| 73 274 16 64 64 220 9 407 71 233 232 233 233 784 190 457 115 40 135 40 13 7 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/khugepaged.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/pagewalk.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> /* Internal core VMA manipulation functions. */ #include "vma.h" struct folio_batch; /* * Maintains state across a page table move. The operation assumes both source * and destination VMAs already exist and are specified by the user. * * Partial moves are permitted, but the old and new ranges must both reside * within a VMA. * * mmap lock must be held in write and VMA write locks must be held on any VMA * that is visible. * * Use the PAGETABLE_MOVE() macro to initialise this struct. * * The old_addr and new_addr fields are updated as the page table move is * executed. * * NOTE: The page table move is affected by reading from [old_addr, old_end), * and old_addr may be updated for better page table alignment, so len_in * represents the length of the range being copied as specified by the user. */ struct pagetable_move_control { struct vm_area_struct *old; /* Source VMA. */ struct vm_area_struct *new; /* Destination VMA. */ unsigned long old_addr; /* Address from which the move begins. */ unsigned long old_end; /* Exclusive address at which old range ends. */ unsigned long new_addr; /* Address to move page tables to. */ unsigned long len_in; /* Bytes to remap specified by user. */ bool need_rmap_locks; /* Do rmap locks need to be taken? */ bool for_stack; /* Is this an early temp stack being moved? */ }; #define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \ struct pagetable_move_control name = { \ .old = old_, \ .new = new_, \ .old_addr = old_addr_, \ .old_end = (old_addr_) + (len_), \ .new_addr = new_addr_, \ .len_in = len_, \ } /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) return -1; return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~FOLIO_MAPPING_FLAGS); } /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ static inline int mmap_file(struct file *file, struct vm_area_struct *vma) { int err = vfs_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we must not invoke * any further hooks on it. */ vma->vm_ops = &vma_dummy_vm_ops; return err; } /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ static inline void vma_close(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &vma_dummy_vm_ops; } } /* unmap_vmas is in mm/memory.c */ void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap); #ifdef CONFIG_MMU static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); } void __put_anon_vma(struct anon_vma *anon_vma); static inline void put_anon_vma(struct anon_vma *anon_vma) { if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma); } static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_write(struct anon_vma *anon_vma) { return down_write_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } static inline void anon_vma_lock_read(struct anon_vma *anon_vma) { down_read(&anon_vma->root->rwsem); } static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) { return down_read_trylock(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); } struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* Operations which modify VMAs. */ enum vma_operation { VMA_OP_SPLIT, VMA_OP_MERGE_UNFAULTED, VMA_OP_REMAP, VMA_OP_FORK, }; int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation); int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma); int __anon_vma_prepare(struct vm_area_struct *vma); void unlink_anon_vmas(struct vm_area_struct *vma); static inline int anon_vma_prepare(struct vm_area_struct *vma) { if (likely(vma->anon_vma)) return 0; return __anon_vma_prepare(vma); } /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs respecting the dirty bit. */ #define FPB_RESPECT_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs respecting the soft-dirty bit. */ #define FPB_RESPECT_SOFT_DIRTY ((__force fpb_t)BIT(1)) /* Compare PTEs respecting the writable bit. */ #define FPB_RESPECT_WRITE ((__force fpb_t)BIT(2)) /* * Merge PTE write bits: if any PTE in the batch is writable, modify the * PTE at @ptentp to be writable. */ #define FPB_MERGE_WRITE ((__force fpb_t)BIT(3)) /* * Merge PTE young and dirty bits: if any PTE in the batch is young or dirty, * modify the PTE at @ptentp to be young or dirty, respectively. */ #define FPB_MERGE_YOUNG_DIRTY ((__force fpb_t)BIT(4)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (!(flags & FPB_RESPECT_DIRTY)) pte = pte_mkclean(pte); if (likely(!(flags & FPB_RESPECT_SOFT_DIRTY))) pte = pte_clear_soft_dirty(pte); if (likely(!(flags & FPB_RESPECT_WRITE))) pte = pte_wrprotect(pte); return pte_mkold(pte); } /** * folio_pte_batch_flags - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @vma: The VMA. Only relevant with FPB_MERGE_WRITE, otherwise can be NULL. * @ptep: Page table pointer for the first entry. * @ptentp: Pointer to a COPY of the first page table entry whose flags this * function updates based on @flags if appropriate. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio in a single VMA and a single page table. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (unless FPB_RESPECT_DIRTY is set) * and soft-dirty bit (unless FPB_RESPECT_SOFT_DIRTY is set). * * @ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single VMA and * a single page table. * * Depending on the FPB_MERGE_* flags, the pte stored at @ptentp will * be updated: it's crucial that a pointer to a COPY of the first * page table entry, obtained through ptep_get(), is provided as @ptentp. * * This function will be inlined to optimize based on the input parameters; * consider using folio_pte_batch() instead if applicable. * * Return: the number of table entries in the batch. */ static inline unsigned int folio_pte_batch_flags(struct folio *folio, struct vm_area_struct *vma, pte_t *ptep, pte_t *ptentp, unsigned int max_nr, fpb_t flags) { bool any_writable = false, any_young = false, any_dirty = false; pte_t expected_pte, pte = *ptentp; unsigned int nr, cur_nr; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); /* * Ensure this is a pointer to a copy not a pointer into a page table. * If this is a stack value, it won't be a valid virtual address, but * that's fine because it also cannot be pointing into the page table. */ VM_WARN_ON(virt_addr_valid(ptentp) && PageTable(virt_to_page(ptentp))); /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ max_nr = min_t(unsigned long, max_nr, folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); nr = pte_batch_hint(ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = ptep + nr; while (nr < max_nr) { pte = ptep_get(ptep); if (!pte_same(__pte_batch_clear_ignored(pte, flags), expected_pte)) break; if (flags & FPB_MERGE_WRITE) any_writable |= pte_write(pte); if (flags & FPB_MERGE_YOUNG_DIRTY) { any_young |= pte_young(pte); any_dirty |= pte_dirty(pte); } cur_nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, cur_nr); ptep += cur_nr; nr += cur_nr; } if (any_writable) *ptentp = pte_mkwrite(*ptentp, vma); if (any_young) *ptentp = pte_mkyoung(*ptentp); if (any_dirty) *ptentp = pte_mkdirty(*ptentp); return min(nr, max_nr); } unsigned int folio_pte_batch(struct folio *folio, pte_t *ptep, pte_t pte, unsigned int max_nr); /** * pte_move_swp_offset - Move the swap entry offset field of a swap pte * forward or backward by delta * @pte: The initial pte state; must be a swap entry * @delta: The direction and the offset we are moving; forward if delta * is positive; backward if delta is negative * * Moves the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_move_swp_offset(pte_t pte, long delta) { const softleaf_t entry = softleaf_from_pte(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + delta))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; must be a swap entry. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { return pte_move_swp_offset(pte, 1); } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; const softleaf_t entry = softleaf_from_pte(pte); pte_t *ptep = start_ptep + 1; unsigned short cgroup_id; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!softleaf_is_swap(entry)); cgroup_id = lookup_swap_cgroup_id(entry); while (ptep < end_ptep) { softleaf_t entry; pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; entry = softleaf_from_pte(pte); if (lookup_swap_cgroup_id(entry) != cgroup_id) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { vm_fault_t ret = __vmf_anon_prepare(vmf); if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vmf->vma); return ret; } vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct unmap_desc *desc); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void zap_page_range_single_batched(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long size, struct zap_details *details); int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, gfp_t gfp); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } static inline void set_pages_refcounted(struct page *page, unsigned long nr_pages) { unsigned long pfn = page_to_pfn(page); for (; nr_pages--; pfn++) set_page_refcounted(pfn_to_page(pfn)); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; extern int defrag_mode; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); bool pfn_range_intersects_zones(int nid, unsigned long start_pfn, unsigned long nr_pages); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order, enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; VM_WARN_ON_ONCE(order > MAX_FOLIO_ORDER); folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef NR_PAGES_IN_LARGE_FOLIO folio->_nr_pages = 1U << order; #endif } bool __folio_unqueue_deferred_split(struct folio *folio); static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) return false; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return false; return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, 0); if (IS_ENABLED(CONFIG_MM_ID)) { folio->_mm_ids = 0; folio->_mm_id_mapcount[0] = -1; folio->_mm_id_mapcount[1] = -1; } if (IS_ENABLED(CONFIG_64BIT) || order > 1) { atomic_set(&folio->_pincount, 0); atomic_set(&folio->_entire_mapcount, -1); } if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid, nodemask_t *); #define __alloc_frozen_pages(...) \ alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) void free_frozen_pages(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); #ifdef CONFIG_NUMA struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); #else static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order) { return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL); } #endif #define alloc_frozen_pages(...) \ alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__)) struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order); #define alloc_frozen_pages_nolock(...) \ alloc_hooks(alloc_frozen_pages_nolock_noprof(__VA_ARGS__)) void free_frozen_pages_nolock(struct page *page, unsigned int order); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int, bool); #ifdef CONFIG_SPARSEMEM void sparse_init(void); #else static inline void sparse_init(void) {} #endif /* CONFIG_SPARSEMEM */ #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ struct cma; #ifdef CONFIG_CMA bool cma_validate_zones(struct cma *cma); void *cma_reserve_early(struct cma *cma, unsigned long size); void init_cma_pageblock(struct page *page); #else static inline bool