfree() will RCU-delay the actual free. If * we enter rcu_read_lock() and see that the pointer to the queue is * non-NULL, we can then lock it without the memory being freed out from * under us. * * Keep holding rcu_read_lock() as long as we hold the queue lock, in * case the caller deletes the entry from the queue, leaving it empty. * In that case, only RCU prevents the queue memory from being freed. */ rcu_read_lock(); io_poll_remove_entry(poll); if (poll_double) io_poll_remove_entry(poll_double); rcu_read_unlock(); } /* * All poll tw should go through this. Checks for poll events, manages * references, does rewait, etc. * * Returns a negative error on failure. >0 when no action require, which is * either spurious wakeup or multishot CQE is served. 0 when it's done with * the request, then the mask is stored in req->result. */ static int io_poll_check_events(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct io_poll_iocb *poll = io_poll_get_single(req); int v; /* req->task == current here, checking PF_EXITING is safe */ if (unlikely(req->task->flags & PF_EXITING)) io_poll_mark_cancelled(req); do { v = atomic_read(&req->poll_refs); /* tw handler should be the owner, and so have some references */ if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK))) return 0; if (v & IO_POLL_CANCEL_FLAG) return -ECANCELED; /* * cqe.res contains only events of the first wake up * and all others are be lost. Redo vfs_poll() to get * up to date state. */ if ((v & IO_POLL_REF_MASK) != 1) req->result = 0; if (v & IO_POLL_RETRY_FLAG) { req->result = 0; /* * We won't find new events that came in between * vfs_poll and the ref put unless we clear the * flag in advance. */ atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs); v &= ~IO_POLL_RETRY_FLAG; } if (!req->result) { struct poll_table_struct pt = { ._key = poll->events }; req->result = vfs_poll(req->file, &pt) & poll->events; } /* multishot, just fill an CQE and proceed */ if (req->result && !(poll->events & EPOLLONESHOT)) { __poll_t mask = mangle_poll(req->result & poll->events); bool filled; spin_lock(&ctx->completion_lock); filled = io_fill_cqe_aux(ctx, req->user_data, mask, IORING_CQE_F_MORE); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (unlikely(!filled)) return -ECANCELED; io_cqring_ev_posted(ctx); } else if (req->result) { return 0; } /* force the next iteration to vfs_poll() */ req->result = 0; /* * Release all references, retry if someone tried to restart * task_work while we were executing it. */ } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & IO_POLL_REF_MASK); return 1; } static void io_poll_task_func(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; int ret; ret = io_poll_check_events(req); if (ret > 0) return; if (!ret) { req->result = mangle_poll(req->result & req->poll.events); } else { req->result = ret; req_set_fail(req); } io_poll_remove_entries(req); spin_lock(&ctx->completion_lock); hash_del(&req->hash_node); spin_unlock(&ctx->completion_lock); io_req_complete_post(req, req->result, 0); } static void io_apoll_task_func(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; int ret; ret = io_poll_check_events(req); if (ret > 0) return; io_tw_lock(req->ctx, locked); io_poll_remove_entries(req); spin_lock(&ctx->completion_lock); hash_del(&req->hash_node); spin_unlock(&ctx->completion_lock); if (!ret) io_req_task_submit(req, locked); else io_req_complete_failed(req, ret); } static void __io_poll_execute(struct io_kiocb *req, int mask) { req->result = mask; if (req->opcode == IORING_OP_POLL_ADD) req->io_task_work.func = io_poll_task_func; else req->io_task_work.func = io_apoll_task_func; trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask); io_req_task_work_add(req); } static inline void io_poll_execute(struct io_kiocb *req, int res) { if (io_poll_get_ownership(req)) __io_poll_execute(req, res); } static void io_poll_cancel_req(struct io_kiocb *req) { io_poll_mark_cancelled(req); /* kick tw, which should complete the request */ io_poll_execute(req, 0); } static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct io_kiocb *req = wait->private; struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb, wait); __poll_t mask = key_to_poll(key); if (unlikely(mask & POLLFREE)) { io_poll_mark_cancelled(req); /* we have to kick tw in case it's not already */ io_poll_execute(req, 0); /* * If the waitqueue is being freed early but someone is already * holds ownership over it, we have to tear down the request as * best we can. That means immediately removing the request from * its waitqueue and preventing all further accesses to the * waitqueue via the request. */ list_del_init(&poll->wait.entry); /* * Careful: this *must* be the last step, since as soon * as req->head is NULL'ed out, the request can be * completed and freed, since aio_poll_complete_work() * will no longer need to take the waitqueue lock. */ smp_store_release(&poll->head, NULL); return 1; } /* for instances that support it check for an event match first */ if (mask && !(mask & poll->events)) return 0; if (io_poll_get_ownership(req)) { /* * If we trigger a multishot poll off our own wakeup path, * disable multishot as there is a circular dependency between * CQ posting and triggering the event. */ if (mask & EPOLL_URING_WAKE) poll->events |= EPOLLONESHOT; __io_poll_execute(req, mask); } return 1; } static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, struct wait_queue_head *head, struct io_poll_iocb **poll_ptr) { struct io_kiocb *req = pt->req; /* * The file being polled uses multiple waitqueues for poll handling * (e.g. one for read, one for write). Setup a separate io_poll_iocb * if this happens. */ if (unlikely(pt->nr_entries)) { struct io_poll_iocb *first = poll; /* double add on the same waitqueue head, ignore */ if (first->head == head) return; /* already have a 2nd entry, fail a third attempt */ if (*poll_ptr) { if ((*poll_ptr)->head == head) return; pt->error = -EINVAL; return; } poll = kmalloc(sizeof(*poll), GFP_ATOMIC); if (!poll) { pt->error = -ENOMEM; return; } io_init_poll_iocb(poll, first->events, first->wait.func); *poll_ptr = poll; } pt->nr_entries++; poll->head = head; poll->wait.private = req; if (poll->events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(head, &poll->wait); else add_wait_queue(head, &poll->wait); } static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); __io_queue_proc(&pt->req->poll, pt, head, (struct io_poll_iocb **) &pt->req->async_data); } static int __io_arm_poll_handler(struct io_kiocb *req, struct io_poll_iocb *poll, struct io_poll_table *ipt, __poll_t mask) { struct io_ring_ctx *ctx = req->ctx; INIT_HLIST_NODE(&req->hash_node); io_init_poll_iocb(poll, mask, io_poll_wake); poll->file = req->file; poll->wait.private = req; ipt->pt._key = mask; ipt->req = req; ipt->error = 0; ipt->nr_entries = 0; /* * Take the ownership to delay any tw execution up until we're done * with poll arming. see io_poll_get_ownership(). */ atomic_set(&req->poll_refs, 1); mask = vfs_poll(req->file, &ipt->pt) & poll->events; if (mask && (poll->events & EPOLLONESHOT)) { io_poll_remove_entries(req); /* no one else has access to the req, forget about the ref */ return mask; } if (!mask && unlikely(ipt->error || !ipt->nr_entries)) { io_poll_remove_entries(req); if (!ipt->error) ipt->error = -EINVAL; return 0; } spin_lock(&ctx->completion_lock); io_poll_req_insert(req); spin_unlock(&ctx->completion_lock); if (mask) { /* can't multishot if failed, just queue the event we've got */ if (unlikely(ipt->error || !ipt->nr_entries)) { poll->events |= EPOLLONESHOT; ipt->error = 0; } __io_poll_execute(req, mask); return 0; } /* * Try to release ownership. If we see a change of state, e.g. * poll was waken up, queue up a tw, it'll deal with it. */ if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) __io_poll_execute(req, 0); return 0; } static void io_async_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct io_poll_table *pt = container_of(p, struct io_poll_table, pt); struct async_poll *apoll = pt->req->apoll; __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll); } enum { IO_APOLL_OK, IO_APOLL_ABORTED, IO_APOLL_READY }; /* * We can't reliably detect loops in repeated poll triggers and issue * subsequently failing. But rather than fail these immediately, allow a * certain amount of retries before we give up. Given that this condition * should _rarely_ trigger even once, we should be fine with a larger value. */ #define APOLL_MAX_RETRY 128 static int io_arm_poll_handler(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; __poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI; int ret; if (!req->file || !file_can_poll(req->file)) return IO_APOLL_ABORTED; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; if (def->pollin) { mask |= POLLIN | POLLRDNORM; /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ if ((req->opcode == IORING_OP_RECVMSG) && (req->sr_msg.msg_flags & MSG_ERRQUEUE)) mask &= ~POLLIN; } else { mask |= POLLOUT | POLLWRNORM; } if (req->flags & REQ_F_POLLED) { apoll = req->apoll; kfree(apoll->double_poll); if (unlikely(!--apoll->poll.retries)) { apoll->double_poll = NULL; return IO_APOLL_ABORTED; } } else { apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) return IO_APOLL_ABORTED; apoll->poll.retries = APOLL_MAX_RETRY; } apoll->double_poll = NULL; req->apoll = apoll; req->flags |= REQ_F_POLLED; ipt.pt._qproc = io_async_queue_proc; ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask); if (ret || ipt.error) return ret ? IO_APOLL_READY : IO_APOLL_ABORTED; trace_io_uring_poll_arm(ctx, req, req->opcode, req->user_data, mask, apoll->poll.events); return IO_APOLL_OK; } /* * Returns true if we found and killed one or more poll requests */ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; bool found = false; int i; spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list; list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { if (io_match_task_safe(req, tsk, cancel_all)) { hlist_del_init(&req->hash_node); io_poll_cancel_req(req); found = true; } } } spin_unlock(&ctx->completion_lock); return found; } static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr, bool poll_only) __must_hold(&ctx->completion_lock) { struct hlist_head *list; struct io_kiocb *req; list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)]; hlist_for_each_entry(req, list, hash_node) { if (sqe_addr != req->user_data) continue; if (poll_only && req->opcode != IORING_OP_POLL_ADD) continue; return req; } return NULL; } static bool io_poll_disarm(struct io_kiocb *req) __must_hold(&ctx->completion_lock) { if (!io_poll_get_ownership(req)) return false; io_poll_remove_entries(req); hash_del(&req->hash_node); return true; } static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr, bool poll_only) __must_hold(&ctx->completion_lock) { struct io_kiocb *req = io_poll_find(ctx, sqe_addr, poll_only); if (!req) return -ENOENT; io_poll_cancel_req(req); return 0; } static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe, unsigned int flags) { u32 events; events = READ_ONCE(sqe->poll32_events); #ifdef __BIG_ENDIAN events = swahw32(events); #endif if (!(flags & IORING_POLL_ADD_MULTI)) events |= EPOLLONESHOT; return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT)); } static int io_poll_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_poll_update *upd = &req->poll_update; u32 flags; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; flags = READ_ONCE(sqe->len); if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA | IORING_POLL_ADD_MULTI)) return -EINVAL; /* meaningless without update */ if (flags == IORING_POLL_ADD_MULTI) return -EINVAL; upd->old_user_data = READ_ONCE(sqe->addr); upd->update_events = flags & IORING_POLL_UPDATE_EVENTS; upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA; upd->new_user_data = READ_ONCE(sqe->off); if (!upd->update_user_data && upd->new_user_data) return -EINVAL; if (upd->update_events) upd->events = io_poll_parse_events(sqe, flags); else if (sqe->poll32_events) return -EINVAL; return 0; } static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_poll_iocb *poll = &req->poll; u32 flags; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr) return -EINVAL; flags = READ_ONCE(sqe->len); if (flags & ~IORING_POLL_ADD_MULTI) return -EINVAL; io_req_set_refcount(req); poll->events = io_poll_parse_events(sqe, flags); return 0; } static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) { struct io_poll_iocb *poll = &req->poll; struct io_poll_table ipt; int ret; ipt.pt._qproc = io_poll_queue_proc; ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events); if (!ret && ipt.error) req_set_fail(req); ret = ret ?: ipt.error; if (ret) __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *preq; int ret2, ret = 0; io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); spin_lock(&ctx->completion_lock); preq = io_poll_find(ctx, req->poll_update.old_user_data, true); if (!preq || !io_poll_disarm(preq)) { spin_unlock(&ctx->completion_lock); ret = preq ? -EALREADY : -ENOENT; goto out; } spin_unlock(&ctx->completion_lock); if (req->poll_update.update_events || req->poll_update.update_user_data) { /* only mask one event flags, keep behavior flags */ if (req->poll_update.update_events) { preq->poll.events &= ~0xffff; preq->poll.events |= req->poll_update.events & 0xffff; preq->poll.events |= IO_POLL_UNMASK; } if (req->poll_update.update_user_data) preq->user_data = req->poll_update.new_user_data; ret2 = io_poll_add(preq, issue_flags); /* successfully updated, don't complete poll request */ if (!ret2) goto out; } req_set_fail(preq); io_req_complete(preq, -ECANCELED); out: if (ret < 0) req_set_fail(req); /* complete update request, we're done with it */ io_req_complete(req, ret); io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return 0; } static void io_req_task_timeout(struct io_kiocb *req, bool *locked) { req_set_fail(req); io_req_complete_post(req, -ETIME, 0); } static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) { struct io_timeout_data *data = container_of(timer, struct io_timeout_data, timer); struct io_kiocb *req = data->req; struct io_ring_ctx *ctx = req->ctx; unsigned long flags; spin_lock_irqsave(&ctx->timeout_lock, flags); list_del_init(&req->timeout.list); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); spin_unlock_irqrestore(&ctx->timeout_lock, flags); req->io_task_work.func = io_req_task_timeout; io_req_task_work_add(req); return HRTIMER_NORESTART; } static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, __u64 user_data) __must_hold(&ctx->timeout_lock) { struct io_timeout_data *io; struct io_kiocb *req; bool found = false; list_for_each_entry(req, &ctx->timeout_list, timeout.list) { found = user_data == req->user_data; if (found) break; } if (!found) return ERR_PTR(-ENOENT); io = req->async_data; if (hrtimer_try_to_cancel(&io->timer) == -1) return ERR_PTR(-EALREADY); list_del_init(&req->timeout.list); return req; } static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) __must_hold(&ctx->completion_lock) __must_hold(&ctx->timeout_lock) { struct io_kiocb *req = io_timeout_extract(ctx, user_data); if (IS_ERR(req)) return PTR_ERR(req); req_set_fail(req); io_fill_cqe_req(req, -ECANCELED, 0); io_put_req_deferred(req); return 0; } static clockid_t io_timeout_get_clock(struct io_timeout_data *data) { switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) { case IORING_TIMEOUT_BOOTTIME: return CLOCK_BOOTTIME; case IORING_TIMEOUT_REALTIME: return CLOCK_REALTIME; default: /* can't happen, vetted at prep time */ WARN_ON_ONCE(1); fallthrough; case 0: return CLOCK_MONOTONIC; } } static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, struct timespec64 *ts, enum hrtimer_mode mode) __must_hold(&ctx->timeout_lock) { struct io_timeout_data *io; struct io_kiocb *req; bool found = false; list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) { found = user_data == req->user_data; if (found) break; } if (!found) return -ENOENT; io = req->async_data; if (hrtimer_try_to_cancel(&io->timer) == -1) return -EALREADY; hrtimer_init(&io->timer, io_timeout_get_clock(io), mode); io->timer.function = io_link_timeout_fn; hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode); return 0; } static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, struct timespec64 *ts, enum hrtimer_mode mode) __must_hold(&ctx->timeout_lock) { struct io_kiocb *req = io_timeout_extract(ctx, user_data); struct io_timeout_data *data; if (IS_ERR(req)) return PTR_ERR(req); req->timeout.off = 0; /* noseq */ data = req->async_data; list_add_tail(&req->timeout.list, &ctx->timeout_list); hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); return 0; } static int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_timeout_rem *tr = &req->timeout_rem; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in) return -EINVAL; tr->ltimeout = false; tr->addr = READ_ONCE(sqe->addr); tr->flags = READ_ONCE(sqe->timeout_flags); if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) { if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1) return -EINVAL; if (tr->flags & IORING_LINK_TIMEOUT_UPDATE) tr->ltimeout = true; if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) return -EINVAL; if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) return -EFAULT; } else if (tr->flags) { /* timeout removal doesn't support flags */ return -EINVAL; } return 0; } static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags) { return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL; } /* * Remove or update an existing timeout command */ static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) { struct io_timeout_rem *tr = &req->timeout_rem; struct io_ring_ctx *ctx = req->ctx; int ret; if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) { spin_lock(&ctx->completion_lock); spin_lock_irq(&ctx->timeout_lock); ret = io_timeout_cancel(ctx, tr->addr); spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); } else { enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags); spin_lock_irq(&ctx->timeout_lock); if (tr->ltimeout) ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode); else ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode); spin_unlock_irq(&ctx->timeout_lock); } if (ret < 0) req_set_fail(req); io_req_complete_post(req, ret, 0); return 0; } static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, bool is_timeout_link) { struct io_timeout_data *data; unsigned flags; u32 off = READ_ONCE(sqe->off); if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in) return -EINVAL; if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) return -EINVAL; /* more than one clock specified is invalid, obviously */ if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) return -EINVAL; INIT_LIST_HEAD(&req->timeout.list); req->timeout.off = off; if (unlikely(off && !req->ctx->off_timeout_used)) req->ctx->off_timeout_used = true; if (!req->async_data && io_alloc_async_data(req)) return -ENOMEM; data = req->async_data; data->req = req; data->flags = flags; if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; INIT_LIST_HEAD(&req->timeout.list); data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); if (is_timeout_link) { struct io_submit_link *link = &req->ctx->submit_state.link; if (!link->head) return -EINVAL; if (link->last->opcode == IORING_OP_LINK_TIMEOUT) return -EINVAL; req->timeout.head = link->last; link->last->flags |= REQ_F_ARM_LTIMEOUT; } return 0; } static int io_timeout(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data = req->async_data; struct list_head *entry; u32 tail, off = req->timeout.off; spin_lock_irq(&ctx->timeout_lock); /* * sqe->off holds how many events that need to occur for this * timeout event to be satisfied. If it isn't set, then this is * a pure timeout request, sequence isn't used. */ if (io_is_timeout_noseq(req)) { entry = ctx->timeout_list.prev; goto add; } tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); req->timeout.target_seq = tail + off; /* Update the last seq here in case io_flush_timeouts() hasn't. * This is safe because ->completion_lock is held, and submissions * and completions are never mixed in the same ->completion_lock section. */ ctx->cq_last_tm_flush = tail; /* * Insertion sort, ensuring the first entry in the list is always * the one we need first. */ list_for_each_prev(entry, &ctx->timeout_list) { struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, timeout.list); if (io_is_timeout_noseq(nxt)) continue; /* nxt.seq is behind @tail, otherwise would've been completed */ if (off >= nxt->timeout.target_seq - tail) break; } add: list_add(&req->timeout.list, entry); data->timer.function = io_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); spin_unlock_irq(&ctx->timeout_lock); return 0; } struct io_cancel_data { struct io_ring_ctx *ctx; u64 user_data; }; static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_cancel_data *cd = data; return req->ctx == cd->ctx && req->user_data == cd->user_data; } static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data, struct io_ring_ctx *ctx) { struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, }; enum io_wq_cancel cancel_ret; int ret = 0; if (!tctx || !tctx->io_wq) return -ENOENT; cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; break; case IO_WQ_CANCEL_RUNNING: ret = -EALREADY; break; case IO_WQ_CANCEL_NOTFOUND: ret = -ENOENT; break; } return ret; } static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr) { struct io_ring_ctx *ctx = req->ctx; int ret; WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current); ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx); if (ret != -ENOENT) return ret; spin_lock(&ctx->completion_lock); spin_lock_irq(&ctx->timeout_lock); ret = io_timeout_cancel(ctx, sqe_addr); spin_unlock_irq(&ctx->timeout_lock); if (ret != -ENOENT) goto out; ret = io_poll_cancel(ctx, sqe_addr, false); out: spin_unlock(&ctx->completion_lock); return ret; } static int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags || sqe->splice_fd_in) return -EINVAL; req->cancel.addr = READ_ONCE(sqe->addr); return 0; } static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; u64 sqe_addr = req->cancel.addr; struct io_tctx_node *node; int ret; ret = io_try_cancel_userdata(req, sqe_addr); if (ret != -ENOENT) goto done; /* slow path, try all io-wq's */ io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; ret = io_async_cancel_one(tctx, req->cancel.addr, ctx); if (ret != -ENOENT) break; } io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); done: if (ret < 0) req_set_fail(req); io_req_complete_post(req, ret, 0); return 0; } static int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; req->rsrc_update.offset = READ_ONCE(sqe->off); req->rsrc_update.nr_args = READ_ONCE(sqe->len); if (!req->rsrc_update.nr_args) return -EINVAL; req->rsrc_update.arg = READ_ONCE(sqe->addr); return 0; } static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_uring_rsrc_update2 up; int ret; up.offset = req->rsrc_update.offset; up.data = req->rsrc_update.arg; up.nr = 0; up.tags = 0; up.resv = 0; up.resv2 = 0; io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, req->rsrc_update.nr_args); io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); if (ret < 0) req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { switch (req->opcode) { case IORING_OP_NOP: return 0; case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: return io_write_prep(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: return io_poll_update_prep(req, sqe); case IORING_OP_FSYNC: return io_fsync_prep(req, sqe); case IORING_OP_SYNC_FILE_RANGE: return io_sfr_prep(req, sqe); case IORING_OP_SENDMSG: case IORING_OP_SEND: return io_sendmsg_prep(req, sqe); case IORING_OP_RECVMSG: case IORING_OP_RECV: return io_recvmsg_prep(req, sqe); case IORING_OP_CONNECT: return io_connect_prep(req, sqe); case IORING_OP_TIMEOUT: return io_timeout_prep(req, sqe, false); case IORING_OP_TIMEOUT_REMOVE: return io_timeout_remove_prep(req, sqe); case IORING_OP_ASYNC_CANCEL: return io_async_cancel_prep(req, sqe); case IORING_OP_LINK_TIMEOUT: return io_timeout_prep(req, sqe, true); case IORING_OP_ACCEPT: return io_accept_prep(req, sqe); case IORING_OP_FALLOCATE: return io_fallocate_prep(req, sqe); case IORING_OP_OPENAT: return io_openat_prep(req, sqe); case IORING_OP_CLOSE: return io_close_prep(req, sqe); case IORING_OP_FILES_UPDATE: return io_rsrc_update_prep(req, sqe); case IORING_OP_STATX: return io_statx_prep(req, sqe); case IORING_OP_FADVISE: return io_fadvise_prep(req, sqe); case IORING_OP_MADVISE: return io_madvise_prep(req, sqe); case IORING_OP_OPENAT2: return io_openat2_prep(req, sqe); case IORING_OP_EPOLL_CTL: return io_epoll_ctl_prep(req, sqe); case IORING_OP_SPLICE: return io_splice_prep(req, sqe); case IORING_OP_PROVIDE_BUFFERS: return io_provide_buffers_prep(req, sqe); case IORING_OP_REMOVE_BUFFERS: return io_remove_buffers_prep(req, sqe); case IORING_OP_TEE: return io_tee_prep(req, sqe); case IORING_OP_SHUTDOWN: return io_shutdown_prep(req, sqe); case IORING_OP_RENAMEAT: return io_renameat_prep(req, sqe); case IORING_OP_UNLINKAT: return io_unlinkat_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", req->opcode); return -EINVAL; } static int io_req_prep_async(struct io_kiocb *req) { if (!io_op_defs[req->opcode].needs_async_setup) return 0; if (WARN_ON_ONCE(req->async_data)) return -EFAULT; if (io_alloc_async_data(req)) return -EAGAIN; switch (req->opcode) { case IORING_OP_READV: return io_rw_prep_async(req, READ); case IORING_OP_WRITEV: return io_rw_prep_async(req, WRITE); case IORING_OP_SENDMSG: return io_sendmsg_prep_async(req); case IORING_OP_RECVMSG: return io_recvmsg_prep_async(req); case IORING_OP_CONNECT: return io_connect_prep_async(req); } printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n", req->opcode); return -EFAULT; } static u32 io_get_sequence(struct io_kiocb *req) { u32 seq = req->ctx->cached_sq_head; /* need original cached_sq_head, but it was increased for each req */ io_for_each_link(req, req) seq--; return seq; } static bool io_drain_req(struct io_kiocb *req) { struct io_kiocb *pos; struct io_ring_ctx *ctx = req->ctx; struct io_defer_entry *de; int ret; u32 seq; if (req->flags & REQ_F_FAIL) { io_req_complete_fail_submit(req); return true; } /* * If we need to drain a request in the middle of a link, drain the * head request and the next request/link after the current link. * Considering sequential execution of links, IOSQE_IO_DRAIN will be * maintained for every request of our link. */ if (ctx->drain_next) { req->flags |= REQ_F_IO_DRAIN; ctx->drain_next = false; } /* not interested in head, start from the first linked */ io_for_each_link(pos, req->link) { if (pos->flags & REQ_F_IO_DRAIN) { ctx->drain_next = true; req->flags |= REQ_F_IO_DRAIN; break; } } /* Still need defer if there is pending req in defer list. */ spin_lock(&ctx->completion_lock); if (likely(list_empty_careful(&ctx->defer_list) && !(req->flags & REQ_F_IO_DRAIN))) { spin_unlock(&ctx->completion_lock); ctx->drain_active = false; return false; } spin_unlock(&ctx->completion_lock); seq = io_get_sequence(req); /* Still a chance to pass the sequence check */ if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) return false; ret = io_req_prep_async(req); if (ret) goto fail; io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { ret = -ENOMEM; fail: io_req_complete_failed(req, ret); return true; } spin_lock(&ctx->completion_lock); if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { spin_unlock(&ctx->completion_lock); kfree(de); io_queue_async_work(req, NULL); return true; } trace_io_uring_defer(ctx, req, req->user_data); de->req = req; de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); spin_unlock(&ctx->completion_lock); return true; } static void io_clean_op(struct io_kiocb *req) { if (req->flags & REQ_F_BUFFER_SELECTED) { switch (req->opcode) { case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: kfree((void *)(unsigned long)req->rw.addr); break; case IORING_OP_RECVMSG: case IORING_OP_RECV: kfree(req->sr_msg.kbuf); break; } } if (req->flags & REQ_F_NEED_CLEANUP) { switch (req->opcode) { case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: { struct io_async_rw *io = req->async_data; kfree(io->free_iovec); break; } case IORING_OP_RECVMSG: case IORING_OP_SENDMSG: { struct io_async_msghdr *io = req->async_data; kfree(io->free_iov); break; } case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) putname(req->open.filename); break; case IORING_OP_RENAMEAT: putname(req->rename.oldpath); putname(req->rename.newpath); break; case IORING_OP_UNLINKAT: putname(req->unlink.filename); break; } } if ((req->flags & REQ_F_POLLED) && req->apoll) { kfree(req->apoll->double_poll); kfree(req->apoll); req->apoll = NULL; } if (req->flags & REQ_F_INFLIGHT) { struct io_uring_task *tctx = req->task->io_uring; atomic_dec(&tctx->inflight_tracked); } if (req->flags & REQ_F_CREDS) put_cred(req->creds); req->flags &= ~IO_REQ_CLEAN_FLAGS; } static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; const struct cred *creds = NULL; int ret; if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) creds = override_creds(req->creds); switch (req->opcode) { case IORING_OP_NOP: ret = io_nop(req, issue_flags); break; case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: ret = io_read(req, issue_flags); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: ret = io_write(req, issue_flags); break; case IORING_OP_FSYNC: ret = io_fsync(req, issue_flags); break; case IORING_OP_POLL_ADD: ret = io_poll_add(req, issue_flags); break; case IORING_OP_POLL_REMOVE: ret = io_poll_update(req, issue_flags); break; case IORING_OP_SYNC_FILE_RANGE: ret = io_sync_file_range(req, issue_flags); break; case IORING_OP_SENDMSG: ret = io_sendmsg(req, issue_flags); break; case IORING_OP_SEND: ret = io_send(req, issue_flags); break; case IORING_OP_RECVMSG: ret = io_recvmsg(req, issue_flags); break; case IORING_OP_RECV: ret = io_recv(req, issue_flags); break; case IORING_OP_TIMEOUT: ret = io_timeout(req, issue_flags); break; case IORING_OP_TIMEOUT_REMOVE: ret = io_timeout_remove(req, issue_flags); break; case IORING_OP_ACCEPT: ret = io_accept(req, issue_flags); break; case IORING_OP_CONNECT: ret = io_connect(req, issue_flags); break; case IORING_OP_ASYNC_CANCEL: ret = io_async_cancel(req, issue_flags); break; case IORING_OP_FALLOCATE: ret = io_fallocate(req, issue_flags); break; case IORING_OP_OPENAT: ret = io_openat(req, issue_flags); break; case IORING_OP_CLOSE: ret = io_close(req, issue_flags); break; case IORING_OP_FILES_UPDATE: ret = io_files_update(req, issue_flags); break; case IORING_OP_STATX: ret = io_statx(req, issue_flags); break; case IORING_OP_FADVISE: ret = io_fadvise(req, issue_flags); break; case IORING_OP_MADVISE: ret = io_madvise(req, issue_flags); break; case IORING_OP_OPENAT2: ret = io_openat2(req, issue_flags); break; case IORING_OP_EPOLL_CTL: ret = io_epoll_ctl(req, issue_flags); break; case IORING_OP_SPLICE: ret = io_splice(req, issue_flags); break; case IORING_OP_PROVIDE_BUFFERS: ret = io_provide_buffers(req, issue_flags); break; case IORING_OP_REMOVE_BUFFERS: ret = io_remove_buffers(req, issue_flags); break; case IORING_OP_TEE: ret = io_tee(req, issue_flags); break; case IORING_OP_SHUTDOWN: ret = io_shutdown(req, issue_flags); break; case IORING_OP_RENAMEAT: ret = io_renameat(req, issue_flags); break; case IORING_OP_UNLINKAT: ret = io_unlinkat(req, issue_flags); break; default: ret = -EINVAL; break; } if (creds) revert_creds(creds); if (ret) return ret; /* If the op doesn't have a file, we're not polling for it */ if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) io_iopoll_req_issued(req); return 0; } static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); req = io_put_req_find_next(req); return req ? &req->work : NULL; } static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_kiocb *timeout; int ret = 0; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) __io_req_set_refcount(req, 2); else req_ref_get(req); timeout = io_prep_linked_timeout(req); if (timeout) io_queue_linked_timeout(timeout); /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) ret = -ECANCELED; if (!ret) { do { ret = io_issue_sqe(req, 0); /* * We can get EAGAIN for polled IO even though we're * forcing a sync submission from here, since we can't * wait for request slots on the block side. */ if (ret != -EAGAIN || !