cma_validate_zones(struct cma *cma) { return false; } static inline void *cma_reserve_early(struct cma *cma, unsigned long size) { return NULL; } static inline void init_cma_pageblock(struct page *page) { } #endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool claimable); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* mm/util.c */ struct anon_vma *folio_anon_vma(const struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); bool mlock_future_ok(const struct mm_struct *mm, bool is_vma_locked, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(const struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ void init_deferred_page(unsigned long pfn, int nid); enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else #define node_reclaim_mode 0 static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } /* * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill); void shake_folio(struct folio *folio); typedef int hwpoison_filter_func_t(struct page *p); void hwpoison_filter_register(hwpoison_filter_func_t *filter); void hwpoison_filter_unregister(void); #define MAGIC_HWPOISON 0x48575053U /* HWPS */ void SetPageHWPoisonTakenOff(struct page *page); void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); unsigned long page_mapped_in_vma(const struct page *page, struct vm_area_struct *vma); #else static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { return -EBUSY; } #endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_TRYLOCK 0x400 /* Only use spin_trylock in allocation path */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask); unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift, gfp_t gfp_mask) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); static inline bool vma_is_single_threaded_private(struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHARED) return false; return atomic_read(&vma->vm_mm->mm_users) == 1; } #ifdef CONFIG_NUMA_BALANCING bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, bool is_private_single_threaded); #else static inline bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, bool is_private_single_threaded) { return false; } #endif int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long vm_flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller); /* * mm/gup.c */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); bool touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. */ static inline int get_order_from_str(const char *size_str, unsigned long valid_orders) { unsigned long size; char *endptr; int order; size = memparse(size_str, &endptr); if (!is_power_of_2(size)) return -EINVAL; order = get_order(size); if (BIT(order) & ~valid_orders) return -EINVAL; return order; } enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; bool memblock_has_mirror(void); void memblock_free_all(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!pgtable_supports_soft_dirty()) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); void __meminit __init_page_from_nid(unsigned long pfn, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp); int shmem_inode_acct_blocks(struct inode *inode, long pages); bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped); #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ xas_set_lru(xas, &shadow_nodes); \ } \ } while (0) /* mremap.c */ unsigned long move_page_tables(struct pagetable_move_control *pmc); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { } #endif /* CONFIG_UNACCEPTED_MEMORY */ /* pagewalk.c */ int walk_page_range_mm_unsafe(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); int walk_page_range_debug(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private); void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm); int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm); void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn); int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t pgprot); static inline void io_remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long orig_pfn, unsigned long size) { const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); return remap_pfn_range_prepare(desc, pfn); } static inline int io_remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr, unsigned long orig_pfn, unsigned long size, pgprot_t orig_prot) { const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size); const pgprot_t prot = pgprot_decrypted(orig_prot); return remap_pfn_range_complete(vma, addr, pfn, size, prot); } #endif /* __MM_INTERNAL_H */ |
| 1427 1423 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Generic sched_clock() support, to extend low level hardware time * counters to full 64-bit ns values. */ #include <linux/clocksource.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/kernel.h> #include <linux/math.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/hrtimer.h> #include <linux/sched_clock.h> #include <linux/seqlock.h> #include <linux/bitops.h> #include "timekeeping.h" /** * struct clock_data - all data needed for sched_clock() (including * registration of a new clock source) * * @seq: Sequence counter for protecting updates. The lowest * bit is the index for @read_data. * @read_data: Data required to read from sched_clock. * @wrap_kt: Duration for which clock can run before wrapping. * @rate: Tick rate of the registered clock. * @actual_read_sched_clock: Registered hardware level clock read function. * * The ordering of this structure has been chosen to optimize cache * performance. In particular 'seq' and 'read_data[0]' (combined) should fit * into a single 64-byte cache line. */ struct clock_data { seqcount_latch_t seq; struct clock_read_data read_data[2]; ktime_t wrap_kt; unsigned long rate; u64 (*actual_read_sched_clock)(void); }; static struct hrtimer sched_clock_timer; static int irqtime = -1; core_param(irqtime, irqtime, int, 0400); static u64 notrace jiffy_sched_clock_read(void) { /* * We don't need to use get_jiffies_64 on 32-bit arches here * because we register with BITS_PER_LONG */ return (u64)(jiffies - INITIAL_JIFFIES); } static struct clock_data cd ____cacheline_aligned = { .read_data[0] = { .mult = NSEC_PER_SEC / HZ, .read_sched_clock = jiffy_sched_clock_read, }, .actual_read_sched_clock = jiffy_sched_clock_read, }; static __always_inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq) { *seq = read_seqcount_latch(&cd.seq); return cd.read_data + (*seq & 1); } notrace int sched_clock_read_retry(unsigned int seq) { return read_seqcount_latch_retry(&cd.seq, seq); } static __always_inline unsigned long long __sched_clock(void) { struct clock_read_data *rd; unsigned int seq; u64 cyc, res; do { seq = raw_read_seqcount_latch(&cd.seq); rd = cd.read_data + (seq & 1); cyc = (rd->read_sched_clock() - rd->epoch_cyc) & rd->sched_clock_mask; res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift); } while (raw_read_seqcount_latch_retry(&cd.seq, seq)); return res; } unsigned long long noinstr sched_clock_noinstr(void) { return __sched_clock(); } unsigned long long notrace sched_clock(void) { unsigned long long ns; preempt_disable_notrace(); /* * All of __sched_clock() is a seqcount_latch reader critical section, * but relies on the raw helpers which are uninstrumented. For KCSAN, * mark all accesses in __sched_clock() as atomic. */ kcsan_nestable_atomic_begin(); ns = __sched_clock(); kcsan_nestable_atomic_end(); preempt_enable_notrace(); return ns; } /* * Updating the data required to read the clock. * * sched_clock() will never observe mis-matched data even if called from * an NMI. We do this by maintaining an odd/even copy of the data and * steering sched_clock() to one or the other using a sequence counter. * In order to preserve the data cache profile of sched_clock() as much * as possible the system reverts back to the even copy when the update * completes; the odd copy is used *only* during an update. */ static void update_clock_read_data(struct clock_read_data *rd) { /* steer readers towards the odd copy */ write_seqcount_latch_begin(&cd.seq); /* now its safe for us to update the normal (even) copy */ cd.read_data[0] = *rd; /* switch readers back to the even copy */ write_seqcount_latch(&cd.seq); /* update the backup (odd) copy with the new data */ cd.read_data[1] = *rd; write_seqcount_latch_end(&cd.seq); } /* * Atomically update the sched_clock() epoch. */ static void update_sched_clock(void) { u64 cyc; u64 ns; struct clock_read_data rd; rd = cd.read_data[0]; cyc = cd.actual_read_sched_clock(); ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); rd.epoch_ns = ns; rd.epoch_cyc = cyc; update_clock_read_data(&rd); } static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) { update_sched_clock(); hrtimer_forward_now(hrt, cd.wrap_kt); return HRTIMER_RESTART; } void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { u64 res, wrap, new_mask, new_epoch, cyc, ns; u32 new_mult, new_shift; unsigned long r, flags; char r_unit; struct clock_read_data rd; if (cd.rate > rate) return; /* Cannot register a sched_clock with interrupts on */ local_irq_save(flags); /* Calculate the mult/shift to convert counter ticks to ns. */ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); new_mask = CLOCKSOURCE_MASK(bits); cd.rate = rate; /* Calculate how many nanosecs until we risk wrapping */ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL); cd.wrap_kt = ns_to_ktime(wrap); rd = cd.read_data[0]; /* Update epoch for new counter and update 'epoch_ns' from old counter*/ new_epoch = read(); cyc = cd.actual_read_sched_clock(); ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift); cd.actual_read_sched_clock = read; rd.read_sched_clock = read; rd.sched_clock_mask = new_mask; rd.mult = new_mult; rd.shift = new_shift; rd.epoch_cyc = new_epoch; rd.epoch_ns = ns; update_clock_read_data(&rd); if (ACCESS_PRIVATE(&sched_clock_timer, function) != NULL) { /* update timeout for clock wrap */ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); } r = rate; if (r >= 4000000) { r = DIV_ROUND_CLOSEST(r, 1000000); r_unit = 'M'; } else if (r >= 4000) { r = DIV_ROUND_CLOSEST(r, 1000); r_unit = 'k'; } else { r_unit = ' '; } /* Calculate the ns resolution of this counter */ res = cyc_to_ns(1ULL, new_mult, new_shift); pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", bits, r, r_unit, res, wrap); /* Enable IRQ time accounting if we have a fast enough sched_clock() */ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); local_irq_restore(flags); pr_debug("Registered %pS as sched_clock source\n", read); } EXPORT_SYMBOL_GPL(sched_clock_register); void __init generic_sched_clock_init(void) { /* * If no sched_clock() function has been provided at that point, * make it the final one. */ if (cd.actual_read_sched_clock == jiffy_sched_clock_read) sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ); update_sched_clock(); /* * Start the timer to keep sched_clock() properly updated and * sets the initial epoch. */ hrtimer_setup(&sched_clock_timer, sched_clock_poll, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); } /* * Clock read function for use when the clock is suspended. * * This function makes it appear to sched_clock() as if the clock * stopped counting at its last update. * * This function must only be called from the critical * section in sched_clock(). It relies on the read_seqcount_retry() * at the end of the critical section to be sure we observe the * correct copy of 'epoch_cyc'. */ static u64 notrace suspended_sched_clock_read(void) { unsigned int seq = read_seqcount_latch(&cd.seq); return cd.read_data[seq & 1].epoch_cyc; } int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; update_sched_clock(); hrtimer_cancel(&sched_clock_timer); rd->read_sched_clock = suspended_sched_clock_read; return 0; } static int sched_clock_syscore_suspend(void *data) { return sched_clock_suspend(); } void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; rd->epoch_cyc = cd.actual_read_sched_clock(); hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL_HARD); rd->read_sched_clock = cd.actual_read_sched_clock; } static void sched_clock_syscore_resume(void *data) { sched_clock_resume(); } static const struct syscore_ops sched_clock_syscore_ops = { .suspend = sched_clock_syscore_suspend, .resume = sched_clock_syscore_resume, }; static struct syscore sched_clock_syscore = { .ops = &sched_clock_syscore_ops, }; static int __init sched_clock_syscore_init(void) { register_syscore(&sched_clock_syscore); return 0; } device_initcall(sched_clock_syscore_init); |
| 2 | 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 /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/bpf_mem_alloc.h> #include <linux/gfp.h> #include <linux/memory.h> #include <linux/mutex.h> static void bpf_stream_elem_init(struct bpf_stream_elem *elem, int len) { init_llist_node(&elem->node); elem->total_len = len; elem->consumed_len = 0; } static struct bpf_stream_elem *bpf_stream_elem_alloc(int len) { const int max_len = ARRAY_SIZE((struct bpf_bprintf_buffers){}.buf); struct bpf_stream_elem *elem; size_t alloc_size; /* * Length denotes the amount of data to be written as part of stream element, * thus includes '\0' byte. We're capped by how much bpf_bprintf_buffers can * accomodate, therefore deny allocations that won't fit into them. */ if (len < 0 || len > max_len) return NULL; alloc_size = offsetof(struct bpf_stream_elem, str[len]); elem = kmalloc_nolock(alloc_size, __GFP_ZERO, -1); if (!elem) return NULL; bpf_stream_elem_init(elem, len); return elem; } static int __bpf_stream_push_str(struct llist_head *log, const char *str, int len) { struct bpf_stream_elem *elem = NULL; /* * Allocate a bpf_prog_stream_elem and push it to the bpf_prog_stream * log, elements will be popped at once and reversed to print the log. */ elem = bpf_stream_elem_alloc(len); if (!elem) return -ENOMEM; memcpy(elem->str, str, len); llist_add(&elem->node, log); return 0; } static int bpf_stream_consume_capacity(struct bpf_stream *stream, int len) { if (atomic_read(&stream->capacity) >= BPF_STREAM_MAX_CAPACITY) return -ENOSPC; if (atomic_add_return(len, &stream->capacity) >= BPF_STREAM_MAX_CAPACITY) { atomic_sub(len, &stream->capacity); return -ENOSPC; } return 0; } static void bpf_stream_release_capacity(struct bpf_stream *stream, struct bpf_stream_elem *elem) { int len = elem->total_len; atomic_sub(len, &stream->capacity); } static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int len) { int ret = bpf_stream_consume_capacity(stream, len); return ret ?: __bpf_stream_push_str(&stream->log, str, len); } static struct bpf_stream *bpf_stream_get(enum bpf_stream_id stream_id, struct bpf_prog_aux *aux) { if (stream_id != BPF_STDOUT && stream_id != BPF_STDERR) return NULL; return &aux->stream[stream_id - 1]; } static void bpf_stream_free_elem(struct bpf_stream_elem *elem) { kfree_nolock(elem); } static void bpf_stream_free_list(struct llist_node *list) { struct bpf_stream_elem *elem, *tmp; llist_for_each_entry_safe(elem, tmp, list, node) bpf_stream_free_elem(elem); } static struct llist_node *bpf_stream_backlog_peek(struct bpf_stream *stream) { return stream->backlog_head; } static struct llist_node *bpf_stream_backlog_pop(struct bpf_stream *stream) { struct llist_node *node; node = stream->backlog_head; if (stream->backlog_head == stream->backlog_tail) stream->backlog_head = stream->backlog_tail = NULL; else stream->backlog_head = node->next; return node; } static void bpf_stream_backlog_fill(struct bpf_stream *stream) { struct llist_node *head, *tail; if (llist_empty(&stream->log)) return; tail = llist_del_all(&stream->log); if (!tail) return; head = llist_reverse_order(tail); if (!stream->backlog_head) { stream->backlog_head = head; stream->backlog_tail = tail; } else { stream->backlog_tail->next = head; stream->backlog_tail = tail; } return; } static bool bpf_stream_consume_elem(struct bpf_stream_elem *elem, int *len) { int rem = elem->total_len - elem->consumed_len; int used = min(rem, *len); elem->consumed_len += used; *len -= used; return elem->consumed_len == elem->total_len; } static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len) { int rem_len = len, cons_len, ret = 0; struct bpf_stream_elem *elem = NULL; struct llist_node *node; mutex_lock(&stream->lock); while (rem_len) { int pos = len - rem_len; bool cont; node = bpf_stream_backlog_peek(stream); if (!node) { bpf_stream_backlog_fill(stream); node = bpf_stream_backlog_peek(stream); } if (!node) break; elem = container_of(node, typeof(*elem), node); cons_len = elem->consumed_len; cont = bpf_stream_consume_elem(elem, &rem_len) == false; ret = copy_to_user(buf + pos, elem->str + cons_len, elem->consumed_len - cons_len); /* Restore in case of error. */ if (ret) { ret = -EFAULT; elem->consumed_len = cons_len; break; } if (cont) continue; bpf_stream_backlog_pop(stream); bpf_stream_release_capacity(stream, elem); bpf_stream_free_elem(elem); } mutex_unlock(&stream->lock); return ret ? ret : len - rem_len; } int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len) { struct bpf_stream *stream; stream = bpf_stream_get(stream_id, prog->aux); if (!stream) return -ENOENT; return bpf_stream_read(stream, buf, len); } __bpf_kfunc_start_defs(); /* * Avoid using enum bpf_stream_id so that kfunc users don't have to pull in the * enum in headers. */ __bpf_kfunc int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args, u32 len__sz, struct bpf_prog_aux *aux) { struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; u32 fmt_size = strlen(fmt__str) + 1; struct bpf_stream *stream; u32 data_len = len__sz; int ret, num_args; stream = bpf_stream_get(stream_id, aux); if (!stream) return -ENOENT; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; ret = bpf_bprintf_prepare(fmt__str, fmt_size, args, num_args, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt__str, data.bin_args); /* Exclude NULL byte during push. */ ret = bpf_stream_push_str(stream, data.buf, ret); bpf_bprintf_cleanup(&data); return ret; } /* Directly trigger a stack dump from the program. */ __bpf_kfunc int bpf_stream_print_stack(int stream_id, struct bpf_prog_aux *aux) { struct bpf_stream_stage ss; struct bpf_prog *prog; /* Make sure the stream ID is valid. */ if (!bpf_stream_get(stream_id, aux)) return -ENOENT; prog = aux->main_prog_aux->prog; bpf_stream_stage(ss, prog, stream_id, ({ bpf_stream_dump_stack(ss); })); return 0; } __bpf_kfunc_end_defs(); /* Added kfunc to common_btf_ids */ void bpf_prog_stream_init(struct bpf_prog *prog) { int i; for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { atomic_set(&prog->aux->stream[i].capacity, 0); init_llist_head(&prog->aux->stream[i].log); mutex_init(&prog->aux->stream[i].lock); prog->aux->stream[i].backlog_head = NULL; prog->aux->stream[i].backlog_tail = NULL; } } void bpf_prog_stream_free(struct bpf_prog *prog) { struct llist_node *list; int i; for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) { list = llist_del_all(&prog->aux->stream[i].log); bpf_stream_free_list(list); bpf_stream_free_list(prog->aux->stream[i].backlog_head); } } void bpf_stream_stage_init(struct bpf_stream_stage *ss) { init_llist_head(&ss->log); ss->len = 0; } void bpf_stream_stage_free(struct bpf_stream_stage *ss) { struct llist_node *node; node = llist_del_all(&ss->log); bpf_stream_free_list(node); } int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...) { struct bpf_bprintf_buffers *buf; va_list args; int ret; if (bpf_try_get_buffers(&buf)) return -EBUSY; va_start(args, fmt); ret = vsnprintf(buf->buf, ARRAY_SIZE(buf->buf), fmt, args); va_end(args); ss->len += ret; /* Exclude NULL byte during push. */ ret = __bpf_stream_push_str(&ss->log, buf->buf, ret); bpf_put_buffers(); return ret; } int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog, enum bpf_stream_id stream_id) { struct llist_node *list, *head, *tail; struct bpf_stream *stream; int ret; stream = bpf_stream_get(stream_id, prog->aux); if (!stream) return -EINVAL; ret = bpf_stream_consume_capacity(stream, ss->len); if (ret) return ret; list = llist_del_all(&ss->log); head = tail = list; if (!list) return 0; while (llist_next(list)) { tail = llist_next(list); list = tail; } llist_add_batch(head, tail, &stream->log); return 0; } struct dump_stack_ctx { struct bpf_stream_stage *ss; int err; }; static bool dump_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp) { struct dump_stack_ctx *ctxp = cookie; const char *file = "", *line = ""; struct bpf_prog *prog; int num, ret; rcu_read_lock(); prog = bpf_prog_ksym_find(ip); rcu_read_unlock(); if (prog) { ret = bpf_prog_get_file_line(prog, ip, &file, &line, &num); if (ret < 0) goto end; ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n %s @ %s:%d\n", (void *)(long)ip, line, file, num); return !ctxp->err; } end: ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n", (void *)(long)ip); return !ctxp->err; } int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss) { struct dump_stack_ctx ctx = { .ss = ss }; int ret; ret = bpf_stream_stage_printk(ss, "CPU: %d UID: %d PID: %d Comm: %s\n", raw_smp_processor_id(), __kuid_val(current_real_cred()->euid), current->pid, current->comm); if (ret) return ret; ret = bpf_stream_stage_printk(ss, "Call trace:\n"); if (ret) return ret; arch_bpf_stack_walk(dump_stack_cb, &ctx); if (ctx.err) return ctx.err; return bpf_stream_stage_printk(ss, "\n"); } |