(req->ctx->flags & IORING_SETUP_IOPOLL)) break; if (io_wq_worker_stopped()) break; /* * If REQ_F_NOWAIT is set, then don't wait or retry with * poll. -EAGAIN is final for that case. */ if (req->flags & REQ_F_NOWAIT) break; cond_resched(); } while (1); } /* avoid locking problems by failing it from a clean context */ if (ret) io_req_task_queue_fail(req, ret); } static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table, unsigned i) { return &table->files[i]; } static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index); return (struct file *) (slot->file_ptr & FFS_MASK); } static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file) { unsigned long file_ptr = (unsigned long) file; if (__io_file_supports_nowait(file, READ)) file_ptr |= FFS_ASYNC_READ; if (__io_file_supports_nowait(file, WRITE)) file_ptr |= FFS_ASYNC_WRITE; if (S_ISREG(file_inode(file)->i_mode)) file_ptr |= FFS_ISREG; file_slot->file_ptr = file_ptr; } static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, struct io_kiocb *req, int fd, unsigned int issue_flags) { struct file *file = NULL; unsigned long file_ptr; io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); if (unlikely((unsigned int)fd >= ctx->nr_user_files)) goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); io_req_set_rsrc_node(req); out: io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return file; } static struct file *io_file_get_normal(struct io_ring_ctx *ctx, struct io_kiocb *req, int fd) { struct file *file = fget(fd); trace_io_uring_file_get(ctx, fd); /* we don't allow fixed io_uring files */ if (file && unlikely(file->f_op == &io_uring_fops)) io_req_track_inflight(req); return file; } static inline struct file *io_file_get(struct io_ring_ctx *ctx, struct io_kiocb *req, int fd, bool fixed, unsigned int issue_flags) { if (fixed) return io_file_get_fixed(ctx, req, fd, issue_flags); else return io_file_get_normal(ctx, req, fd); } static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; int ret = -ENOENT; if (prev) { if (!(req->task->flags & PF_EXITING)) ret = io_try_cancel_userdata(req, prev->user_data); io_req_complete_post(req, ret ?: -ETIME, 0); io_put_req(prev); } else { io_req_complete_post(req, -ETIME, 0); } } static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) { struct io_timeout_data *data = container_of(timer, struct io_timeout_data, timer); struct io_kiocb *prev, *req = data->req; struct io_ring_ctx *ctx = req->ctx; unsigned long flags; spin_lock_irqsave(&ctx->timeout_lock, flags); prev = req->timeout.head; req->timeout.head = NULL; /* * We don't expect the list to be empty, that will only happen if we * race with the completion of the linked work. */ if (prev) { io_remove_next_linked(prev); if (!req_ref_inc_not_zero(prev)) prev = NULL; } list_del(&req->timeout.list); req->timeout.prev = prev; spin_unlock_irqrestore(&ctx->timeout_lock, flags); req->io_task_work.func = io_req_task_link_timeout; io_req_task_work_add(req); return HRTIMER_NORESTART; } static void io_queue_linked_timeout(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; spin_lock_irq(&ctx->timeout_lock); /* * If the back reference is NULL, then our linked request finished * before we got a chance to setup the timer */ if (req->timeout.head) { struct io_timeout_data *data = req->async_data; data->timer.function = io_link_timeout_fn; hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode); list_add_tail(&req->timeout.list, &ctx->ltimeout_list); } spin_unlock_irq(&ctx->timeout_lock); /* drop submission reference */ io_put_req(req); } static void __io_queue_sqe(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { struct io_kiocb *linked_timeout; int ret; issue_sqe: ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); /* * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ if (likely(!ret)) { if (req->flags & REQ_F_COMPLETE_INLINE) { struct io_ring_ctx *ctx = req->ctx; struct io_submit_state *state = &ctx->submit_state; state->compl_reqs[state->compl_nr++] = req; if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) io_submit_flush_completions(ctx); return; } linked_timeout = io_prep_linked_timeout(req); if (linked_timeout) io_queue_linked_timeout(linked_timeout); } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { linked_timeout = io_prep_linked_timeout(req); switch (io_arm_poll_handler(req)) { case IO_APOLL_READY: if (linked_timeout) io_queue_linked_timeout(linked_timeout); goto issue_sqe; case IO_APOLL_ABORTED: /* * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ io_queue_async_work(req, NULL); break; } if (linked_timeout) io_queue_linked_timeout(linked_timeout); } else { io_req_complete_failed(req, ret); } } static inline void io_queue_sqe(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { if (unlikely(req->ctx->drain_active) && io_drain_req(req)) return; if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) { __io_queue_sqe(req); } else if (req->flags & REQ_F_FAIL) { io_req_complete_fail_submit(req); } else { int ret = io_req_prep_async(req); if (unlikely(ret)) io_req_complete_failed(req, ret); else io_queue_async_work(req, NULL); } } /* * Check SQE restrictions (opcode and flags). * * Returns 'true' if SQE is allowed, 'false' otherwise. */ static inline bool io_check_restriction(struct io_ring_ctx *ctx, struct io_kiocb *req, unsigned int sqe_flags) { if (likely(!ctx->restricted)) return true; if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) return false; if ((sqe_flags & ctx->restrictions.sqe_flags_required) != ctx->restrictions.sqe_flags_required) return false; if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed | ctx->restrictions.sqe_flags_required)) return false; return true; } static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { struct io_submit_state *state; unsigned int sqe_flags; int personality, ret = 0; /* req is partially pre-initialised, see io_preinit_req() */ req->opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ req->flags = sqe_flags = READ_ONCE(sqe->flags); req->user_data = READ_ONCE(sqe->user_data); req->file = NULL; req->fixed_rsrc_refs = NULL; req->task = current; /* enforce forwards compatibility on users */ if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) return -EINVAL; if (unlikely(req->opcode >= IORING_OP_LAST)) return -EINVAL; if (!io_check_restriction(ctx, req, sqe_flags)) return -EACCES; if ((sqe_flags & IOSQE_BUFFER_SELECT) && !io_op_defs[req->opcode].buffer_select) return -EOPNOTSUPP; if (unlikely(sqe_flags & IOSQE_IO_DRAIN)) ctx->drain_active = true; personality = READ_ONCE(sqe->personality); if (personality) { req->creds = xa_load(&ctx->personalities, personality); if (!req->creds) return -EINVAL; get_cred(req->creds); req->flags |= REQ_F_CREDS; } state = &ctx->submit_state; /* * Plug now if we have more than 1 IO left after this, and the target * is potentially a read/write to block based storage. */ if (!state->plug_started && state->ios_left > 1 && io_op_defs[req->opcode].plug) { blk_start_plug(&state->plug); state->plug_started = true; } if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), (sqe_flags & IOSQE_FIXED_FILE), IO_URING_F_NONBLOCK); if (unlikely(!req->file)) ret = -EBADF; } state->ios_left--; return ret; } static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { struct io_submit_link *link = &ctx->submit_state.link; int ret; ret = io_init_req(ctx, req, sqe); if (unlikely(ret)) { fail_req: /* fail even hard links since we don't submit */ if (link->head) { /* * we can judge a link req is failed or cancelled by if * REQ_F_FAIL is set, but the head is an exception since * it may be set REQ_F_FAIL because of other req's failure * so let's leverage req->result to distinguish if a head * is set REQ_F_FAIL because of its failure or other req's * failure so that we can set the correct ret code for it. * init result here to avoid affecting the normal path. */ if (!(link->head->flags & REQ_F_FAIL)) req_fail_link_node(link->head, -ECANCELED); } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { /* * the current req is a normal req, we should return * error and thus break the submittion loop. */ io_req_complete_failed(req, ret); return ret; } req_fail_link_node(req, ret); } else { ret = io_req_prep(req, sqe); if (unlikely(ret)) goto fail_req; } /* don't need @sqe from now on */ trace_io_uring_submit_sqe(ctx, req, req->opcode, req->user_data, req->flags, true, ctx->flags & IORING_SETUP_SQPOLL); /* * If we already have a head request, queue this one for async * submittal once the head completes. If we don't have a head but * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be * submitted sync once the chain is complete. If none of those * conditions are true (normal request), then just queue it. */ if (link->head) { struct io_kiocb *head = link->head; if (!(req->flags & REQ_F_FAIL)) { ret = io_req_prep_async(req); if (unlikely(ret)) { req_fail_link_node(req, ret); if (!(head->flags & REQ_F_FAIL)) req_fail_link_node(head, -ECANCELED); } } trace_io_uring_link(ctx, req, head); link->last->link = req; link->last = req; /* last request of a link, enqueue the link */ if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { link->head = NULL; io_queue_sqe(head); } } else { if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { link->head = req; link->last = req; } else { io_queue_sqe(req); } } return 0; } /* * Batched submission is done, ensure local IO is flushed out. */ static void io_submit_state_end(struct io_submit_state *state, struct io_ring_ctx *ctx) { if (state->link.head) io_queue_sqe(state->link.head); if (state->compl_nr) io_submit_flush_completions(ctx); if (state->plug_started) blk_finish_plug(&state->plug); } /* * Start submission side cache. */ static void io_submit_state_start(struct io_submit_state *state, unsigned int max_ios) { state->plug_started = false; state->ios_left = max_ios; /* set only head, no need to init link_last in advance */ state->link.head = NULL; } static void io_commit_sqring(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; /* * Ensure any loads from the SQEs are done at this point, * since once we write the new head, the application could * write new data to them. */ smp_store_release(&rings->sq.head, ctx->cached_sq_head); } /* * Fetch an sqe, if one is available. Note this returns a pointer to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later * used, it's important that those reads are done through READ_ONCE() to * prevent a re-load down the line. */ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) { unsigned head, mask = ctx->sq_entries - 1; unsigned sq_idx = ctx->cached_sq_head++ & mask; /* * The cached sq head (or cq tail) serves two purposes: * * 1) allows us to batch the cost of updating the user visible * head updates. * 2) allows the kernel side to track the head on its own, even * though the application is the one updating it. */ head = READ_ONCE(ctx->sq_array[sq_idx]); if (likely(head < ctx->sq_entries)) return &ctx->sq_sqes[head]; /* drop invalid entries */ ctx->cq_extra--; WRITE_ONCE(ctx->rings->sq_dropped, READ_ONCE(ctx->rings->sq_dropped) + 1); return NULL; } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) __must_hold(&ctx->uring_lock) { int submitted = 0; /* make sure SQ entry isn't read before tail */ nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); if (!percpu_ref_tryget_many(&ctx->refs, nr)) return -EAGAIN; io_get_task_refs(nr); io_submit_state_start(&ctx->submit_state, nr); while (submitted < nr) { const struct io_uring_sqe *sqe; struct io_kiocb *req; req = io_alloc_req(ctx); if (unlikely(!req)) { if (!submitted) submitted = -EAGAIN; break; } sqe = io_get_sqe(ctx); if (unlikely(!sqe)) { list_add(&req->inflight_entry, &ctx->submit_state.free_list); break; } /* will complete beyond this point, count as submitted */ submitted++; if (io_submit_sqe(ctx, req, sqe)) break; } if (unlikely(submitted != nr)) { int ref_used = (submitted == -EAGAIN) ? 0 : submitted; int unused = nr - ref_used; current->io_uring->cached_refs += unused; percpu_ref_put_many(&ctx->refs, unused); } io_submit_state_end(&ctx->submit_state, ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); return submitted; } static inline bool io_sqd_events_pending(struct io_sq_data *sqd) { return READ_ONCE(sqd->state); } static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { /* Tell userspace we may need a wakeup call */ spin_lock(&ctx->completion_lock); WRITE_ONCE(ctx->rings->sq_flags, ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); spin_unlock(&ctx->completion_lock); } static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) { spin_lock(&ctx->completion_lock); WRITE_ONCE(ctx->rings->sq_flags, ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); spin_unlock(&ctx->completion_lock); } static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) { unsigned int to_submit; int ret = 0; to_submit = io_sqring_entries(ctx); /* if we're handling multiple rings, cap submit size for fairness */ if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; if (!list_empty(&ctx->iopoll_list) || to_submit) { unsigned nr_events = 0; const struct cred *creds = NULL; if (ctx->sq_creds != current_cred()) creds = override_creds(ctx->sq_creds); mutex_lock(&ctx->uring_lock); if (!list_empty(&ctx->iopoll_list)) io_do_iopoll(ctx, &nr_events, 0); /* * Don't submit if refs are dying, good for io_uring_register(), * but also it is relied upon by io_ring_exit_work() */ if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) && !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) revert_creds(creds); } return ret; } static void io_sqd_update_thread_idle(struct io_sq_data *sqd) { struct io_ring_ctx *ctx; unsigned sq_thread_idle = 0; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle); sqd->sq_thread_idle = sq_thread_idle; } static bool io_sqd_handle_event(struct io_sq_data *sqd) { bool did_sig = false; struct ksignal ksig; if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || signal_pending(current)) { mutex_unlock(&sqd->lock); if (signal_pending(current)) did_sig = get_signal(&ksig); cond_resched(); mutex_lock(&sqd->lock); } return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); } static int io_sq_thread(void *data) { struct io_sq_data *sqd = data; struct io_ring_ctx *ctx; unsigned long timeout = 0; char buf[TASK_COMM_LEN]; DEFINE_WAIT(wait); snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); if (sqd->sq_cpu != -1) set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); else set_cpus_allowed_ptr(current, cpu_online_mask); current->flags |= PF_NO_SETAFFINITY; mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; if (io_sqd_events_pending(sqd) || signal_pending(current)) { if (io_sqd_handle_event(sqd)) break; timeout = jiffies + sqd->sq_thread_idle; } cap_entries = !list_is_singular(&sqd->ctx_list); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { int ret = __io_sq_thread(ctx, cap_entries); if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) sqt_spin = true; } if (io_run_task_work()) sqt_spin = true; if (sqt_spin || !time_after(jiffies, timeout)) { cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; continue; } prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); if (!io_sqd_events_pending(sqd) && !current->task_works) { bool needs_sched = true; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { io_ring_set_wakeup_flag(ctx); if ((ctx->flags & IORING_SETUP_IOPOLL) && !list_empty_careful(&ctx->iopoll_list)) { needs_sched = false; break; } if (io_sqring_entries(ctx)) { needs_sched = false; break; } } if (needs_sched) { mutex_unlock(&sqd->lock); schedule(); mutex_lock(&sqd->lock); } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_clear_wakeup_flag(ctx); } finish_wait(&sqd->wait, &wait); timeout = jiffies + sqd->sq_thread_idle; } io_uring_cancel_generic(true, sqd); sqd->thread = NULL; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_set_wakeup_flag(ctx); io_run_task_work(); mutex_unlock(&sqd->lock); complete(&sqd->exited); do_exit(0); } struct io_wait_queue { struct wait_queue_entry wq; struct io_ring_ctx *ctx; unsigned cq_tail; unsigned nr_timeouts; }; static inline bool io_should_wake(struct io_wait_queue *iowq) { struct io_ring_ctx *ctx = iowq->ctx; int dist = ctx->cached_cq_tail - (int) iowq->cq_tail; /* * Wake up if we have enough events, or if a timeout occurred since we * started waiting. For timeouts, we always want to return to userspace, * regardless of event count. */ return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts; } static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, int wake_flags, void *key) { struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq); /* * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } static int io_run_task_work_sig(void) { if (io_run_task_work()) return 1; if (!signal_pending(current)) return 0; if (test_thread_flag(TIF_NOTIFY_SIGNAL)) return -ERESTARTSYS; return -EINTR; } static bool current_pending_io(void) { struct io_uring_task *tctx = current->io_uring; if (!tctx) return false; return percpu_counter_read_positive(&tctx->inflight); } /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, ktime_t *timeout) { int ret; /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); if (ret || io_should_wake(iowq)) return ret; /* let the caller flush overflows, retry */ if (test_bit(0, &ctx->check_cq_overflow)) return 1; /* * Mark us as being in io_wait if we have pending requests, so cpufreq * can take into account that the task is waiting for IO - turns out * to be important for low QD IO. */ if (current_pending_io()) current->in_iowait = 1; ret = 1; if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) ret = -ETIME; current->in_iowait = 0; return ret; } /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. */ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, const sigset_t __user *sig, size_t sigsz, struct __kernel_timespec __user *uts) { struct io_wait_queue iowq; struct io_rings *rings = ctx->rings; ktime_t timeout = KTIME_MAX; int ret; do { io_cqring_overflow_flush(ctx); if (io_cqring_events(ctx) >= min_events) return 0; if (!io_run_task_work()) break; } while (1); if (uts) { struct timespec64 ts; if (get_timespec64(&ts, uts)) return -EFAULT; timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } if (sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, sigsz); else #endif ret = set_user_sigmask(sig, sigsz); if (ret) return ret; } init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); iowq.ctx = ctx; iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts); iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; trace_io_uring_cqring_wait(ctx, min_events); do { /* if we can't even flush overflow, don't wait for more */ if (!io_cqring_overflow_flush(ctx)) { ret = -EBUSY; break; } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); restore_saved_sigmask_unless(ret == -EINTR); return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } static void io_free_page_table(void **table, size_t size) { unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); for (i = 0; i < nr_tables; i++) kfree(table[i]); kfree(table); } static void **io_alloc_page_table(size_t size) { unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); size_t init_size = size; void **table; table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT); if (!table) return NULL; for (i = 0; i < nr_tables; i++) { unsigned int this_size = min_t(size_t, size, PAGE_SIZE); table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT); if (!table[i]) { io_free_page_table(table, init_size); return NULL; } size -= this_size; } return table; } static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) { percpu_ref_exit(&ref_node->refs); kfree(ref_node); } static void io_rsrc_node_ref_zero(struct percpu_ref *ref) { struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); struct io_ring_ctx *ctx = node->rsrc_data->ctx; unsigned long flags; bool first_add = false; unsigned long delay = HZ; spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); node->done = true; /* if we are mid-quiesce then do not delay */ if (node->rsrc_data->quiesce) delay = 0; while (!list_empty(&ctx->rsrc_ref_list)) { node = list_first_entry(&ctx->rsrc_ref_list, struct io_rsrc_node, node); /* recycle ref nodes in order */ if (!node->done) break; list_del(&node->node); first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); } spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); if (first_add) mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); } static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) { struct io_rsrc_node *ref_node; ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL); if (!ref_node) return NULL; if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero, 0, GFP_KERNEL)) { kfree(ref_node); return NULL; } INIT_LIST_HEAD(&ref_node->node); INIT_LIST_HEAD(&ref_node->rsrc_list); ref_node->done = false; return ref_node; } static void io_rsrc_node_switch(struct io_ring_ctx *ctx, struct io_rsrc_data *data_to_kill) { WARN_ON_ONCE(!ctx->rsrc_backup_node); WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); if (data_to_kill) { struct io_rsrc_node *rsrc_node = ctx->rsrc_node; rsrc_node->rsrc_data = data_to_kill; spin_lock_irq(&ctx->rsrc_ref_lock); list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); spin_unlock_irq(&ctx->rsrc_ref_lock); atomic_inc(&data_to_kill->refs); percpu_ref_kill(&rsrc_node->refs); ctx->rsrc_node = NULL; } if (!ctx->rsrc_node) { ctx->rsrc_node = ctx->rsrc_backup_node; ctx->rsrc_backup_node = NULL; } } static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) { if (ctx->rsrc_backup_node) return 0; ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx); return ctx->rsrc_backup_node ? 0 : -ENOMEM; } static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx) { int ret; /* As we may drop ->uring_lock, other task may have started quiesce */ if (data->quiesce) return -ENXIO; data->quiesce = true; do { ret = io_rsrc_node_switch_start(ctx); if (ret) break; io_rsrc_node_switch(ctx, data); /* kill initial ref, already quiesced if zero */ if (atomic_dec_and_test(&data->refs)) break; mutex_unlock(&ctx->uring_lock); flush_delayed_work(&ctx->rsrc_put_work); ret = wait_for_completion_interruptible(&data->done); if (!ret) { mutex_lock(&ctx->uring_lock); if (atomic_read(&data->refs) > 0) { /* * it has been revived by another thread while * we were unlocked */ mutex_unlock(&ctx->uring_lock); } else { break; } } atomic_inc(&data->refs); /* wait for all works potentially completing data->done */ flush_delayed_work(&ctx->rsrc_put_work); reinit_completion(&data->done); ret = io_run_task_work_sig(); mutex_lock(&ctx->uring_lock); } while (ret >= 0); data->quiesce = false; return ret; } static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) { unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; return &data->tags[table_idx][off]; } static void io_rsrc_data_free(struct io_rsrc_data *data) { size_t size = data->nr * sizeof(data->tags[0][0]); if (data->tags) io_free_page_table((void **)data->tags, size); kfree(data); } static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, u64 __user *utags, unsigned nr, struct io_rsrc_data **pdata) { struct io_rsrc_data *data; int ret = -ENOMEM; unsigned i; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); if (!data->tags) { kfree(data); return -ENOMEM; } data->nr = nr; data->ctx = ctx; data->do_put = do_put; if (utags) { ret = -EFAULT; for (i = 0; i < nr; i++) { u64 *tag_slot = io_get_tag_slot(data, i); if (copy_from_user(tag_slot, &utags[i], sizeof(*tag_slot))) goto fail; } } atomic_set(&data->refs, 1); init_completion(&data->done); *pdata = data; return 0; fail: io_rsrc_data_free(data); return ret; } static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) { table->files = kvcalloc(nr_files, sizeof(table->files[0]), GFP_KERNEL_ACCOUNT); return !!table->files; } static void io_free_file_tables(struct io_file_table *table) { kvfree(table->files); table->files = NULL; } static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) { int i; for (i = 0; i < ctx->nr_user_files; i++) { struct file *file; file = io_file_from_index(ctx, i); if (file) fput(file); } io_free_file_tables(&ctx->file_table); io_rsrc_data_free(ctx->file_data); ctx->file_data = NULL; ctx->nr_user_files = 0; } static int io_sqe_files_unregister(struct io_ring_ctx *ctx) { unsigned nr = ctx->nr_user_files; int ret; if (!ctx->file_data) return -ENXIO; /* * Quiesce may unlock ->uring_lock, and while it's not held * prevent new requests using the table. */ ctx->nr_user_files = 0; ret = io_rsrc_ref_quiesce(ctx->file_data, ctx); ctx->nr_user_files = nr; if (!ret) __io_sqe_files_unregister(ctx); return ret; } static void io_sq_thread_unpark(struct io_sq_data *sqd) __releases(&sqd->lock) { WARN_ON_ONCE(sqd->thread == current); /* * Do the dance but not conditional clear_bit() because it'd race with * other threads incrementing park_pending and setting the bit. */ clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); if (atomic_dec_return(&sqd->park_pending)) set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); mutex_unlock(&sqd->lock); } static void io_sq_thread_park(struct io_sq_data *sqd) __acquires(&sqd->lock) { WARN_ON_ONCE(sqd->thread == current); atomic_inc(&sqd->park_pending); set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); mutex_lock(&sqd->lock); if (sqd->thread) wake_up_process(sqd->thread); } static void io_sq_thread_stop(struct io_sq_data *sqd) { WARN_ON_ONCE(sqd->thread == current); WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)); set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); mutex_lock(&sqd->lock); if (sqd->thread) wake_up_process(sqd->thread); mutex_unlock(&sqd->lock); wait_for_completion(&sqd->exited); } static void io_put_sq_data(struct io_sq_data *sqd) { if (refcount_dec_and_test(&sqd->refs)) { WARN_ON_ONCE(atomic_read(&sqd->park_pending)); io_sq_thread_stop(sqd); kfree(sqd); } } static void io_sq_thread_finish(struct io_ring_ctx *ctx) { struct io_sq_data *sqd = ctx->sq_data; if (sqd) { io_sq_thread_park(sqd); list_del_init(&ctx->sqd_list); io_sqd_update_thread_idle(sqd); io_sq_thread_unpark(sqd); io_put_sq_data(sqd); ctx->sq_data = NULL; } } static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p) { struct io_ring_ctx *ctx_attach; struct io_sq_data *sqd; struct fd f; f = fdget(p->wq_fd); if (!f.file) return ERR_PTR(-ENXIO); if (f.file->f_op != &io_uring_fops) { fdput(f); return ERR_PTR(-EINVAL); } ctx_attach = f.file->private_data; sqd = ctx_attach->sq_data; if (!sqd) { fdput(f); return ERR_PTR(-EINVAL); } if (sqd->task_tgid != current->tgid) { fdput(f); return ERR_PTR(-EPERM); } refcount_inc(&sqd->refs); fdput(f); return sqd; } static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, bool *attached) { struct io_sq_data *sqd; *attached = false; if (p->flags & IORING_SETUP_ATTACH_WQ) { sqd = io_attach_sq_data(p); if (!IS_ERR(sqd)) { *attached = true; return sqd; } /* fall through for EPERM case, setup new sqd/task */ if (PTR_ERR(sqd) != -EPERM) return sqd; } sqd = kzalloc(sizeof(*sqd), GFP_KERNEL); if (!sqd) return ERR_PTR(-ENOMEM); atomic_set(&sqd->park_pending, 0); refcount_set(&sqd->refs, 1); INIT_LIST_HEAD(&sqd->ctx_list); mutex_init(&sqd->lock); init_waitqueue_head(&sqd->wait); init_completion(&sqd->exited); return sqd; } static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { struct file *file = prsrc->file; fput(file); } static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) { struct io_rsrc_data *rsrc_data = ref_node->rsrc_data; struct io_ring_ctx *ctx = rsrc_data->ctx; struct io_rsrc_put *prsrc, *tmp; list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) { list_del(&prsrc->list); if (prsrc->tag) { bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; io_ring_submit_lock(ctx, lock_ring); spin_lock(&ctx->completion_lock); io_fill_cqe_aux(ctx, prsrc->tag, 0, 0); io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); io_ring_submit_unlock(ctx, lock_ring); } rsrc_data->do_put(ctx, prsrc); kfree(prsrc); } io_rsrc_node_destroy(ref_node); if (atomic_dec_and_test(&rsrc_data->refs)) complete(&rsrc_data->done); } static void io_rsrc_put_work(struct work_struct *work) { struct io_ring_ctx *ctx; struct llist_node *node; ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work); node = llist_del_all(&ctx->rsrc_put_llist); while (node) { struct io_rsrc_node *ref_node; struct llist_node *next = node->next; ref_node = llist_entry(node, struct io_rsrc_node, llist); __io_rsrc_put_work(ref_node); node = next; } } static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args, u64 __user *tags) { __s32 __user *fds = (__s32 __user *) arg; struct file *file; int fd, ret; unsigned i; if (ctx->file_data) return -EBUSY; if (!nr_args) return -EINVAL; if (nr_args > IORING_MAX_FIXED_FILES) return -EMFILE; if (nr_args > rlimit(RLIMIT_NOFILE)) return -EMFILE; ret = io_rsrc_node_switch_start(ctx); if (ret) return ret; ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, &ctx->file_data); if (ret) return ret; ret = -ENOMEM; if (!io_alloc_file_tables(&ctx->file_table, nr_args)) goto out_free; for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { if (copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; goto out_fput; } /* allow sparse sets */ if (fd == -1) { ret = -EINVAL; if (unlikely(*io_get_tag_slot(ctx->file_data, i))) goto out_fput; continue; } file = fget(fd); ret = -EBADF; if (unlikely(!file)) goto out_fput; /* * Don't allow io_uring instances to be registered. If UNIX * isn't enabled, then this causes a reference cycle and this * instance can never get freed. If UNIX is enabled we'll * handle it just fine, but there's still no point in allowing * a ring fd as it doesn't support regular read/write anyway. */ if (file->f_op == &io_uring_fops) { fput(file); goto out_fput; } io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); } io_rsrc_node_switch(ctx, NULL); return 0; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { file = io_file_from_index(ctx, i); if (file) fput(file); } io_free_file_tables(&ctx->file_table); ctx->nr_user_files = 0; out_free: io_rsrc_data_free(ctx->file_data); ctx->file_data = NULL; return ret; } static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { u64 *tag_slot = io_get_tag_slot(data, idx); struct io_rsrc_put *prsrc; prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); if (!prsrc) return -ENOMEM; prsrc->tag = *tag_slot; *tag_slot = 0; prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; } static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index) { struct io_ring_ctx *ctx = req->ctx; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; bool needs_switch = false; struct io_fixed_file *file_slot; int ret = -EBADF; io_ring_submit_lock(ctx, !force_nonblock); if (file->f_op == &io_uring_fops) goto err; ret = -ENXIO; if (!ctx->file_data) goto err; ret = -EINVAL; if (slot_index >= ctx->nr_user_files) goto err; slot_index = array_index_nospec(slot_index, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); if (file_slot->file_ptr) { struct file *old_file; ret = io_rsrc_node_switch_start(ctx); if (ret) goto err; old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); ret = io_queue_rsrc_removal(ctx->file_data, slot_index, ctx->rsrc_node, old_file); if (ret) goto err; file_slot->file_ptr = 0; needs_switch = true; } *io_get_tag_slot(ctx->file_data, slot_index) = 0; io_fixed_file_set(file_slot, file); ret = 0; err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); io_ring_submit_unlock(ctx, !force_nonblock); if (ret) fput(file); return ret; } static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) { unsigned int offset = req->close.file_slot - 1; struct io_ring_ctx *ctx = req->ctx; struct io_fixed_file *file_slot; struct file *file; int ret; io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); ret = -ENXIO; if (unlikely(!ctx->file_data)) goto out; ret = -EINVAL; if (offset >= ctx->nr_user_files) goto out; ret = io_rsrc_node_switch_start(ctx); if (ret) goto out; offset = array_index_nospec(offset, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, offset); ret = -EBADF; if (!file_slot->file_ptr) goto out; file = (struct file *)(file_slot->file_ptr & FFS_MASK); ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); if (ret) goto out; file_slot->file_ptr = 0; io_rsrc_node_switch(ctx, ctx->file_data); ret = 0; out: io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return ret; } static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_rsrc_update2 *up, unsigned nr_args) { u64 __user *tags = u64_to_user_ptr(up->tags); __s32 __user *fds = u64_to_user_ptr(up->data); struct io_rsrc_data *data = ctx->file_data; struct io_fixed_file *file_slot; struct file *file; int fd, i, err = 0; unsigned int done; bool needs_switch = false; if (!ctx->file_data) return -ENXIO; if (up->offset + nr_args > ctx->nr_user_files) return -EINVAL; for (done = 0; done < nr_args; done++) { u64 tag = 0; if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) || copy_from_user(&fd, &fds[done], sizeof(fd))) { err = -EFAULT; break; } if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) { err = -EINVAL; break; } if (fd == IORING_REGISTER_FILES_SKIP) continue; i = array_index_nospec(up->offset + done, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, i); if (file_slot->file_ptr) { file = (struct file *)(file_slot->file_ptr & FFS_MASK); err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; file_slot->file_ptr = 0; needs_switch = true; } if (fd != -1) { file = fget(fd); if (!file) { err = -EBADF; break; } /* * Don't allow io_uring instances to be registered. If * UNIX isn't enabled, then this causes a reference * cycle and this instance can never get freed. If UNIX * is enabled we'll handle it just fine, but there's * still no point in allowing a ring fd as it doesn't * support regular read/write anyway. */ if (file->f_op == &io_uring_fops) { fput(file); err = -EBADF; break; } *io_get_tag_slot(data, i) = tag; io_fixed_file_set(file_slot, file); } } if (needs_switch) io_rsrc_node_switch(ctx, data); return done ? done : err; } static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, struct task_struct *task) { struct io_wq_hash *hash; struct io_wq_data data; unsigned int concurrency; mutex_lock(&ctx->uring_lock); hash = ctx->hash_map; if (!hash) { hash = kzalloc(sizeof(*hash), GFP_KERNEL); if (!hash) { mutex_unlock(&ctx->uring_lock); return ERR_PTR(-ENOMEM); } refcount_set(&hash->refs, 1); init_waitqueue_head(&hash->wait); ctx->hash_map = hash; } mutex_unlock(&ctx->uring_lock); data.hash = hash; data.task = task; data.free_work = io_wq_free_work; data.do_work = io_wq_submit_work; /* Do QD, or 4 * CPUS, whatever is smallest */ concurrency = min(ctx->sq_entries, 4 * num_online_cpus()); return io_wq_create(concurrency, &data); } static int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx) { struct io_uring_task *tctx; int ret; tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); if (unlikely(!tctx)) return -ENOMEM; ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL); if (unlikely(ret)) { kfree(tctx); return ret; } tctx->io_wq = io_init_wq_offload(ctx, task); if (IS_ERR(tctx->io_wq)) { ret = PTR_ERR(tctx->io_wq); percpu_counter_destroy(&tctx->inflight); kfree(tctx); return ret; } xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); init_task_work(&tctx->task_work, tctx_task_work); return 0; } void __io_uring_free(struct task_struct *tsk) { struct io_uring_task *tctx = tsk->io_uring; WARN_ON_ONCE(!xa_empty(&tctx->xa)); WARN_ON_ONCE(tctx->io_wq); WARN_ON_ONCE(tctx->cached_refs); percpu_counter_destroy(&tctx->inflight); kfree(tctx); tsk->io_uring = NULL; } static int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p) { int ret; /* Retain compatibility with failing for an invalid attach attempt */ if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) == IORING_SETUP_ATTACH_WQ) { struct fd f; f = fdget(p->wq_fd); if (!f.file) return -ENXIO; if (f.file->f_op != &io_uring_fops) { fdput(f); return -EINVAL; } fdput(f); } if (ctx->flags & IORING_SETUP_SQPOLL) { struct task_struct *tsk; struct io_sq_data *sqd; bool attached; sqd = io_get_sq_data(p, &attached); if (IS_ERR(sqd)) { ret = PTR_ERR(sqd); goto err; } ctx->sq_creds = get_current_cred(); ctx->sq_data = sqd; ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); if (!ctx->sq_thread_idle) ctx->sq_thread_idle = HZ; io_sq_thread_park(sqd); list_add(&ctx->sqd_list, &sqd->ctx_list); io_sqd_update_thread_idle(sqd); /* don't attach to a dying SQPOLL thread, would be racy */ ret = (attached && !sqd->thread) ? -ENXIO : 0; io_sq_thread_unpark(sqd); if (ret < 0) goto err; if (attached) return 0; if (p->flags & IORING_SETUP_SQ_AFF) { int cpu = p->sq_thread_cpu; ret = -EINVAL; if (cpu >= nr_cpu_ids || !cpu_online(cpu)) goto err_sqpoll; sqd->sq_cpu = cpu; } else { sqd->sq_cpu = -1; } sqd->task_pid = current->pid; sqd->task_tgid = current->tgid; tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE); if (IS_ERR(tsk)) { ret = PTR_ERR(tsk); goto err_sqpoll; } sqd->thread = tsk; ret = io_uring_alloc_task_context(tsk, ctx); wake_up_new_task(tsk); if (ret) goto err; } else if (p->flags & IORING_SETUP_SQ_AFF) { /* Can't have SQ_AFF without SQPOLL */ ret = -EINVAL; goto err; } return 0; err_sqpoll: complete(&ctx->sq_data->exited); err: io_sq_thread_finish(ctx); return ret; } static inline void __io_unaccount_mem(struct user_struct *user, unsigned long nr_pages) { atomic_long_sub(nr_pages, &user->locked_vm); } static inline int __io_account_mem(struct user_struct *user, unsigned long nr_pages) { unsigned long page_limit, cur_pages, new_pages; /* Don't allow more pages than we can safely lock */ page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; do { cur_pages = atomic_long_read(&user->locked_vm); new_pages = cur_pages + nr_pages; if (new_pages > page_limit) return -ENOMEM; } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages, new_pages) != cur_pages); return 0; } static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { if (ctx->user) __io_unaccount_mem(ctx->user, nr_pages); if (ctx->mm_account) atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm); } static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages) { int ret; if (ctx->user) { ret = __io_account_mem(ctx->user, nr_pages); if (ret) return ret; } if (ctx->mm_account) atomic64_add(nr_pages, &ctx->mm_account->pinned_vm); return 0; } static void io_mem_free(void *ptr) { struct page *page; if (!ptr) return; page = virt_to_head_page(ptr); if (put_page_testzero(page)) free_compound_page(page); } static void *io_mem_alloc(size_t size) { gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; return (void *) __get_free_pages(gfp, get_order(size)); } static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries, size_t *sq_offset) { struct io_rings *rings; size_t off, sq_array_size; off = struct_size(rings, cqes, cq_entries); if (off == SIZE_MAX) return SIZE_MAX; #ifdef CONFIG_SMP off = ALIGN(off, SMP_CACHE_BYTES); if (off == 0) return SIZE_MAX; #endif if (sq_offset) *sq_offset = off; sq_array_size = array_size(sizeof(u32), sq_entries); if (sq_array_size == SIZE_MAX) return SIZE_MAX; if (check_add_overflow(off, sq_array_size, &off)) return SIZE_MAX; return off; } static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot) { struct io_mapped_ubuf *imu = *slot; unsigned int i; if (imu != ctx->dummy_ubuf) { for (i = 0; i < imu->nr_bvecs; i++) unpin_user_page(imu->bvec[i].bv_page); if (imu->acct_pages) io_unaccount_mem(ctx, imu->acct_pages); kvfree(imu); } *slot = NULL; } static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { io_buffer_unmap(ctx, &prsrc->buf); prsrc->buf = NULL; } static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx) { unsigned int i; for (i = 0; i < ctx->nr_user_bufs; i++) io_buffer_unmap(ctx, &ctx->user_bufs[i]); kfree(ctx->user_bufs); io_rsrc_data_free(ctx->buf_data); ctx->user_bufs = NULL; ctx->buf_data = NULL; ctx->nr_user_bufs = 0; } static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx) { unsigned nr = ctx->nr_user_bufs; int ret; if (!ctx->buf_data) return -ENXIO; /* * Quiesce may unlock ->uring_lock, and while it's not held * prevent new requests using the table. */ ctx->nr_user_bufs = 0; ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx); ctx->nr_user_bufs = nr; if (!ret) __io_sqe_buffers_unregister(ctx); return ret; } static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst, void __user *arg, unsigned index) { struct iovec __user *src; #ifdef CONFIG_COMPAT if (ctx->compat) { struct compat_iovec __user *ciovs; struct compat_iovec ciov; ciovs = (struct compat_iovec __user *) arg; if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov))) return -EFAULT; dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base); dst->iov_len = ciov.iov_len; return 0; } #endif src = (struct iovec __user *) arg; if (copy_from_user(dst, &src[index], sizeof(*dst))) return -EFAULT; return 0; } /* * Not super efficient, but this is just a registration time. And we do cache * the last compound head, so generally we'll only do a full search if we don't * match that one. * * We check if the given compound head page has already been accounted, to * avoid double accounting it. This allows us to account the full size of the * page, not just the constituent pages of a huge page. */ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages, int nr_pages, struct page *hpage) { int i, j; /* check current page array */ for (i = 0; i < nr_pages; i++) { if (!PageCompound(pages[i])) continue; if (compound_head(pages[i]) == hpage) return true; } /* check previously registered pages */ for (i = 0; i < ctx->nr_user_bufs; i++) { struct io_mapped_ubuf *imu = ctx->user_bufs[i]; for (j = 0; j < imu->nr_bvecs; j++) { if (!PageCompound(imu->bvec[j].bv_page)) continue; if (compound_head(imu->bvec[j].bv_page) == hpage) return true; } } return false; } static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages, int nr_pages, struct io_mapped_ubuf *imu, struct page **last_hpage) { int i, ret; imu->acct_pages = 0; for (i = 0; i < nr_pages; i++) { if (!PageCompound(pages[i])) { imu->acct_pages++; } else { struct page *hpage; hpage = compound_head(pages[i]); if (hpage == *last_hpage) continue; *last_hpage = hpage; if (headpage_already_acct(ctx, pages, i, hpage)) continue; imu->acct_pages += page_size(hpage) >> PAGE_SHIFT; } } if (!imu->acct_pages) return 0; ret = io_account_mem(ctx, imu->acct_pages); if (ret) imu->acct_pages = 0; return ret; } static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, struct io_mapped_ubuf **pimu, struct page **last_hpage) { struct io_mapped_ubuf *imu = NULL; struct vm_area_struct **vmas = NULL; struct page **pages = NULL; unsigned long off, start, end, ubuf; size_t size; int ret, pret, nr_pages, i; if (!iov->iov_base) { *pimu = ctx->dummy_ubuf; return 0; } ubuf = (unsigned long) iov->iov_base; end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; start = ubuf >> PAGE_SHIFT; nr_pages = end - start; *pimu = NULL; ret = -ENOMEM; pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) goto done; vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), GFP_KERNEL); if (!vmas) goto done; imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL); if (!imu) goto done; ret = 0; mmap_read_lock(current->mm); pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM, pages, vmas); if (pret == nr_pages) { struct file *file = vmas[0]->vm_file; /* don't support file backed memory */ for (i = 0; i < nr_pages; i++) { if (vmas[i]->vm_file != file) { ret = -EINVAL; break; } if (!file) continue; if (!vma_is_shmem(vmas[i]) && !is_file_hugepages(file)) { ret = -EOPNOTSUPP; break; } } } else { ret = pret < 0 ? pret : -EFAULT; } mmap_read_unlock(current->mm); if (ret) { /* * if we did partial map, or found file backed vmas, * release any pages we did get */ if (pret > 0) unpin_user_pages(pages, pret); goto done; } ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage); if (ret) { unpin_user_pages(pages, pret); goto done; } off = ubuf & ~PAGE_MASK; size = iov->iov_len; for (i = 0; i < nr_pages; i++) { size_t vec_len; vec_len = min_t(size_t, size, PAGE_SIZE - off); imu->bvec[i].bv_page = pages[i]; imu->bvec[i].bv_len = vec_len; imu->bvec[i].bv_offset = off; off = 0; size -= vec_len; } /* store original address for later verification */ imu->ubuf = ubuf; imu->ubuf_end = ubuf + iov->iov_len; imu->nr_bvecs = nr_pages; *pimu = imu; ret = 0; done: if (ret) kvfree(imu); kvfree(pages); kvfree(vmas); return ret; } static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args) { ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL); return ctx->user_bufs ? 0 : -ENOMEM; } static int io_buffer_validate(struct iovec *iov) { unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1); /* * Don't impose further limits on the size and buffer * constraints here, we'll -EINVAL later when IO is * submitted if they are wrong. */ if (!iov->iov_base) return iov->iov_len ? -EFAULT : 0; if (!iov->iov_len) return -EFAULT; /* arbitrary limit, but we need something */ if (iov->iov_len > SZ_1G) return -EFAULT; if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp)) return -EOVERFLOW; return 0; } static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, unsigned int nr_args, u64 __user *tags) { struct page *last_hpage = NULL; struct io_rsrc_data *data; int i, ret; struct iovec iov; if (ctx->user_bufs) return -EBUSY; if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) return -EINVAL; ret = io_rsrc_node_switch_start(ctx); if (ret) return ret; ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); if (ret) return ret; ret = io_buffers_map_alloc(ctx, nr_args); if (ret) { io_rsrc_data_free(data); return ret; } for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { ret = io_copy_iov(ctx, &iov, arg, i); if (ret) break; ret = io_buffer_validate(&iov); if (ret) break; if (!iov.iov_base && *io_get_tag_slot(data, i)) { ret = -EINVAL; break; } ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i], &last_hpage); if (ret) break; } WARN_ON_ONCE(ctx->buf_data); ctx->buf_data = data; if (ret) __io_sqe_buffers_unregister(ctx); else io_rsrc_node_switch(ctx, NULL); return ret; } static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, struct io_uring_rsrc_update2 *up, unsigned int nr_args) { u64 __user *tags = u64_to_user_ptr(up->tags); struct iovec iov, __user *iovs = u64_to_user_ptr(up->data); struct page *last_hpage = NULL; bool needs_switch = false; __u32 done; int i, err; if (!ctx->buf_data) return -ENXIO; if (up->offset + nr_args > ctx->nr_user_bufs) return -EINVAL; for (done = 0; done < nr_args; done++) { struct io_mapped_ubuf *imu; int offset = up->offset + done; u64 tag = 0; err = io_copy_iov(ctx, &iov, iovs, done); if (err) break; if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) { err = -EFAULT; break; } err = io_buffer_validate(&iov); if (err) break; if (!iov.iov_base && tag) { err = -EINVAL; break; } err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage); if (err) break; i = array_index_nospec(offset, ctx->nr_user_bufs); if (ctx->user_bufs[i] != ctx->dummy_ubuf) { err = io_queue_rsrc_removal(ctx->buf_data, i, ctx->rsrc_node, ctx->user_bufs[i]); if (unlikely(err)) { io_buffer_unmap(ctx, &imu); break; } ctx->user_bufs[i] = NULL; needs_switch = true; } ctx->user_bufs[i] = imu; *io_get_tag_slot(ctx->buf_data, offset) = tag; } if (needs_switch) io_rsrc_node_switch(ctx, ctx->buf_data); return done ? done : err; } static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) { __s32 __user *fds = arg; int fd; if (ctx->cq_ev_fd) return -EBUSY; if (copy_from_user(&fd, fds, sizeof(*fds))) return -EFAULT; ctx->cq_ev_fd = eventfd_ctx_fdget(fd); if (IS_ERR(ctx->cq_ev_fd)) { int ret = PTR_ERR(ctx->cq_ev_fd); ctx->cq_ev_fd = NULL; return