| 99 99 51 49 120 116 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * * We implement four types of file locks: BSD locks, posix locks, open * file description locks, and leases. For details about BSD locks, * see the flock(2) man page; for details about the other three, see * fcntl(2). * * * Locking conflicts and dependencies: * If multiple threads attempt to lock the same byte (or flock the same file) * only one can be granted the lock, and other must wait their turn. * The first lock has been "applied" or "granted", the others are "waiting" * and are "blocked" by the "applied" lock.. * * Waiting and applied locks are all kept in trees whose properties are: * * - the root of a tree may be an applied or waiting lock. * - every other node in the tree is a waiting lock that * conflicts with every ancestor of that node. * * Every such tree begins life as a waiting singleton which obviously * satisfies the above properties. * * The only ways we modify trees preserve these properties: * * 1. We may add a new leaf node, but only after first verifying that it * conflicts with all of its ancestors. * 2. We may remove the root of a tree, creating a new singleton * tree from the root and N new trees rooted in the immediate * children. * 3. If the root of a tree is not currently an applied lock, we may * apply it (if possible). * 4. We may upgrade the root of the tree (either extend its range, * or upgrade its entire range from read to write). * * When an applied lock is modified in a way that reduces or downgrades any * part of its range, we remove all its children (2 above). This particularly * happens when a lock is unlocked. * * For each of those child trees we "wake up" the thread which is * waiting for the lock so it can continue handling as follows: if the * root of the tree applies, we do so (3). If it doesn't, it must * conflict with some applied lock. We remove (wake up) all of its children * (2), and add it is a new leaf to the tree rooted in the applied * lock (1). We then repeat the process recursively with those * children. * */ #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/filelock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> #include <linux/sysctl.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> #include <linux/uaccess.h> static struct file_lock *file_lock(struct file_lock_core *flc) { return container_of(flc, struct file_lock, c); } static struct file_lease *file_lease(struct file_lock_core *flc) { return container_of(flc, struct file_lease, c); } static bool lease_breaking(struct file_lease *fl) { return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); } static int target_leasetype(struct file_lease *fl) { if (fl->c.flc_flags & FL_UNLOCK_PENDING) return F_UNLCK; if (fl->c.flc_flags & FL_DOWNGRADE_PENDING) return F_RDLCK; return fl->c.flc_type; } static int leases_enable = 1; static int lease_break_time = 45; #ifdef CONFIG_SYSCTL static const struct ctl_table locks_sysctls[] = { { .procname = "leases-enable", .data = &leases_enable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_MMU { .procname = "lease-break-time", .data = &lease_break_time, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_MMU */ }; static int __init init_fs_locks_sysctls(void) { register_sysctl_init("fs", locks_sysctls); return 0; } early_initcall(init_fs_locks_sysctls); #endif /* CONFIG_SYSCTL */ /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock. * Global serialization is done using file_rwsem. * * Note that alterations to the list also require that the relevant flc_lock is * held. */ struct file_lock_list_struct { spinlock_t lock; struct hlist_head hlist; }; static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. * It is protected by blocked_lock_lock. * * We hash locks by lockowner in order to optimize searching for the lock a * particular lockowner is waiting on. * * FIXME: make this value scale via some heuristic? We generally will want more * buckets when we have more lockowners holding locks, but that's a little * difficult to determine without knowing what the workload will look like. */ #define BLOCKED_HASH_BITS 7 static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); /* * This lock protects the blocked_hash. Generally, if you're accessing it, you * want to be holding this lock. * * In addition, it also protects the fl->fl_blocked_requests list, and the * fl->fl_blocker pointer for file_lock structures that are acting as lock * requests (in contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the * flc_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); static struct kmem_cache *flctx_cache __ro_after_init; static struct kmem_cache *filelock_cache __ro_after_init; static struct kmem_cache *filelease_cache __ro_after_init; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *ctx; ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); if (!ctx) goto out; spin_lock_init(&ctx->flc_lock); INIT_LIST_HEAD(&ctx->flc_flock); INIT_LIST_HEAD(&ctx->flc_posix); INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ spin_lock(&inode->i_lock); if (!(inode->i_opflags & IOP_FLCTX)) { VFS_BUG_ON_INODE(inode->i_flctx, inode); WRITE_ONCE(inode->i_flctx, ctx); /* * Paired with locks_inode_context(). */ smp_store_release(&inode->i_opflags, inode->i_opflags | IOP_FLCTX); spin_unlock(&inode->i_lock); } else { VFS_BUG_ON_INODE(!inode->i_flctx, inode); spin_unlock(&inode->i_lock); kmem_cache_free(flctx_cache, ctx); ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); return ctx; } static void locks_dump_ctx_list(struct list_head *list, char *list_type) { struct file_lock_core *flc; list_for_each_entry(flc, list, flc_list) pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, flc->flc_owner, flc->flc_flags, flc->flc_type, flc->flc_pid); } static void locks_check_ctx_lists(struct inode *inode) { struct file_lock_context *ctx = inode->i_flctx; if (unlikely(!list_empty(&ctx->flc_flock) || !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_lease))) { pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); } } static void locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { struct file_lock_core *flc; struct inode *inode = file_inode(filp); list_for_each_entry(flc, list, flc_list) if (flc->flc_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, flc->flc_owner, flc->flc_flags, flc->flc_type, flc->flc_pid); } void locks_free_lock_context(struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } static void locks_init_lock_heads(struct file_lock_core *flc) { INIT_HLIST_NODE(&flc->flc_link); INIT_LIST_HEAD(&flc->flc_list); INIT_LIST_HEAD(&flc->flc_blocked_requests); INIT_LIST_HEAD(&flc->flc_blocked_member); init_waitqueue_head(&flc->flc_wait); } /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); /* Allocate an empty lock structure. */ struct file_lease *locks_alloc_lease(void) { struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lease); void locks_release_private(struct file_lock *fl) { struct file_lock_core *flc = &fl->c; BUG_ON(waitqueue_active(&flc->flc_wait)); BUG_ON(!list_empty(&flc->flc_list)); BUG_ON(!list_empty(&flc->flc_blocked_requests)); BUG_ON(!list_empty(&flc->flc_blocked_member)); BUG_ON(!hlist_unhashed(&flc->flc_link)); if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); fl->fl_ops = NULL; } if (fl->fl_lmops) { if (fl->fl_lmops->lm_put_owner) { fl->fl_lmops->lm_put_owner(flc->flc_owner); flc->flc_owner = NULL; } fl->fl_lmops = NULL; } } EXPORT_SYMBOL_GPL(locks_release_private); /** * locks_owner_has_blockers - Check for blocking lock requests * @flctx: file lock context * @owner: lock owner * * Return values: * %true: @owner has at least one blocker * %false: @owner has no blockers */ bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { struct file_lock_core *flc; spin_lock(&flctx->flc_lock); list_for_each_entry(flc, &flctx->flc_posix, flc_list) { if (flc->flc_owner != owner) continue; if (!list_empty(&flc->flc_blocked_requests)) { spin_unlock(&flctx->flc_lock); return true; } } spin_unlock(&flctx->flc_lock); return false; } EXPORT_SYMBOL_GPL(locks_owner_has_blockers); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } EXPORT_SYMBOL(locks_free_lock); /* Free a lease which is not in use. */ void locks_free_lease(struct file_lease *fl) { kmem_cache_free(filelease_cache, fl); } EXPORT_SYMBOL(locks_free_lease); static void locks_dispose_list(struct list_head *dispose) { struct file_lock_core *flc; while (!list_empty(dispose)) { flc = list_first_entry(dispose, struct file_lock_core, flc_list); list_del_init(&flc->flc_list); locks_free_lock(file_lock(flc)); } } static void lease_dispose_list(struct list_head *dispose) { struct file_lock_core *flc; while (!list_empty(dispose)) { flc = list_first_entry(dispose, struct file_lock_core, flc_list); list_del_init(&flc->flc_list); locks_free_lease(file_lease(flc)); } } void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lock); void locks_init_lease(struct file_lease *fl) { memset(fl, 0, sizeof(*fl)); locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lease); /* * Initialize a new lock from an existing file_lock structure. */ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { new->c.flc_owner = fl->c.flc_owner; new->c.flc_pid = fl->c.flc_pid; new->c.flc_file = NULL; new->c.flc_flags = fl->c.flc_flags; new->c.flc_type = fl->c.flc_type; new->fl_start = fl->fl_start; new->fl_end = fl->fl_end; new->fl_lmops = fl->fl_lmops; new->fl_ops = NULL; if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) fl->fl_lmops->lm_get_owner(fl->c.flc_owner); } } EXPORT_SYMBOL(locks_copy_conflock); void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { /* "new" must be a freshly-initialized lock */ WARN_ON_ONCE(new->fl_ops); locks_copy_conflock(new, fl); new->c.flc_file = fl->c.flc_file; new->fl_ops = fl->fl_ops; if (fl->fl_ops) { if (fl->fl_ops->fl_copy_lock) fl->fl_ops->fl_copy_lock(new, fl); } } EXPORT_SYMBOL(locks_copy_lock); static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) { struct file_lock *f; /* * As ctx->flc_lock is held, new requests cannot be added to * ->flc_blocked_requests, so we don't need a lock to check if it * is empty. */ if (list_empty(&fl->c.flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); list_splice_init(&fl->c.flc_blocked_requests, &new->c.flc_blocked_requests); list_for_each_entry(f, &new->c.flc_blocked_requests, c.flc_blocked_member) f->c.flc_blocker = &new->c; spin_unlock(&blocked_lock_lock); } static inline int flock_translate_cmd(int cmd) { switch (cmd) { case LOCK_SH: return F_RDLCK; case LOCK_EX: return F_WRLCK; case LOCK_UN: return F_UNLCK; } return -EINVAL; } /* Fill in a file_lock structure with an appropriate FLOCK lock. */ static void flock_make_lock(struct file *filp, struct file_lock *fl, int type) { locks_init_lock(fl); fl->c.flc_file = filp; fl->c.flc_owner = filp; fl->c.flc_pid = current->tgid; fl->c.flc_flags = FL_FLOCK; fl->c.flc_type = type; fl->fl_end = OFFSET_MAX; } static int assign_type(struct file_lock_core *flc, int type) { switch (type) { case F_RDLCK: case F_WRLCK: case F_UNLCK: flc->flc_type = type; break; default: return -EINVAL; } return 0; } static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock64 *l) { switch (l->l_whence) { case SEEK_SET: fl->fl_start = 0; break; case SEEK_CUR: fl->fl_start = filp->f_pos; break; case SEEK_END: fl->fl_start = i_size_read(file_inode(filp)); break; default: return -EINVAL; } if (l->l_start > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_start += l->l_start; if (fl->fl_start < 0) return -EINVAL; /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ if (l->l_len > 0) { if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_end = fl->fl_start + (l->l_len - 1); } else if (l->l_len < 0) { if (fl->fl_start + l->l_len < 0) return -EINVAL; fl->fl_end = fl->fl_start - 1; fl->fl_start += l->l_len; } else fl->fl_end = OFFSET_MAX; fl->c.flc_owner = current->files; fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; fl->c.flc_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; return assign_type(&fl->c, l->l_type); } /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX * style lock. */ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock *l) { struct flock64 ll = { .l_type = l->l_type, .l_whence = l->l_whence, .l_start = l->l_start, .l_len = l->l_len, }; return flock64_to_posix_lock(filp, fl, &ll); } /* default lease lock manager operations */ static bool lease_break_callback(struct file_lease *fl) { kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); return false; } static void lease_setup(struct file_lease *fl, void **priv) { struct file *filp = fl->c.flc_file; struct fasync_struct *fa = *priv; /* * fasync_insert_entry() returns the old entry if any. If there was no * old entry, then it used "priv" and inserted it into the fasync list. * Clear the pointer to indicate that it shouldn't be freed. */ if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa)) *priv = NULL; __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } /** * lease_open_conflict - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. * @filp: file to check * @arg: type of lease that we're trying to acquire * * Check to see if there's an existing open fd on this file that would * conflict with the lease we're trying to set. */ static int lease_open_conflict(struct file *filp, const int arg) { struct inode *inode = file_inode(filp); int self_wcount = 0, self_rcount = 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; else if (arg != F_WRLCK) return 0; /* * Make sure that only read/write count is from lease requestor. * Note that this will result in denying write leases when i_writecount * is negative, which is what we want. (We shouldn't grant write leases * on files open for execution.) */ if (filp->f_mode & FMODE_WRITE) self_wcount = 1; else if (filp->f_mode & FMODE_READ) self_rcount = 1; if (atomic_read(&inode->i_writecount) != self_wcount || atomic_read(&inode->i_readcount) != self_rcount) return -EAGAIN; return 0; } static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, .lm_open_conflict = lease_open_conflict, }; /* * Initialize a lease, use the default lock manager operations */ static int lease_init(struct file *filp, unsigned int flags, int type, struct file_lease *fl) { if (assign_type(&fl->c, type) != 0) return -EINVAL; fl->c.flc_owner = filp; fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; fl->c.flc_flags = flags; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ static struct file_lease *lease_alloc(struct file *filp, unsigned int flags, int type) { struct file_lease *fl = locks_alloc_lease(); int error = -ENOMEM; if (fl == NULL) return ERR_PTR(error); error = lease_init(filp, flags, type, fl); if (error) { locks_free_lease(fl); return ERR_PTR(error); } return fl; } /* Check if two locks overlap each other. */ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) { return ((fl1->fl_end >= fl2->fl_start) && (fl2->fl_end >= fl1->fl_start)); } /* * Check whether two locks have the same owner. */ static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2) { return fl1->flc_owner == fl2->flc_owner; } /* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); percpu_rwsem_assert_held(&file_rwsem); spin_lock(&fll->lock); flc->flc_link_cpu = smp_processor_id(); hlist_add_head(&flc->flc_link, &fll->hlist); spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll; percpu_rwsem_assert_held(&file_rwsem); /* * Avoid taking lock if already unhashed. This is safe since this check * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&flc->flc_link)) return; fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu); spin_lock(&fll->lock); hlist_del_init(&flc->flc_link); spin_unlock(&fll->lock); } static unsigned long posix_owner_key(struct file_lock_core *flc) { return (unsigned long) flc->flc_owner; } static void locks_insert_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter)); } static void locks_delete_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_del(&waiter->flc_link); } /* Remove waiter from blocker's block list. * When blocker ends up pointing to itself then the list is empty. * * Must be called with blocked_lock_lock held. */ static void __locks_unlink_block(struct file_lock_core *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->flc_blocked_member); } static void __locks_wake_up_blocks(struct file_lock_core *blocker) { while (!list_empty(&blocker->flc_blocked_requests)) { struct file_lock_core *waiter; struct file_lock *fl; waiter = list_first_entry(&blocker->flc_blocked_requests, struct file_lock_core, flc_blocked_member); fl = file_lock(waiter); __locks_unlink_block(waiter); if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) && fl->fl_lmops && fl->fl_lmops->lm_notify) fl->fl_lmops->lm_notify(fl); else locks_wake_up_waiter(waiter); /* * The setting of flc_blocker to NULL marks the "done" * point in deleting a block. Paired with acquire at the top * of locks_delete_block(). */ smp_store_release(&waiter->flc_blocker, NULL); } } static int __locks_delete_block(struct file_lock_core *waiter) { int status = -ENOENT; /* * If fl_blocker is NULL, it won't be set again as this thread "owns" * the lock and is the only one that might try to claim the lock. * * We use acquire/release to manage fl_blocker so that we can * optimize away taking the blocked_lock_lock in many cases. * * The smp_load_acquire guarantees two things: * * 1/ that fl_blocked_requests can be tested locklessly. If something * was recently added to that list it must have been in a locked region * *before* the locked region when fl_blocker was set to NULL. * * 2/ that no other thread is accessing 'waiter', so it is safe to free * it. __locks_wake_up_blocks is careful not to touch waiter after * fl_blocker is released. * * If a lockless check of fl_blocker shows it to be NULL, we know that * no new locks can be inserted into its fl_blocked_requests list, and * can avoid doing anything further if the list is empty. */ if (!smp_load_acquire(&waiter->flc_blocker) && list_empty(&waiter->flc_blocked_requests)) return status; spin_lock(&blocked_lock_lock); if (waiter->flc_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_unlink_block(waiter); /* * The setting of fl_blocker to NULL marks the "done" point in deleting * a block. Paired with acquire at the top of this function. */ smp_store_release(&waiter->flc_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } /** * locks_delete_block - stop waiting for a file lock * @waiter: the lock which was waiting * * lockd/nfsd need to disconnect the lock while working on it. */ int locks_delete_block(struct file_lock *waiter) { return __locks_delete_block(&waiter->c); } EXPORT_SYMBOL(locks_delete_block); /* Insert waiter into blocker's block list. * We use a circular list so that processes can be easily woken up in * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * * Must be called with both the flc_lock and blocked_lock_lock held. The * fl_blocked_requests list itself is protected by the blocked_lock_lock, * but by ensuring that the flc_lock is also held on insertions we can avoid * taking the blocked_lock_lock in some cases when we see that the * fl_blocked_requests list is empty. * * Rather than just adding to the list, we check for conflicts with any existing * waiters, and add beneath any waiter that blocks the new waiter. * Thus wakeups don't happen until needed. */ static void __locks_insert_block(struct file_lock_core *blocker, struct file_lock_core *waiter, bool conflict(struct file_lock_core *, struct file_lock_core *)) { struct file_lock_core *flc; BUG_ON(!list_empty(&waiter->flc_blocked_member)); new_blocker: list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member) if (conflict(flc, waiter)) { blocker = flc; goto new_blocker; } waiter->flc_blocker = blocker; list_add_tail(&waiter->flc_blocked_member, &blocker->flc_blocked_requests); if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX) locks_insert_global_blocked(waiter); /* The requests in waiter->flc_blocked are known to conflict with * waiter, but might not conflict with blocker, or the requests * and lock which block it. So they all need to be woken. */ __locks_wake_up_blocks(waiter); } /* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock_core *blocker, struct file_lock_core *waiter, bool conflict(struct file_lock_core *, struct file_lock_core *)) { spin_lock(&blocked_lock_lock); __locks_insert_block(blocker, waiter, conflict); spin_unlock(&blocked_lock_lock); } /* * Wake up processes blocked waiting for blocker. * * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock_core *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new * blocked requests are only added to the list under the flc_lock, and * the flc_lock is always held here. Note that removal from the * fl_blocked_requests list does not require the flc_lock, so we must * recheck list_empty() after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); __locks_wake_up_blocks(blocker); spin_unlock(&blocked_lock_lock); } static void locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before) { list_add_tail(&fl->flc_list, before); locks_insert_global_locks(fl); } static void locks_unlink_lock_ctx(struct file_lock_core *fl) { locks_delete_global_locks(fl); list_del_init(&fl->flc_list); locks_wake_up_blocks(fl); } static void locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose) { locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->flc_list, dispose); else locks_free_lock(file_lock(fl)); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ static bool locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { if (sys_flc->flc_type == F_WRLCK) return true; if (caller_flc->flc_type == F_WRLCK) return true; return false; } /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific * checking before calling the locks_conflict(). */ static bool posix_locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { struct file_lock *caller_fl = file_lock(caller_flc); struct file_lock *sys_fl = file_lock(sys_flc); /* POSIX locks owned by the same process do not conflict with * each other. */ if (posix_same_owner(caller_flc, sys_flc)) return false; /* Check whether they overlap */ if (!locks_overlap(caller_fl, sys_fl)) return false; return locks_conflict(caller_flc, sys_flc); } /* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK * path so checks for additional GETLK-specific things like F_UNLCK. */ static bool posix_test_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { struct file_lock_core *caller = &caller_fl->c; struct file_lock_core *sys = &sys_fl->c; /* F_UNLCK checks any locks on the same fd. */ if (lock_is_unlock(caller_fl)) { if (!posix_same_owner(caller, sys)) return false; return locks_overlap(caller_fl, sys_fl); } return posix_locks_conflict(caller, sys); } /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific * checking before calling the locks_conflict(). */ static bool flock_locks_conflict(struct file_lock_core *caller_flc, struct file_lock_core *sys_flc) { /* FLOCK locks referring to the same filp do not conflict with * each other. */ if (caller_flc->flc_file == sys_flc->flc_file) return false; return locks_conflict(caller_flc, sys_flc); } void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; struct inode *inode = file_inode(filp); void *owner; void (*func)(void); ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->c.flc_type = F_UNLCK; return; } retry: spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) { if (!posix_test_locks_conflict(fl, cfl)) continue; if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { owner = cfl->fl_lmops->lm_mod_owner; func = cfl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); (*func)(); module_put(owner); goto retry; } locks_copy_conflock(fl, cfl); goto out; } fl->c.flc_type = F_UNLCK; out: spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); /* * Deadlock detection: * * We attempt to detect deadlocks that are due purely to posix file * locks. * * We assume that a task can be waiting for at most one lock at a time. * So for any acquired lock, the process holding that lock may be * waiting on at most one other lock. That lock in turns may be held by * someone waiting for at most one other lock. Given a requested lock * caller_fl which is about to wait for a conflicting lock block_fl, we * follow this chain of waiters to ensure we are not about to create a * cycle. * * Since we do this before we ever put a process to sleep