ret; } return 0; } static int io_eventfd_unregister(struct io_ring_ctx *ctx) { if (ctx->cq_ev_fd) { eventfd_ctx_put(ctx->cq_ev_fd); ctx->cq_ev_fd = NULL; return 0; } return -ENXIO; } static void io_destroy_buffers(struct io_ring_ctx *ctx) { struct io_buffer *buf; unsigned long index; xa_for_each(&ctx->io_buffers, index, buf) __io_remove_buffers(ctx, buf, index, -1U); } static void io_req_cache_free(struct list_head *list) { struct io_kiocb *req, *nxt; list_for_each_entry_safe(req, nxt, list, inflight_entry) { list_del(&req->inflight_entry); kmem_cache_free(req_cachep, req); } } static void io_req_caches_free(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; mutex_lock(&ctx->uring_lock); if (state->free_reqs) { kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); state->free_reqs = 0; } io_flush_cached_locked_reqs(ctx, state); io_req_cache_free(&state->free_list); mutex_unlock(&ctx->uring_lock); } static void io_wait_rsrc_data(struct io_rsrc_data *data) { if (data && !atomic_dec_and_test(&data->refs)) wait_for_completion(&data->done); } static void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_sq_thread_finish(ctx); /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ io_wait_rsrc_data(ctx->buf_data); io_wait_rsrc_data(ctx->file_data); mutex_lock(&ctx->uring_lock); if (ctx->buf_data) __io_sqe_buffers_unregister(ctx); if (ctx->file_data) __io_sqe_files_unregister(ctx); if (ctx->rings) __io_cqring_overflow_flush(ctx, true); mutex_unlock(&ctx->uring_lock); io_eventfd_unregister(ctx); io_destroy_buffers(ctx); if (ctx->sq_creds) put_cred(ctx->sq_creds); /* there are no registered resources left, nobody uses it */ if (ctx->rsrc_node) io_rsrc_node_destroy(ctx->rsrc_node); if (ctx->rsrc_backup_node) io_rsrc_node_destroy(ctx->rsrc_backup_node); flush_delayed_work(&ctx->rsrc_put_work); WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); if (ctx->mm_account) { mmdrop(ctx->mm_account); ctx->mm_account = NULL; } io_mem_free(ctx->rings); io_mem_free(ctx->sq_sqes); percpu_ref_exit(&ctx->refs); free_uid(ctx->user); io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); kfree(ctx); } static __poll_t io_uring_poll(struct file *file, poll_table *wait) { struct io_ring_ctx *ctx = file->private_data; __poll_t mask = 0; poll_wait(file, &ctx->poll_wait, wait); /* * synchronizes with barrier from wq_has_sleeper call in * io_commit_cqring */ smp_rmb(); if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Don't flush cqring overflow list here, just do a simple check. * Otherwise there could possible be ABBA deadlock: * CPU0 CPU1 * ---- ---- * lock(&ctx->uring_lock); * lock(&ep->mtx); * lock(&ctx->uring_lock); * lock(&ep->mtx); * * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushs them to do the flush. */ if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { const struct cred *creds; creds = xa_erase(&ctx->personalities, id); if (creds) { put_cred(creds); return 0; } return -EINVAL; } struct io_tctx_exit { struct callback_head task_work; struct completion completion; struct io_ring_ctx *ctx; }; static void io_tctx_exit_cb(struct callback_head *cb) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_exit *work; work = container_of(cb, struct io_tctx_exit, task_work); /* * When @in_idle, we're in cancellation and it's racy to remove the * node. It'll be removed by the end of cancellation, just ignore it. * tctx can be NULL if the queueing of this task_work raced with * work cancelation off the exec path. */ if (tctx && !atomic_read(&tctx->in_idle)) io_uring_del_tctx_node((unsigned long)work->ctx); complete(&work->completion); } static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); return req->ctx == data; } static void io_ring_exit_work(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); unsigned long timeout = jiffies + HZ * 60 * 5; unsigned long interval = HZ / 20; struct io_tctx_exit exit; struct io_tctx_node *node; int ret; /* * If we're doing polled IO and end up having requests being * submitted async (out-of-line), then completions can come in while * we're waiting for refs to drop. We need to reap these manually, * as nobody else will be looking for them. */ do { io_uring_try_cancel_requests(ctx, NULL, true); if (ctx->sq_data) { struct io_sq_data *sqd = ctx->sq_data; struct task_struct *tsk; io_sq_thread_park(sqd); tsk = sqd->thread; if (tsk && tsk->io_uring && tsk->io_uring->io_wq) io_wq_cancel_cb(tsk->io_uring->io_wq, io_cancel_ctx_cb, ctx, true); io_sq_thread_unpark(sqd); } if (WARN_ON_ONCE(time_after(jiffies, timeout))) { /* there is little hope left, don't run it too often */ interval = HZ * 60; } /* * This is really an uninterruptible wait, as it has to be * complete. But it's also run from a kworker, which doesn't * take signals, so it's fine to make it interruptible. This * avoids scenarios where we knowingly can wait much longer * on completions, for example if someone does a SIGSTOP on * a task that needs to finish task_work to make this loop * complete. That's a synthetic situation that should not * cause a stuck task backtrace, and hence a potential panic * on stuck tasks if that is enabled. */ } while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval)); init_completion(&exit.completion); init_task_work(&exit.task_work, io_tctx_exit_cb); exit.ctx = ctx; /* * Some may use context even when all refs and requests have been put, * and they are free to do so while still holding uring_lock or * completion_lock, see io_req_task_submit(). Apart from other work, * this lock/unlock section also waits them to finish. */ mutex_lock(&ctx->uring_lock); while (!list_empty(&ctx->tctx_list)) { WARN_ON_ONCE(time_after(jiffies, timeout)); node = list_first_entry(&ctx->tctx_list, struct io_tctx_node, ctx_node); /* don't spin on a single task if cancellation failed */ list_rotate_left(&ctx->tctx_list); ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); if (WARN_ON_ONCE(ret)) continue; wake_up_process(node->task); mutex_unlock(&ctx->uring_lock); /* * See comment above for * wait_for_completion_interruptible_timeout() on why this * wait is marked as interruptible. */ wait_for_completion_interruptible(&exit.completion); mutex_lock(&ctx->uring_lock); } mutex_unlock(&ctx->uring_lock); spin_lock(&ctx->completion_lock); spin_unlock(&ctx->completion_lock); io_ring_ctx_free(ctx); } /* Returns true if we found and killed one or more timeouts */ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, bool cancel_all) { struct io_kiocb *req, *tmp; int canceled = 0; spin_lock(&ctx->completion_lock); spin_lock_irq(&ctx->timeout_lock); list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { if (io_match_task(req, tsk, cancel_all)) { io_kill_timeout(req, -ECANCELED); canceled++; } } spin_unlock_irq(&ctx->timeout_lock); if (canceled != 0) io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); if (canceled != 0) io_cqring_ev_posted(ctx); return canceled != 0; } static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; struct creds *creds; mutex_lock(&ctx->uring_lock); percpu_ref_kill(&ctx->refs); if (ctx->rings) __io_cqring_overflow_flush(ctx, true); xa_for_each(&ctx->personalities, index, creds) io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); io_kill_timeouts(ctx, NULL, true); io_poll_remove_all(ctx, NULL, true); /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); /* drop cached put refs after potentially doing completions */ if (current->io_uring) io_uring_drop_tctx_refs(current); INIT_WORK(&ctx->exit_work, io_ring_exit_work); /* * Use system_unbound_wq to avoid spawning tons of event kworkers * if we're exiting a ton of rings at the same time. It just adds * noise and overhead, there's no discernable change in runtime * over using system_wq. */ queue_work(system_unbound_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) { struct io_ring_ctx *ctx = file->private_data; file->private_data = NULL; io_ring_ctx_wait_and_kill(ctx); return 0; } struct io_task_cancel { struct task_struct *task; bool all; }; static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; return io_match_task_safe(req, cancel->task, cancel->all); } static bool io_cancel_defer_files(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all) { struct io_defer_entry *de; LIST_HEAD(list); spin_lock(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { if (io_match_task_safe(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } } spin_unlock(&ctx->completion_lock); if (list_empty(&list)) return false; while (!list_empty(&list)) { de = list_first_entry(&list, struct io_defer_entry, list); list_del_init(&de->list); io_req_complete_failed(de->req, -ECANCELED); kfree(de); } return true; } static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { struct io_tctx_node *node; enum io_wq_cancel cret; bool ret = false; mutex_lock(&ctx->uring_lock); list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; /* * io_wq will stay alive while we hold uring_lock, because it's * killed after ctx nodes, which requires to take the lock. */ if (!tctx || !tctx->io_wq) continue; cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } mutex_unlock(&ctx->uring_lock); return ret; } static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all) { struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; struct io_uring_task *tctx = task ? task->io_uring : NULL; while (1) { enum io_wq_cancel cret; bool ret = false; if (!task) { ret |= io_uring_try_cancel_iowq(ctx); } else if (tctx && tctx->io_wq) { /* * Cancels requests of all rings, not only @ctx, but * it's fine as the task is in exit/exec. */ cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb, &cancel, true); ret |= (cret != IO_WQ_CANCEL_NOTFOUND); } /* SQPOLL thread does its own polling */ if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || (ctx->sq_data && ctx->sq_data->thread == current)) { while (!list_empty_careful(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; cond_resched(); } } ret |= io_cancel_defer_files(ctx, task, cancel_all); ret |= io_poll_remove_all(ctx, task, cancel_all); ret |= io_kill_timeouts(ctx, task, cancel_all); if (task) ret |= io_run_task_work(); if (!ret) break; cond_resched(); } } static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; int ret; if (unlikely(!tctx)) { ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) return ret; tctx = current->io_uring; if (ctx->iowq_limits_set) { unsigned int limits[2] = { ctx->iowq_limits[0], ctx->iowq_limits[1], }; ret = io_wq_max_workers(tctx->io_wq, limits); if (ret) return ret; } } if (!xa_load(&tctx->xa, (unsigned long)ctx)) { node = kmalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; node->ctx = ctx; node->task = current; ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx, node, GFP_KERNEL)); if (ret) { kfree(node); return ret; } mutex_lock(&ctx->uring_lock); list_add(&node->ctx_node, &ctx->tctx_list); mutex_unlock(&ctx->uring_lock); } tctx->last = ctx; return 0; } /* * Note that this task has used io_uring. We use it for cancelation purposes. */ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; if (likely(tctx && tctx->last == ctx)) return 0; return __io_uring_add_tctx_node(ctx); } /* * Remove this io_uring_file -> task mapping. */ static void io_uring_del_tctx_node(unsigned long index) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; if (!tctx) return; node = xa_erase(&tctx->xa, index); if (!node) return; WARN_ON_ONCE(current != node->task); WARN_ON_ONCE(list_empty(&node->ctx_node)); mutex_lock(&node->ctx->uring_lock); list_del(&node->ctx_node); mutex_unlock(&node->ctx->uring_lock); if (tctx->last == node->ctx) tctx->last = NULL; kfree(node); } static void io_uring_clean_tctx(struct io_uring_task *tctx) { struct io_wq *wq = tctx->io_wq; struct io_tctx_node *node; unsigned long index; xa_for_each(&tctx->xa, index, node) { io_uring_del_tctx_node(index); cond_resched(); } if (wq) { /* * Must be after io_uring_del_task_file() (removes nodes under * uring_lock) to avoid race with io_uring_try_cancel_iowq(). */ io_wq_put_and_exit(wq); tctx->io_wq = NULL; } } static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) return atomic_read(&tctx->inflight_tracked); return percpu_counter_sum(&tctx->inflight); } /* * Find any io_uring ctx that this task has registered or done IO on, and cancel * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. */ static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) { struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx; s64 inflight; DEFINE_WAIT(wait); WARN_ON_ONCE(sqd && sqd->thread != current); if (!current->io_uring) return; if (tctx->io_wq) io_wq_exit_start(tctx->io_wq); atomic_inc(&tctx->in_idle); do { io_uring_drop_tctx_refs(current); /* read completions before cancelations */ inflight = tctx_inflight(tctx, !cancel_all); if (!inflight) break; if (!sqd) { struct io_tctx_node *node; unsigned long index; xa_for_each(&tctx->xa, index, node) { /* sqpoll task will cancel all its requests */ if (node->ctx->sq_data) continue; io_uring_try_cancel_requests(node->ctx, current, cancel_all); } } else { list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_uring_try_cancel_requests(ctx, current, cancel_all); } prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); io_run_task_work(); io_uring_drop_tctx_refs(current); /* * If we've seen completions, retry without waiting. This * avoids a race where a completion comes in before we did * prepare_to_wait(). */ if (inflight == tctx_inflight(tctx, !cancel_all)) schedule(); finish_wait(&tctx->wait, &wait); } while (1); io_uring_clean_tctx(tctx); if (cancel_all) { /* * We shouldn't run task_works after cancel, so just leave * ->in_idle set for normal exit. */ atomic_dec(&tctx->in_idle); /* for exec all current's requests should be gone, kill tctx */ __io_uring_free(current); } } void __io_uring_cancel(bool cancel_all) { io_uring_cancel_generic(cancel_all, NULL); } static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff, size_t sz) { struct io_ring_ctx *ctx = file->private_data; loff_t offset = pgoff << PAGE_SHIFT; struct page *page; void *ptr; switch (offset) { case IORING_OFF_SQ_RING: case IORING_OFF_CQ_RING: ptr = ctx->rings; break; case IORING_OFF_SQES: ptr = ctx->sq_sqes; break; default: return ERR_PTR(-EINVAL); } page = virt_to_head_page(ptr); if (sz > page_size(page)) return ERR_PTR(-EINVAL); return ptr; } #ifdef CONFIG_MMU static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { size_t sz = vma->vm_end - vma->vm_start; unsigned long pfn; void *ptr; ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz); if (IS_ERR(ptr)) return PTR_ERR(ptr); pfn = virt_to_phys(ptr) >> PAGE_SHIFT; return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot); } #else /* !CONFIG_MMU */ static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL; } static unsigned int io_uring_nommu_mmap_capabilities(struct file *file) { return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE; } static unsigned long io_uring_nommu_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { void *ptr; ptr = io_uring_validate_mmap_request(file, pgoff, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); return (unsigned long) ptr; } #endif /* !CONFIG_MMU */ static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx) { DEFINE_WAIT(wait); do { if (!io_sqring_full(ctx)) break; prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE); if (!io_sqring_full(ctx)) break; schedule(); } while (!signal_pending(current)); finish_wait(&ctx->sqo_sq_wait, &wait); return 0; } static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz, struct __kernel_timespec __user **ts, const sigset_t __user **sig) { struct io_uring_getevents_arg arg; /* * If EXT_ARG isn't set, then we have no timespec and the argp pointer * is just a pointer to the sigset_t. */ if (!