on a lock, we * are ensured that there is never a cycle; that is what guarantees that * the while() loop in posix_locks_deadlock() eventually completes. * * Note: the above assumption may not be true when handling lock * requests from a broken NFS client. It may also fail in the presence * of tasks (such as posix threads) sharing the same open file table. * To handle those cases, we just bail out after a few iterations. * * For FL_OFDLCK locks, the owner is the filp, not the files_struct. * Because the owner is not even nominally tied to a thread of * execution, the deadlock detection below can't reasonably work well. Just * skip it for those. * * In principle, we could do a more limited deadlock detection on FL_OFDLCK * locks that just checks for the case where two tasks are attempting to * upgrade from read to write locks on the same inode. */ #define MAX_DEADLK_ITERATIONS 10 /* Find a lock that the owner of the given @blocker is blocking on. */ static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker) { struct file_lock_core *flc; hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) { if (posix_same_owner(flc, blocker)) { while (flc->flc_blocker) flc = flc->flc_blocker; return flc; } } return NULL; } /* Must be called with the blocked_lock_lock held! */ static bool posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { struct file_lock_core *caller = &caller_fl->c; struct file_lock_core *blocker = &block_fl->c; int i = 0; lockdep_assert_held(&blocked_lock_lock); /* * This deadlock detector can't reasonably detect deadlocks with * FL_OFDLCK locks, since they aren't owned by a process, per-se. */ if (caller->flc_flags & FL_OFDLCK) return false; while ((blocker = what_owner_is_waiting_for(blocker))) { if (i++ > MAX_DEADLK_ITERATIONS) return false; if (posix_same_owner(caller, blocker)) return true; } return false; } /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks * after any leases, but before any posix locks. * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ static int flock_lock_inode(struct inode *inode, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock *fl; struct file_lock_context *ctx; int error = 0; bool found = false; LIST_HEAD(dispose); ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) { if (request->c.flc_type != F_UNLCK) return -ENOMEM; return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0; } if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->c.flc_flags & FL_ACCESS) goto find_conflict; list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { if (request->c.flc_file != fl->c.flc_file) continue; if (request->c.flc_type == fl->c.flc_type) goto out; found = true; locks_delete_lock_ctx(&fl->c, &dispose); break; } if (lock_is_unlock(request)) { if ((request->c.flc_flags & FL_EXISTS) && !found) error = -ENOENT; goto out; } find_conflict: list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { if (!flock_locks_conflict(&request->c, &fl->c)) continue; error = -EAGAIN; if (!(request->c.flc_flags & FL_SLEEP)) goto out; error = FILE_LOCK_DEFERRED; locks_insert_block(&fl->c, &request->c, flock_locks_conflict); goto out; } if (request->c.flc_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock); new_fl = NULL; error = 0; out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); trace_flock_lock_inode(inode, request, error); return error; } static int posix_lock_inode(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); void *owner; void (*func)(void); ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) return lock_is_unlock(request) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. * * In some cases we can be sure, that no new locks will be needed */ if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK || request->fl_start != 0 || request->fl_end != OFFSET_MAX)) { new_fl = locks_alloc_lock(); new_fl2 = locks_alloc_lock(); } retry: percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->c.flc_type != F_UNLCK) { list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { if (!posix_locks_conflict(&request->c, &fl->c)) continue; if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable && (*fl->fl_lmops->lm_lock_expirable)(fl)) { owner = fl->fl_lmops->lm_mod_owner; func = fl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); (*func)(); module_put(owner); goto retry; } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; if (!(request->c.flc_flags & FL_SLEEP)) goto out; /* * Deadlock detection and insertion into the blocked * locks list must be done while holding the same lock! */ error = -EDEADLK; spin_lock(&blocked_lock_lock); /* * Ensure that we don't find any locks blocked on this * request during deadlock detection. */ __locks_wake_up_blocks(&request->c); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(&fl->c, &request->c, posix_locks_conflict); } spin_unlock(&blocked_lock_lock); goto out; } } /* If we're just looking for a conflict, we're done. */ error = 0; if (request->c.flc_flags & FL_ACCESS) goto out; /* Find the first old lock with the same owner as the new lock */ list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { if (posix_same_owner(&request->c, &fl->c)) break; } /* Process locks with this owner. */ list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) { if (!posix_same_owner(&request->c, &fl->c)) break; /* Detect adjacent or overlapping regions (if same lock type) */ if (request->c.flc_type == fl->c.flc_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ if (fl->fl_start - 1 > request->fl_end) break; /* If we come here, the new and old lock are of the * same type and adjacent or overlapping. Make one * lock yielding from the lower start address of both * locks to the higher end address. */ if (fl->fl_start > request->fl_start) fl->fl_start = request->fl_start; else request->fl_start = fl->fl_start; if (fl->fl_end < request->fl_end) fl->fl_end = request->fl_end; else request->fl_end = fl->fl_end; if (added) { locks_delete_lock_ctx(&fl->c, &dispose); continue; } request = fl; added = true; } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) continue; if (fl->fl_start > request->fl_end) break; if (lock_is_unlock(request)) added = true; if (fl->fl_start < request->fl_start) left = fl; /* If the next lock in the list has a higher end * address than the new one, insert the new one here. */ if (fl->fl_end > request->fl_end) { right = fl; break; } if (fl->fl_start >= request->fl_start) { /* The new lock completely replaces an old * one (This may happen several times). */ if (added) { locks_delete_lock_ctx(&fl->c, &dispose); continue; } /* * Replace the old lock with new_fl, and * remove the old one. It's safe to do the * insert here since we know that we won't be * using new_fl later, and that the lock is * just replacing an existing lock. */ error = -ENOLCK; if (!new_fl) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); request = new_fl; new_fl = NULL; locks_insert_lock_ctx(&request->c, &fl->c.flc_list); locks_delete_lock_ctx(&fl->c, &dispose); added = true; } } } /* * The above code only modifies existing locks in case of merging or * replacing. If new lock(s) need to be inserted all modifications are * done below this, so it's safe yet to bail out. */ error = -ENOLCK; /* "no luck" */ if (right && left == right && !new_fl2) goto out; error = 0; if (!added) { if (lock_is_unlock(request)) { if (request->c.flc_flags & FL_EXISTS) error = -ENOENT; goto out; } if (!new_fl) { error = -ENOLCK; goto out; } locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list); fl = new_fl; new_fl = NULL; } if (right) { if (left == right) { /* The new lock breaks the old one in two pieces, * so we have to use the second new lock. */ left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); locks_insert_lock_ctx(&left->c, &fl->c.flc_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(&right->c); } if (left) { left->fl_end = request->fl_start - 1; locks_wake_up_blocks(&left->c); } out: trace_posix_lock_inode(inode, request, error); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); /* * Free any unused locks. */ if (new_fl) locks_free_lock(new_fl); if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); return error; } /** * posix_lock_file - Apply a POSIX-style lock to a file * @filp: The file to apply the lock to * @fl: The lock to be applied * @conflock: Place to return a copy of the conflicting lock, if found. * * Add a POSIX style lock to a file. * We merge adjacent & overlapping locks whenever possible. * POSIX locks are sorted by owner task, then by starting address * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); /** * posix_lock_inode_wait - Apply a POSIX-style lock to a file * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * * Apply a POSIX style lock request to an inode. */ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } static void lease_clear_pending(struct file_lease *fl, int arg) { switch (arg) { case F_UNLCK: fl->c.flc_flags &= ~FL_UNLOCK_PENDING; fallthrough; case F_RDLCK: fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING; } } /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { int error = assign_type(&fl->c, arg); if (error) return error; lease_clear_pending(fl, arg); locks_wake_up_blocks(&fl->c); if (arg == F_UNLCK) { struct file *filp = fl->c.flc_file; f_delown(filp); file_f_owner(filp)->signum = 0; fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } locks_delete_lock_ctx(&fl->c, dispose); } return 0; } EXPORT_SYMBOL(lease_modify); static bool past_time(unsigned long then) { if (!then) /* 0 is a special value meaning "this never expires": */ return false; return time_after(jiffies, then); } static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; struct file_lease *fl, *tmp; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) lease_modify(fl, F_UNLCK, dispose); } } static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc) { bool rc; struct file_lease *lease = file_lease(lc); struct file_lease *breaker = file_lease(bc); if (lease->fl_lmops->lm_breaker_owns_lease && lease->fl_lmops->lm_breaker_owns_lease(lease)) return false; if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) { rc = false; goto trace; } if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) { rc = false; goto trace; } rc = locks_conflict(bc, lc); trace: trace_leases_conflict(rc, lease, breaker); return rc; } static bool any_leases_conflict(struct inode *inode, struct file_lease *breaker) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock_core *flc; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(flc, &ctx->flc_lease, flc_list) { if (leases_conflict(flc, &breaker->c)) return true; } return false; } /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return * @flags: LEASE_BREAK_* flags * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on * a call to open() or truncate(). This function can block waiting for the * lease break unless you specify LEASE_BREAK_NONBLOCK. */ int __break_lease(struct inode *inode, unsigned int flags) { struct file_lease *new_fl, *fl, *tmp; struct file_lock_context *ctx; unsigned long break_time; unsigned int type; LIST_HEAD(dispose); bool want_write = !