(flags & IORING_ENTER_EXT_ARG)) { *sig = (const sigset_t __user *) argp; *ts = NULL; return 0; } /* * EXT_ARG is set - ensure we agree on the size of it and copy in our * timespec and sigset_t pointers if good. */ if (*argsz != sizeof(arg)) return -EINVAL; if (copy_from_user(&arg, argp, sizeof(arg))) return -EFAULT; if (arg.pad) return -EINVAL; *sig = u64_to_user_ptr(arg.sigmask); *argsz = arg.sigmask_sz; *ts = u64_to_user_ptr(arg.ts); return 0; } SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, u32, min_complete, u32, flags, const void __user *, argp, size_t, argsz) { struct io_ring_ctx *ctx; int submitted = 0; struct fd f; long ret; io_run_task_work(); if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP | IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG))) return -EINVAL; f = fdget(fd); if (unlikely(!f.file)) return -EBADF; ret = -EOPNOTSUPP; if (unlikely(f.file->f_op != &io_uring_fops)) goto out_fput; ret = -ENXIO; ctx = f.file->private_data; if (unlikely(!percpu_ref_tryget(&ctx->refs))) goto out_fput; ret = -EBADFD; if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED)) goto out; /* * For SQ polling, the thread will do all submissions and completions. * Just return the requested submit count, and wake the thread if * we were asked to. */ ret = 0; if (ctx->flags & IORING_SETUP_SQPOLL) { io_cqring_overflow_flush(ctx); if (unlikely(ctx->sq_data->thread == NULL)) { ret = -EOWNERDEAD; goto out; } if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sq_data->wait); if (flags & IORING_ENTER_SQ_WAIT) { ret = io_sqpoll_wait_sq(ctx); if (ret) goto out; } submitted = to_submit; } else if (to_submit) { ret = io_uring_add_tctx_node(ctx); if (unlikely(ret)) goto out; mutex_lock(&ctx->uring_lock); submitted = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); if (submitted != to_submit) goto out; } if (flags & IORING_ENTER_GETEVENTS) { const sigset_t __user *sig; struct __kernel_timespec __user *ts; ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig); if (unlikely(ret)) goto out; min_complete = min(min_complete, ctx->cq_entries); /* * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user * space applications don't need to do io completion events * polling again, they can rely on io_sq_thread to do polling * work, which can reduce cpu usage and uring_lock contention. */ if (ctx->flags & IORING_SETUP_IOPOLL && !(ctx->flags & IORING_SETUP_SQPOLL)) { ret = io_iopoll_check(ctx, min_complete); } else { ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts); } } out: percpu_ref_put(&ctx->refs); out_fput: fdput(f); return submitted ? submitted : ret; } #ifdef CONFIG_PROC_FS static int io_uring_show_cred(struct seq_file *m, unsigned int id, const struct cred *cred) { struct user_namespace *uns = seq_user_ns(m); struct group_info *gi; kernel_cap_t cap; unsigned __capi; int g; seq_printf(m, "%5d\n", id); seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid)); seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid)); seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid)); seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid)); seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid)); seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid)); seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid)); seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid)); seq_puts(m, "\n\tGroups:\t"); gi = cred->group_info; for (g = 0; g < gi->ngroups; g++) { seq_put_decimal_ull(m, g ? " " : "", from_kgid_munged(uns, gi->gid[g])); } seq_puts(m, "\n\tCapEff:\t"); cap = cred->cap_effective; CAP_FOR_EACH_U32(__capi) seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8); seq_putc(m, '\n'); return 0; } static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { int sq_pid = -1, sq_cpu = -1; bool has_lock; int i; /* * Avoid ABBA deadlock between the seq lock and the io_uring mutex, * since fdinfo case grabs it in the opposite direction of normal use * cases. If we fail to get the lock, we just don't iterate any * structures that could be going away outside the io_uring mutex. */ has_lock = mutex_trylock(&ctx->uring_lock); if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { struct io_sq_data *sq = ctx->sq_data; if (mutex_trylock(&sq->lock)) { if (sq->thread) { sq_pid = task_pid_nr(sq->thread); sq_cpu = task_cpu(sq->thread); } mutex_unlock(&sq->lock); } } seq_printf(m, "SqThread:\t%d\n", sq_pid); seq_printf(m, "SqThreadCpu:\t%d\n", sq_cpu); seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); for (i = 0; has_lock && i < ctx->nr_user_files; i++) { struct file *f = io_file_from_index(ctx, i); if (f) seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname); else seq_printf(m, "%5u: <none>\n", i); } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { struct io_mapped_ubuf *buf = ctx->user_bufs[i]; unsigned int len = buf->ubuf_end - buf->ubuf; seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len); } if (has_lock && !xa_empty(&ctx->personalities)) { unsigned long index; const struct cred *cred; seq_printf(m, "Personalities:\n"); xa_for_each(&ctx->personalities, index, cred) io_uring_show_cred(m, index, cred); } seq_printf(m, "PollList:\n"); spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list = &ctx->cancel_hash[i]; struct io_kiocb *req; hlist_for_each_entry(req, list, hash_node) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, req->task->task_works != NULL); } spin_unlock(&ctx->completion_lock); if (has_lock) mutex_unlock(&ctx->uring_lock); } static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) { struct io_ring_ctx *ctx = f->private_data; if (percpu_ref_tryget(&ctx->refs)) { __io_uring_show_fdinfo(ctx, m); percpu_ref_put(&ctx->refs); } } #endif static const struct file_operations io_uring_fops = { .release = io_uring_release, .mmap = io_uring_mmap, #ifndef CONFIG_MMU .get_unmapped_area = io_uring_nommu_get_unmapped_area, .mmap_capabilities = io_uring_nommu_mmap_capabilities, #endif .poll = io_uring_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, #endif }; bool io_is_uring_fops(struct file *file) { return file->f_op == &io_uring_fops; } static int io_allocate_scq_urings(struct io_ring_ctx *ctx, struct io_uring_params *p) { struct io_rings *rings; size_t size, sq_array_offset; /* make sure these are sane, as we already accounted them */ ctx->sq_entries = p->sq_entries; ctx->cq_entries = p->cq_entries; size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset); if (size == SIZE_MAX) return -EOVERFLOW; rings = io_mem_alloc(size); if (!rings) return -ENOMEM; ctx->rings = rings; ctx->sq_array = (u32 *)((char *)rings + sq_array_offset); rings->sq_ring_mask = p->sq_entries - 1; rings->cq_ring_mask = p->cq_entries - 1; rings->sq_ring_entries = p->sq_entries; rings->cq_ring_entries = p->cq_entries; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { io_mem_free(ctx->rings); ctx->rings = NULL; return -EOVERFLOW; } ctx->sq_sqes = io_mem_alloc(size); if (!ctx->sq_sqes) { io_mem_free(ctx->rings); ctx->rings = NULL; return -ENOMEM; } return 0; } static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) { int ret, fd; fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (fd < 0) return fd; ret = io_uring_add_tctx_node(ctx); if (ret) { put_unused_fd(fd); return ret; } fd_install(fd, file); return fd; } /* * Allocate an anonymous fd, this is what constitutes the application * visible backing of an io_uring instance. The application mmaps this * fd to gain access to the SQ/CQ ring details. */ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) { return anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, O_RDWR | O_CLOEXEC); } static int io_uring_create(unsigned entries, struct io_uring_params *p, struct io_uring_params __user *params) { struct io_ring_ctx *ctx; struct file *file; int ret; if (!entries) return -EINVAL; if (entries > IORING_MAX_ENTRIES) { if (!(p->flags & IORING_SETUP_CLAMP)) return -EINVAL; entries = IORING_MAX_ENTRIES; } /* * Use twice as many entries for the CQ ring. It's possible for the * application to drive a higher depth than the size of the SQ ring, * since the sqes are only used at submission time. This allows for * some flexibility in overcommitting a bit. If the application has * set IORING_SETUP_CQSIZE, it will have passed in the desired number * of CQ ring entries manually. */ p->sq_entries = roundup_pow_of_two(entries); if (p->flags & IORING_SETUP_CQSIZE) { /* * If IORING_SETUP_CQSIZE is set, we do the same roundup * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ if (!p->cq_entries) return -EINVAL; if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { if (!(p->flags & IORING_SETUP_CLAMP)) return -EINVAL; p->cq_entries = IORING_MAX_CQ_ENTRIES; } p->cq_entries = roundup_pow_of_two(p->cq_entries); if (p->cq_entries < p->sq_entries) return -EINVAL; } else { p->cq_entries = 2 * p->sq_entries; } ctx = io_ring_ctx_alloc(p); if (!ctx) return -ENOMEM; ctx->compat = in_compat_syscall(); if (!ns_capable_noaudit(&init_user_ns, CAP_IPC_LOCK)) ctx->user = get_uid(current_user()); /* * This is just grabbed for accounting purposes. When a process exits, * the mm is exited and dropped before the files, hence we need to hang * on to this mm purely for the purposes of being able to unaccount * memory (locked/pinned vm). It's not used for anything else. */ mmgrab(current->mm); ctx->mm_account = current->mm; ret = io_allocate_scq_urings(ctx, p); if (ret) goto err; ret = io_sq_offload_create(ctx, p); if (ret) goto err; /* always set a rsrc node */ ret = io_rsrc_node_switch_start(ctx); if (ret) goto err; io_rsrc_node_switch(ctx, NULL); memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); p->sq_off.tail = offsetof(struct io_rings, sq.tail); p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask); p->sq_off.ring_entries = offsetof(struct io_rings, sq_ring_entries); p->sq_off.flags = offsetof(struct io_rings, sq_flags); p->sq_off.dropped = offsetof(struct io_rings, sq_dropped); p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings; memset(&p->cq_off, 0, sizeof(p->cq_off)); p->cq_off.head = offsetof(struct io_rings, cq.head); p->cq_off.tail = offsetof(struct io_rings, cq.tail); p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask); p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries); p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); p->cq_off.flags = offsetof(struct io_rings, cq_flags); p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | IORING_FEAT_RSRC_TAGS; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; goto err; } file = io_uring_get_file(ctx); if (IS_ERR(file)) { ret = PTR_ERR(file); goto err; } /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup */ ret = io_uring_install_fd(ctx, file); if (ret < 0) { /* fput will clean it up */ fput(file); return ret; } trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: io_ring_ctx_wait_and_kill(ctx); return ret; } /* * Sets up an aio uring context, and returns the fd. Applications asks for a * ring size, we return the actual sq/cq ring sizes (among other things) in the * params structure passed in. */ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) { struct io_uring_params p; int i; if (copy_from_user(&p, params, sizeof(p))) return -EFAULT; for (i = 0; i < ARRAY_SIZE(p.resv); i++) { if (p.resv[i]) return -EINVAL; } if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL | IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE | IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ | IORING_SETUP_R_DISABLED)) return -EINVAL; return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, struct io_uring_params __user *, params) { return io_uring_setup(entries, params); } static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { struct io_uring_probe *p; size_t size; int i, ret; size = struct_size(p, ops, nr_args); if (size == SIZE_MAX) return -EOVERFLOW; p = kzalloc(size, GFP_KERNEL); if (!p) return -ENOMEM; ret = -EFAULT; if (copy_from_user(p, arg, size)) goto out; ret = -EINVAL; if (memchr_inv(p, 0, size)) goto out; p->last_op = IORING_OP_LAST - 1; if (nr_args > IORING_OP_LAST) nr_args = IORING_OP_LAST; for (i = 0; i < nr_args; i++) { p->ops[i].op = i; if (!io_op_defs[i].not_supported) p->ops[i].flags = IO_URING_OP_SUPPORTED; } p->ops_len = i; ret = 0; if (copy_to_user(arg, p, size)) ret = -EFAULT; out: kfree(p); return ret; } static int io_register_personality(struct io_ring_ctx *ctx) { const struct cred *creds; u32 id; int ret; creds = get_current_cred(); ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds, XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL); if (ret < 0) { put_cred(creds); return ret; } return id; } static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, unsigned int nr_args) { struct io_uring_restriction *res; size_t size; int i, ret; /* Restrictions allowed only if rings started disabled */ if (!(ctx->flags & IORING_SETUP_R_DISABLED)) return -EBADFD; /* We allow only a single restrictions registration */ if (ctx->restrictions.registered) return -EBUSY; if (!arg || nr_args > IORING_MAX_RESTRICTIONS) return -EINVAL; size = array_size(nr_args, sizeof(*res)); if (size == SIZE_MAX) return -EOVERFLOW; res = memdup_user(arg, size); if (IS_ERR(res)) return PTR_ERR(res); ret = 0; for (i = 0; i < nr_args; i++) { switch (res[i].opcode) { case IORING_RESTRICTION_REGISTER_OP: if (res[i].register_op >= IORING_REGISTER_LAST) { ret = -EINVAL; goto out; } __set_bit(res[i].register_op, ctx->restrictions.register_op); break; case IORING_RESTRICTION_SQE_OP: if (res[i].sqe_op >= IORING_OP_LAST) { ret = -EINVAL; goto out; } __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op); break; case IORING_RESTRICTION_SQE_FLAGS_ALLOWED: ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags; break; case IORING_RESTRICTION_SQE_FLAGS_REQUIRED: ctx->restrictions.sqe_flags_required = res[i].sqe_flags; break; default: ret = -EINVAL; goto out; } } out: /* Reset all restrictions if an error happened */ if (ret != 0) memset(&ctx->restrictions, 0, sizeof(ctx->restrictions)); else ctx->restrictions.registered = true; kfree(res); return ret; } static int io_register_enable_rings(struct io_ring_ctx *ctx) { if (!