(flags & LEASE_BREAK_OPEN_RDONLY); int error = 0; if (flags & LEASE_BREAK_LEASE) type = FL_LEASE; else if (flags & LEASE_BREAK_DELEG) type = FL_DELEG; else if (flags & LEASE_BREAK_LAYOUT) type = FL_LAYOUT; else return -EINVAL; new_fl = lease_alloc(NULL, type, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); if (!any_leases_conflict(inode, new_fl)) goto out; break_time = 0; if (lease_break_time > 0) { break_time = jiffies + lease_break_time * HZ; if (break_time == 0) break_time++; /* so that 0 means no break time */ } list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { if (!leases_conflict(&fl->c, &new_fl->c)) continue; if (want_write) { if (fl->c.flc_flags & FL_UNLOCK_PENDING) continue; fl->c.flc_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { if (lease_breaking(fl)) continue; fl->c.flc_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) locks_delete_lock_ctx(&fl->c, &dispose); } if (list_empty(&ctx->flc_lease)) goto out; if (flags & LEASE_BREAK_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list); break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; locks_insert_block(&fl->c, &new_fl->c, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); lease_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->c.flc_wait, list_empty(&new_fl->c.flc_blocked_member), break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); __locks_delete_block(&new_fl->c); if (error >= 0) { /* * Wait for the next conflicting lease that has not been * broken yet */ if (error == 0) time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; error = 0; } out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); lease_dispose_list(&dispose); free_lock: locks_free_lease(new_fl); return error; } EXPORT_SYMBOL(__break_lease); /** * lease_get_mtime - update modified time of an inode with exclusive lease * @inode: the inode * @time: pointer to a timespec which contains the last modified time * * This is to force NFS clients to flush their caches for files with * exclusive leases. The justification is that if someone has an * exclusive lease, then they could be modifying it. */ void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; struct file_lock_core *flc; ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); flc = list_first_entry_or_null(&ctx->flc_lease, struct file_lock_core, flc_list); if (flc && flc->flc_type == F_WRLCK) has_lease = true; spin_unlock(&ctx->flc_lock); } if (has_lease) *time = current_time(inode); } EXPORT_SYMBOL(lease_get_mtime); /** * __fcntl_getlease - Enquire what lease is currently active * @filp: the file * @flavor: type of lease flags to check * * The value returned by this function will be one of * (if no lease break is pending): * * %F_RDLCK to indicate a shared lease is held. * * %F_WRLCK to indicate an exclusive lease is held. * * %F_UNLCK to indicate no lease is held. * * (if a lease break is pending): * * %F_RDLCK to indicate an exclusive lease needs to be * changed to a shared lease (or removed). * * %F_UNLCK to indicate the lease needs to be removed. * * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ static int __fcntl_getlease(struct file *filp, unsigned int flavor) { struct file_lease *fl; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file != filp) continue; if (fl->c.flc_flags & flavor) type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); lease_dispose_list(&dispose); } return type; } int fcntl_getlease(struct file *filp) { return __fcntl_getlease(filp, FL_LEASE); } int fcntl_getdeleg(struct file *filp, struct delegation *deleg) { if (deleg->d_flags != 0 || deleg->__pad != 0) return -EINVAL; deleg->d_type = __fcntl_getlease(filp, FL_DELEG); return 0; } static int generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv) { struct file_lease *fl, *my_fl = NULL, *lease; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->c.flc_flags & FL_DELEG; int error; LIST_HEAD(dispose); lease = *flp; trace_generic_add_lease(inode, lease); error = file_f_owner_allocate(filp); if (error) return error; /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) return -ENOMEM; /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_rwsem. We trylock * because delegations are an optional optimization, and if * there's some chance of a conflict--we'd rather not * bother, maybe that's a sign this just isn't a good file to * hand out a delegation on. */ if (is_deleg && !inode_trylock(inode)) return -EAGAIN; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) goto out; /* * At this point, we know that if there is an exclusive * lease on this file, then we hold it on this filp * (otherwise our open of this file would have blocked). * And if we are trying to acquire an exclusive lease, * then the file is not open by anyone (including us) * except for this filp. */ error = -EAGAIN; list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file == filp && fl->c.flc_owner == lease->c.flc_owner) { my_fl = fl; continue; } /* * No exclusive leases if someone else has a lease on * this file: */ if (arg == F_WRLCK) goto out; /* * Modifying our existing lease is OK, but no getting a * new lease if someone else is opening for write: */ if (fl->c.flc_flags & FL_UNLOCK_PENDING) goto out; } if (my_fl != NULL) { lease = my_fl; error = lease->fl_lmops->lm_change(lease, arg, &dispose); if (error) goto out; goto out_setup; } error = -EINVAL; if (!leases_enable) goto out; locks_insert_lock_ctx(&lease->c, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting * open but before the lease was inserted. Check again for a * conflicting open and cancel the lease if there is one. * * We also add a barrier here to ensure that the insertion of the lock * precedes these checks. */ smp_mb(); error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) { locks_unlink_lock_ctx(&lease->c); goto out; } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); lease_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) *flp = NULL; return error; } static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lease *fl, *victim = NULL; struct inode *inode = file_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { if (fl->c.flc_file == filp && fl->c.flc_owner == owner) { victim = fl; break; } } trace_generic_delete_lease(inode, victim); if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); lease_dispose_list(&dispose); return error; } /** * generic_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @flp: input - file_lock to use, output - file_lock inserted * @priv: private data for lm_setup (may be NULL if lm_setup * doesn't require it) * * The (input) flp->fl_lmops->lm_break function is required * by break_lease(). */ int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { struct inode *inode = file_inode(filp); if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); case F_WRLCK: if (S_ISDIR(inode->i_mode)) return -EINVAL; fallthrough; case F_RDLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; } return generic_add_lease(filp, arg, flp, priv); default: return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); /* * Kernel subsystems can register to be notified on any attempt to set * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd * to close files that it may have cached when there is an attempt to set a * conflicting lease. */ static struct srcu_notifier_head lease_notifier_chain; static inline void lease_notifier_chain_init(void) { srcu_init_notifier_head(&lease_notifier_chain); } static inline void setlease_notifier(int arg, struct file_lease *lease) { if (arg != F_UNLCK) srcu_notifier_call_chain(&lease_notifier_chain, arg, lease); } int lease_register_notifier(struct notifier_block *nb) { return srcu_notifier_chain_register(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { srcu_notifier_chain_unregister(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_unregister_notifier); int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { if (lease) setlease_notifier(arg, *lease); if (filp->f_op->setlease) return filp->f_op->setlease(filp, arg, lease, priv); return -EINVAL; } EXPORT_SYMBOL_GPL(kernel_setlease); /** * vfs_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @lease: file_lock to use when adding a lease * @priv: private info for lm_setup when adding a lease (may be * NULL if lm_setup doesn't require it) * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It * may be NULL if the lm_setup operation doesn't require it. */ int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { struct inode *inode = file_inode(filp); vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode); int error; if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) return -EACCES; error = security_file_lock(filp, arg); if (error) return error; return kernel_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(vfs_setlease); static int do_fcntl_add_lease(unsigned int fd, struct file *filp, unsigned int flavor, int arg) { struct file_lease *fl; struct fasync_struct *new; int error; fl = lease_alloc(filp, flavor, arg); if (IS_ERR(fl)) return PTR_ERR(fl); new = fasync_alloc(); if (!new) { locks_free_lease(fl); return -ENOMEM; } new->fa_fd = fd; error = vfs_setlease(filp, arg, &fl, (void **)&new); if (fl) locks_free_lease(fl); if (new) fasync_free(new); return error; } /** * fcntl_setlease - sets a lease on an open file * @fd: open file descriptor * @filp: file pointer * @arg: type of lease to obtain * * Call this fcntl to establish a lease on the file. * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { if (S_ISDIR(file_inode(filp)->i_mode)) return -EINVAL; if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, FL_LEASE, arg); } /** * fcntl_setdeleg - sets a delegation on an open file * @fd: open file descriptor * @filp: file pointer * @deleg: delegation request from userland * * Call this fcntl to establish a delegation on the file. * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) { /* For now, no flags are supported */ if (deleg->d_flags != 0 || deleg->__pad != 0) return -EINVAL; if (deleg->d_type == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, FL_DELEG, deleg->d_type); } /** * flock_lock_inode_wait - Apply a FLOCK-style lock to a file * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a FLOCK style lock request to an inode. */ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /** * locks_lock_inode_wait - Apply a lock to an inode * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a POSIX or FLOCK style lock request to an inode. */ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int res = 0; switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: res = posix_lock_inode_wait(inode, fl); break; case FL_FLOCK: res = flock_lock_inode_wait(inode, fl); break; default: BUG(); } return res; } EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. * @fd: the file descriptor to lock. * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. * The @cmd can be one of: * * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED) * * %LOCK_MAND support has been removed from the kernel. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { int can_sleep, error, type; struct file_lock fl; /* * LOCK_MAND locks were broken for a long time in that they never * conflicted with one another and didn't prevent any sort of open, * read or write activity. * * Just ignore these requests now, to preserve legacy behavior, but * throw a warning to let people know that they don't actually work. */ if (cmd & LOCK_MAND) { pr_warn_once("%s(%d): Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n", current->comm, current->pid); return 0; } type = flock_translate_cmd(cmd & ~LOCK_NB); if (type < 0) return type; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (type != F_UNLCK && !