(ctx->flags & IORING_SETUP_R_DISABLED)) return -EBADFD; if (ctx->restrictions.registered) ctx->restricted = 1; ctx->flags &= ~IORING_SETUP_R_DISABLED; if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); return 0; } static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args) { __u32 tmp; int err; if (check_add_overflow(up->offset, nr_args, &tmp)) return -EOVERFLOW; err = io_rsrc_node_switch_start(ctx); if (err) return err; switch (type) { case IORING_RSRC_FILE: return __io_sqe_files_update(ctx, up, nr_args); case IORING_RSRC_BUFFER: return __io_sqe_buffers_update(ctx, up, nr_args); } return -EINVAL; } static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) { struct io_uring_rsrc_update2 up; if (!nr_args) return -EINVAL; memset(&up, 0, sizeof(up)); if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) return -EFAULT; if (up.resv || up.resv2) return -EINVAL; return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); } static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, unsigned size, unsigned type) { struct io_uring_rsrc_update2 up; if (size != sizeof(up)) return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; if (!up.nr || up.resv || up.resv2) return -EINVAL; return __io_register_rsrc_update(ctx, type, &up, up.nr); } static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, unsigned int size, unsigned int type) { struct io_uring_rsrc_register rr; /* keep it extendible */ if (size != sizeof(rr)) return -EINVAL; memset(&rr, 0, sizeof(rr)); if (copy_from_user(&rr, arg, size)) return -EFAULT; if (!rr.nr || rr.resv || rr.resv2) return -EINVAL; switch (type) { case IORING_RSRC_FILE: return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); case IORING_RSRC_BUFFER: return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data), rr.nr, u64_to_user_ptr(rr.tags)); } return -EINVAL; } static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, unsigned len) { struct io_uring_task *tctx = current->io_uring; cpumask_var_t new_mask; int ret; if (!tctx || !tctx->io_wq) return -EINVAL; if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) return -ENOMEM; cpumask_clear(new_mask); if (len > cpumask_size()) len = cpumask_size(); #ifdef CONFIG_COMPAT if (in_compat_syscall()) { ret = compat_get_bitmap(cpumask_bits(new_mask), (const compat_ulong_t __user *)arg, len * 8 /* CHAR_BIT */); } else { ret = copy_from_user(new_mask, arg, len); } #else ret = copy_from_user(new_mask, arg, len); #endif if (ret) { free_cpumask_var(new_mask); return -EFAULT; } ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); free_cpumask_var(new_mask); return ret; } static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; if (!tctx || !tctx->io_wq) return -EINVAL; return io_wq_cpu_affinity(tctx->io_wq, NULL); } static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, void __user *arg) __must_hold(&ctx->uring_lock) { struct io_tctx_node *node; struct io_uring_task *tctx = NULL; struct io_sq_data *sqd = NULL; __u32 new_count[2]; int i, ret; if (copy_from_user(new_count, arg, sizeof(new_count))) return -EFAULT; for (i = 0; i < ARRAY_SIZE(new_count); i++) if (new_count[i] > INT_MAX) return -EINVAL; if (ctx->flags & IORING_SETUP_SQPOLL) { sqd = ctx->sq_data; if (sqd) { /* * Observe the correct sqd->lock -> ctx->uring_lock * ordering. Fine to drop uring_lock here, we hold * a ref to the ctx. */ refcount_inc(&sqd->refs); mutex_unlock(&ctx->uring_lock); mutex_lock(&sqd->lock); mutex_lock(&ctx->uring_lock); if (sqd->thread) tctx = sqd->thread->io_uring; } } else { tctx = current->io_uring; } BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits)); for (i = 0; i < ARRAY_SIZE(new_count); i++) if (new_count[i]) ctx->iowq_limits[i] = new_count[i]; ctx->iowq_limits_set = true; ret = -EINVAL; if (tctx && tctx->io_wq) { ret = io_wq_max_workers(tctx->io_wq, new_count); if (ret) goto err; } else { memset(new_count, 0, sizeof(new_count)); } if (sqd) { mutex_unlock(&sqd->lock); io_put_sq_data(sqd); } if (copy_to_user(arg, new_count, sizeof(new_count))) return -EFAULT; /* that's it for SQPOLL, only the SQPOLL task creates requests */ if (sqd) return 0; /* now propagate the restriction to all registered users */ list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; if (WARN_ON_ONCE(!tctx->io_wq)) continue; for (i = 0; i < ARRAY_SIZE(new_count); i++) new_count[i] = ctx->iowq_limits[i]; /* ignore errors, it always returns zero anyway */ (void)io_wq_max_workers(tctx->io_wq, new_count); } return 0; err: if (sqd) { mutex_unlock(&sqd->lock); io_put_sq_data(sqd); } return ret; } static bool io_register_op_must_quiesce(int op) { switch (op) { case IORING_REGISTER_BUFFERS: case IORING_UNREGISTER_BUFFERS: case IORING_REGISTER_FILES: case IORING_UNREGISTER_FILES: case IORING_REGISTER_FILES_UPDATE: case IORING_REGISTER_PROBE: case IORING_REGISTER_PERSONALITY: case IORING_UNREGISTER_PERSONALITY: case IORING_REGISTER_FILES2: case IORING_REGISTER_FILES_UPDATE2: case IORING_REGISTER_BUFFERS2: case IORING_REGISTER_BUFFERS_UPDATE: case IORING_REGISTER_IOWQ_AFF: case IORING_UNREGISTER_IOWQ_AFF: case IORING_REGISTER_IOWQ_MAX_WORKERS: return false; default: return true; } } static int io_ctx_quiesce(struct io_ring_ctx *ctx) { long ret; percpu_ref_kill(&ctx->refs); /* * Drop uring mutex before waiting for references to exit. If another * thread is currently inside io_uring_enter() it might need to grab the * uring_lock to make progress. If we hold it here across the drain * wait, then we can deadlock. It's safe to drop the mutex here, since * no new references will come in after we've killed the percpu ref. */ mutex_unlock(&ctx->uring_lock); do { ret = wait_for_completion_interruptible(&ctx->ref_comp); if (!ret) break; ret = io_run_task_work_sig(); } while (ret >= 0); mutex_lock(&ctx->uring_lock); if (ret) io_refs_resurrect(&ctx->refs, &ctx->ref_comp); return ret; } static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) __releases(ctx->uring_lock) __acquires(ctx->uring_lock) { int ret; /* * We're inside the ring mutex, if the ref is already dying, then * someone else killed the ctx or is already going through * io_uring_register(). */ if (percpu_ref_is_dying(&ctx->refs)) return -ENXIO; if (ctx->restricted) { opcode = array_index_nospec(opcode, IORING_REGISTER_LAST); if (!test_bit(opcode, ctx->restrictions.register_op)) return -EACCES; } if (io_register_op_must_quiesce(opcode)) { ret = io_ctx_quiesce(ctx); if (ret) return ret; } switch (opcode) { case IORING_REGISTER_BUFFERS: ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_BUFFERS: ret = -EINVAL; if (arg || nr_args) break; ret = io_sqe_buffers_unregister(ctx); break; case IORING_REGISTER_FILES: ret = io_sqe_files_register(ctx, arg, nr_args, NULL); break; case IORING_UNREGISTER_FILES: ret = -EINVAL; if (arg || nr_args) break; ret = io_sqe_files_unregister(ctx); break; case IORING_REGISTER_FILES_UPDATE: ret = io_register_files_update(ctx, arg, nr_args); break; case IORING_REGISTER_EVENTFD: case IORING_REGISTER_EVENTFD_ASYNC: ret = -EINVAL; if (nr_args != 1) break; ret = io_eventfd_register(ctx, arg); if (ret) break; if (opcode == IORING_REGISTER_EVENTFD_ASYNC) ctx->eventfd_async = 1; else ctx->eventfd_async = 0; break; case IORING_UNREGISTER_EVENTFD: ret = -EINVAL; if (arg || nr_args) break; ret = io_eventfd_unregister(ctx); break; case IORING_REGISTER_PROBE: ret = -EINVAL; if (!arg || nr_args > 256) break; ret = io_probe(ctx, arg, nr_args); break; case IORING_REGISTER_PERSONALITY: ret = -EINVAL; if (arg || nr_args) break; ret = io_register_personality(ctx); break; case IORING_UNREGISTER_PERSONALITY: ret = -EINVAL; if (arg) break; ret = io_unregister_personality(ctx, nr_args); break; case IORING_REGISTER_ENABLE_RINGS: ret = -EINVAL; if (arg || nr_args) break; ret = io_register_enable_rings(ctx); break; case IORING_REGISTER_RESTRICTIONS: ret = io_register_restrictions(ctx, arg, nr_args); break; case IORING_REGISTER_FILES2: ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE); break; case IORING_REGISTER_FILES_UPDATE2: ret = io_register_rsrc_update(ctx, arg, nr_args, IORING_RSRC_FILE); break; case IORING_REGISTER_BUFFERS2: ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; case IORING_REGISTER_BUFFERS_UPDATE: ret = io_register_rsrc_update(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; case IORING_REGISTER_IOWQ_AFF: ret = -EINVAL; if (!arg || !nr_args) break; ret = io_register_iowq_aff(ctx, arg, nr_args); break; case IORING_UNREGISTER_IOWQ_AFF: ret = -EINVAL; if (arg || nr_args) break; ret = io_unregister_iowq_aff(ctx); break; case IORING_REGISTER_IOWQ_MAX_WORKERS: ret = -EINVAL; if (!arg || nr_args != 2) break; ret = io_register_iowq_max_workers(ctx, arg); break; default: ret = -EINVAL; break; } if (io_register_op_must_quiesce(opcode)) { /* bring the ctx back to life */ percpu_ref_reinit(&ctx->refs); reinit_completion(&ctx->ref_comp); } return ret; } SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, void __user *, arg, unsigned int, nr_args) { struct io_ring_ctx *ctx; long ret = -EBADF; struct fd f; if (opcode >= IORING_REGISTER_LAST) return -EINVAL; f = fdget(fd); if (!f.file) return -EBADF; ret = -EOPNOTSUPP; if (f.file->f_op != &io_uring_fops) goto out_fput; ctx = f.file->private_data; io_run_task_work(); mutex_lock(&ctx->uring_lock); ret = __io_uring_register(ctx, opcode, arg, nr_args); mutex_unlock(&ctx->uring_lock); trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ctx->cq_ev_fd != NULL, ret); out_fput: fdput(f); return ret; } static int __init io_uring_init(void) { #define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \ BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \ BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \ } while (0) #define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \ __BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename) BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64); BUILD_BUG_SQE_ELEM(0, __u8, opcode); BUILD_BUG_SQE_ELEM(1, __u8, flags); BUILD_BUG_SQE_ELEM(2, __u16, ioprio); BUILD_BUG_SQE_ELEM(4, __s32, fd); BUILD_BUG_SQE_ELEM(8, __u64, off); BUILD_BUG_SQE_ELEM(8, __u64, addr2); BUILD_BUG_SQE_ELEM(16, __u64, addr); BUILD_BUG_SQE_ELEM(16, __u64, splice_off_in); BUILD_BUG_SQE_ELEM(24, __u32, len); BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags); BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags); BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags); BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags); BUILD_BUG_SQE_ELEM(28, /* compat */ __u16, poll_events); BUILD_BUG_SQE_ELEM(28, __u32, poll32_events); BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags); BUILD_BUG_SQE_ELEM(28, __u32, msg_flags); BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags); BUILD_BUG_SQE_ELEM(28, __u32, accept_flags); BUILD_BUG_SQE_ELEM(28, __u32, cancel_flags); BUILD_BUG_SQE_ELEM(28, __u32, open_flags); BUILD_BUG_SQE_ELEM(28, __u32, statx_flags); BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice); BUILD_BUG_SQE_ELEM(28, __u32, splice_flags); BUILD_BUG_SQE_ELEM(32, __u64, user_data); BUILD_BUG_SQE_ELEM(40, __u16, buf_index); BUILD_BUG_SQE_ELEM(40, __u16, buf_group); BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); BUILD_BUG_SQE_ELEM(44, __u32, file_index); BUILD_BUG_ON(sizeof(struct io_uring_files_update) != sizeof(struct io_uring_rsrc_update)); BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) > sizeof(struct io_uring_rsrc_update2)); /* ->buf_index is u16 */ BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16)); /* should fit into one byte */ BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); return 0; }; __initcall(io_uring_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/internal.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <linux/hardirq.h> #include <linux/pkeys.h> #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ union fpregs_state init_fpstate __read_mostly; /* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? */ bool irq_fpu_usable(void) { if (WARN_ON_ONCE(in_nmi())) return false; /* In kernel FPU usage already active? */ if (this_cpu_read(in_kernel_fpu)) return false; /* * When not in NMI or hard interrupt context, FPU can be used in: * * - Task context except from within fpregs_lock()'ed critical * regions. * * - Soft interrupt processing context which cannot happen * while in a fpregs_lock()'ed critical region. */ if (!in_irq()) return true; /* * In hard interrupt context it's safe when soft interrupts * are enabled, which means the interrupt did not hit in * a fpregs_lock()'ed critical region. */ return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact and we can * keep registers active. * * The legacy FNSAVE instruction cleared all FPU state * unconditionally, so registers are essentially destroyed. * Modern FPU state can be kept in registers, if there are * no pending FP exceptions. */ int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); /* * AVX512 state is tracked here because its use is * known to slow the max clock speed of the core. */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; return 1; } if (likely(use_fxsr())) { copy_fxregs_to_kernel(fpu); return 1; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to mark them inactive: */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); return 0; } EXPORT_SYMBOL(copy_fpregs_to_fpstate); void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); WARN_ON_FPU(!irq_fpu_usable()); WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, true); if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); /* * Ignore return value -- we don't care if reg state * is clobbered. */ copy_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, false); preempt_enable(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Save the FPU state (mark it for reload if necessary): * * This only ever gets called for the current task. */ void fpu__save(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } } trace_x86_fpu_after_save(fpu); fpregs_unlock(); } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fregs_state *fp) { fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; fp->fos = 0xffff0000u; } void fpstate_init(union fpregs_state *state) { if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, fpu_kernel_xstate_size); if (static_cpu_has(X86_FEATURE_XSAVES)) fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); } EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct task_struct *dst, struct task_struct *src) { struct fpu *dst_fpu = &dst->thread.fpu; struct fpu *src_fpu = &src->thread.fpu; dst_fpu->last_cpu = -1; if (!static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); /* * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: */ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* * If the FPU registers are not current just memcpy() the state. * Otherwise save current FPU registers directly into the child's FPU * context, without any memory-to-memory copying. * * ( The function 'fails' in the FNSAVE case, which destroys * register contents so we have to load them back. ) */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); else if (!copy_fpregs_to_fpstate(dst_fpu)) copy_kernel_to_fpregs(&dst_fpu->state); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * Activate the current task's in-memory FPU context, * if it has not been used before: */ static void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); set_thread_flag(TIF_NEED_FPU_LOAD); fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); } /* * This function must be called before we read a task's fpstate. * * There's two cases where this gets called: * * - for the current task (when coredumping), in which case we have * to save the latest FPU registers into the fpstate, * * - or it's called for stopped tasks (ptrace), in which case the * registers were already saved by the context-switch code when * the task scheduled out. * * If the task has used the FPU before then save it. */ void fpu__prepare_read(struct fpu *fpu) { if (fpu == ¤t->thread.fpu) fpu__save(fpu); } /* * This function must be called before we write a task's fpstate. * * Invalidate any cached FPU registers. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU * state in the fpstate buffer: */ WARN_ON_FPU(fpu == ¤t->thread.fpu); /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct fpu *fpu) { preempt_disable(); if (fpu == ¤t->thread.fpu) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); } /* * Clear the FPU state back to init state. * * Called by sys_execve(), by the signal handler code and by various * error paths. */ static void fpu__clear(struct fpu *fpu, bool user_only) { WARN_ON_FPU(fpu != ¤t->thread.fpu); if (!static_cpu_has(X86_FEATURE_FPU)) { fpu__drop(fpu); fpu__initialize(fpu); return; } fpregs_lock(); if (user_only) { if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) copy_kernel_to_xregs(&fpu->state.xsave, xfeatures_mask_supervisor()); copy_init_fpstate_to_fpregs(xfeatures_mask_user()); } else { copy_init_fpstate_to_fpregs(xfeatures_mask_all); } fpregs_mark_activate(); fpregs_unlock(); } void fpu__clear_user_states(struct fpu *fpu) { fpu__clear(fpu, true); } void fpu__clear_all(struct fpu *fpu) { fpu__clear(fpu, false); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; __fpregs_load_activate(); } EXPORT_SYMBOL_GPL(switch_fpu_return); #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = ¤t->thread.fpu; if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = ¤t->thread.fpu; fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } EXPORT_SYMBOL_GPL(fpregs_mark_activate); /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->state.fxsave.cwd; swd = fpu->state.fxsave.swd; } else { cwd = (unsigned short)fpu->state.fsave.cwd; swd = (unsigned short)fpu->state.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->state.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; } |
r0 = syz_io_uring_setup(0x5, &(0x7f0000000080), &(0x7f0000ff8000/0x1000)=nil, &(0x7f0000ff9000/0x2000)=nil, &(0x7f0000000100)=<r1=>0x0, &(0x7f0000000540)=<r2=>0x0)
syz_io_uring_submit(r1, r2, &(0x7f0000000280)=@IORING_OP_OPENAT2={0x1c, 0x0, 0x0, 0xffffffffffffff9c, &(0x7f0000000000)={0x120c0, 0xca5d029ff30187a7}, &(0x7f0000000040)='./file0\x00', 0x18}, 0x0)
io_uring_enter(r0, 0x34d6, 0x0, 0x0, 0x0, 0x0)