(fd_file(f)->f_mode & (FMODE_READ | FMODE_WRITE))) return -EBADF; flock_make_lock(fd_file(f), &fl, type); error = security_file_lock(fd_file(f), fl.c.flc_type); if (error) return error; can_sleep = !(cmd & LOCK_NB); if (can_sleep) fl.c.flc_flags |= FL_SLEEP; if (fd_file(f)->f_op->flock) error = fd_file(f)->f_op->flock(fd_file(f), (can_sleep) ? F_SETLKW : F_SETLK, &fl); else error = locks_lock_file_wait(fd_file(f), &fl); locks_release_private(&fl); return error; } /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for * @fl: The byte-range in the file to test; also used to hold result * * On entry, @fl does not contain a lock, but identifies a range (fl_start, fl_end) * in the file (c.flc_file), and an owner (c.flc_owner) for whom existing locks * should be ignored. c.flc_type and c.flc_flags are ignored. * Both fl_lmops and fl_ops in @fl must be NULL. * Returns -ERRNO on failure. Indicates presence of conflicting lock by * setting fl->fl_type to something other than F_UNLCK. * * If vfs_test_lock() does find a lock and return it, the caller must * use locks_free_lock() or locks_release_private() on the returned lock. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { int error = 0; WARN_ON_ONCE(fl->fl_ops || fl->fl_lmops); WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) error = filp->f_op->lock(filp, F_GETLK, fl); else posix_test_lock(filp, fl); /* * We don't expect FILE_LOCK_DEFERRED and callers cannot * handle it. */ if (WARN_ON_ONCE(error == FILE_LOCK_DEFERRED)) error = -EIO; return error; } EXPORT_SYMBOL_GPL(vfs_test_lock); /** * locks_translate_pid - translate a file_lock's fl_pid number into a namespace * @fl: The file_lock who's fl_pid should be translated * @ns: The namespace into which the pid should be translated * * Used to translate a fl_pid into a namespace virtual pid number */ static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns) { pid_t vnr; struct pid *pid; if (fl->flc_flags & FL_OFDLCK) return -1; /* Remote locks report a negative pid value */ if (fl->flc_pid <= 0) return fl->flc_pid; /* * If the flock owner process is dead and its pid has been already * freed, the translation below won't work, but we still want to show * flock owner pid number in init pidns. */ if (ns == &init_pid_ns) return (pid_t) fl->flc_pid; rcu_read_lock(); pid = find_pid_ns(fl->flc_pid, &init_pid_ns); vnr = pid_nr_ns(pid, ns); rcu_read_unlock(); return vnr; } static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via * legacy 32bit flock. */ if (fl->fl_start > OFFT_OFFSET_MAX) return -EOVERFLOW; if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX) return -EOVERFLOW; #endif flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->c.flc_type; return 0; } #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->c.flc_type; } #endif /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; fl->c.flc_flags |= FL_OFDLCK; fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->c.flc_type; if (fl->c.flc_type != F_UNLCK) { error = posix_lock_to_flock(flock, fl); if (error) goto out; } out: locks_free_lock(fl); return error; } /** * vfs_lock_file - file byte range lock * @filp: The file to apply the lock to * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.) * @fl: The lock to be applied * @conf: Place to return a copy of the conflicting lock, if found. * * A caller that doesn't care about the conflicting lock may pass NULL * as the final argument. * * If the filesystem defines a private ->lock() method, then @conf will * be left unchanged; so a caller that cares should initialize it to * some acceptable default. * * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) * lm_grant is set. Additionally FOP_ASYNC_LOCK in file_operations fop_flags * need to be set. * * Callers expecting ->lock() to return asynchronously will only use F_SETLK, * not F_SETLKW; they will set FL_SLEEP if (and only if) the request is for a * blocking lock. When ->lock() does return asynchronously, it must return * FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine * with the result. If the request timed out the callback routine will return a * nonzero return code and the file system should release the lock. The file * system is also responsible to keep a corresponding posix lock when it * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); } EXPORT_SYMBOL_GPL(vfs_lock_file); static int do_lock_file_wait(struct file *filp, unsigned int cmd, struct file_lock *fl) { int error; error = security_file_lock(filp, fl->c.flc_type); if (error) return error; for (;;) { error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->c.flc_wait, list_empty(&fl->c.flc_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { switch (fl->c.flc_type) { case F_RDLCK: if (!(fl->c.flc_file->f_mode & FMODE_READ)) return -EBADF; break; case F_WRLCK: if (!(fl->c.flc_file->f_mode & FMODE_WRITE)) return -EBADF; } return 0; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = file_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; fallthrough; case F_SETLKW: file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->c.flc_type != F_UNLCK && !(file_lock->c.flc_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } #if BITS_PER_LONG == 32 /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock64_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; fl->c.flc_flags |= FL_OFDLCK; fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->c.flc_type; if (fl->c.flc_type != F_UNLCK) posix_lock_to_flock64(flock, fl); out: locks_free_lock(fl); return error; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK64; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; file_lock->c.flc_flags |= FL_OFDLCK; file_lock->c.flc_owner = filp; fallthrough; case F_SETLKW64: file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->c.flc_type != F_UNLCK && !(file_lock->c.flc_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: locks_free_lock(file_lock); return error; } #endif /* BITS_PER_LONG == 32 */ /* * This function is called when the file is being removed * from the task's fd array. POSIX locks belonging to this task * are deleted at this time. */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; struct inode *inode = file_inode(filp); struct file_lock lock; struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; locks_init_lock(&lock); lock.c.flc_type = F_UNLCK; lock.c.flc_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; lock.c.flc_owner = owner; lock.c.flc_pid = current->tgid; lock.c.flc_file = filp; lock.fl_ops = NULL; lock.fl_lmops = NULL; error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); trace_locks_remove_posix(inode, &lock, error); } EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; struct inode *inode = file_inode(filp); if (list_empty(&flctx->flc_flock)) return; flock_make_lock(filp, &fl, F_UNLCK); fl.c.flc_flags |= FL_CLOSE; if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); else flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl); } /* The i_flctx must be valid when calling into here */ static void locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { struct file_lease *fl, *tmp; LIST_HEAD(dispose); if (list_empty(&ctx->flc_lease)) return; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) if (filp == fl->c.flc_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); lease_dispose_list(&dispose); } /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; ctx = locks_inode_context(file_inode(filp)); if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp, ctx); /* remove any leases */ locks_remove_lease(filp, ctx); spin_lock(&ctx->flc_lock); locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE"); spin_unlock(&ctx->flc_lock); } /** * vfs_cancel_lock - file byte range unblock lock * @filp: The file to apply the unblock to * @fl: The lock to be unblocked * * Used by lock managers to cancel blocked requests */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_cancel_lock); /** * vfs_inode_has_locks - are any file locks held on @inode? * @inode: inode to check for locks * * Return true if there are any FL_POSIX or FL_FLOCK locks currently * set on @inode. */ bool vfs_inode_has_locks(struct inode *inode) { struct file_lock_context *ctx; bool ret; ctx = locks_inode_context(inode); if (!ctx) return false; spin_lock(&ctx->flc_lock); ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); spin_unlock(&ctx->flc_lock); return ret; } EXPORT_SYMBOL_GPL(vfs_inode_has_locks); #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> struct locks_iterator { int li_cpu; loff_t li_pos; }; static void lock_get_status(struct seq_file *f, struct file_lock_core *flc, loff_t id, char *pfx, int repeat) { struct inode *inode = NULL; unsigned int pid; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); int type = flc->flc_type; struct file_lock *fl = file_lock(flc); pid = locks_translate_pid(flc, proc_pidns); /* * If lock owner is dead (and pid is freed) or not visible in current * pidns, zero is shown as a pid value. Check lock info from * init_pid_ns to get saved lock pid value. */ if (flc->flc_file != NULL) inode = file_inode(flc->flc_file); seq_printf(f, "%lld: ", id); if (repeat) seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx); if (flc->flc_flags & FL_POSIX) { if (flc->flc_flags & FL_ACCESS) seq_puts(f, "ACCESS"); else if (flc->flc_flags & FL_OFDLCK) seq_puts(f, "OFDLCK"); else seq_puts(f, "POSIX "); seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : "ADVISORY "); } else if (flc->flc_flags & FL_FLOCK) { seq_puts(f, "FLOCK ADVISORY "); } else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) { struct file_lease *lease = file_lease(flc); type = target_leasetype(lease); if (flc->flc_flags & FL_DELEG) seq_puts(f, "DELEG "); else seq_puts(f, "LEASE "); if (lease_breaking(lease)) seq_puts(f, "BREAKING "); else if (flc->flc_file) seq_puts(f, "ACTIVE "); else seq_puts(f, "BREAKER "); } else { seq_puts(f, "UNKNOWN UNKNOWN "); } seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : (type == F_RDLCK) ? "READ" : "UNLCK"); if (inode) { /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%lu ", pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { seq_printf(f, "%d <none>:0 ", pid); } if (flc->flc_flags & FL_POSIX) { if (fl->fl_end == OFFSET_MAX) seq_printf(f, "%Ld EOF\n", fl->fl_start); else seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end); } else { seq_puts(f, "0 EOF\n"); } } static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node) { struct file_lock_core *tmp; /* NULL node or root node */ if (node == NULL || node->flc_blocker == NULL) return NULL; /* Next member in the linked list could be itself */ tmp = list_next_entry(node, flc_blocked_member); if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests, flc_blocked_member) || tmp == node) { return NULL; } return tmp; } static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock_core *cur, *tmp; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); int level = 0; cur = hlist_entry(v, struct file_lock_core, flc_link); if (locks_translate_pid(cur, proc_pidns) == 0) return 0; /* View this crossed linked list as a binary tree, the first member of flc_blocked_requests * is the left child of current node, the next silibing in flc_blocked_member is the * right child, we can alse get the parent of current node from flc_blocker, so this * question becomes traversal of a binary tree */ while (cur != NULL) { if (level) lock_get_status(f, cur, iter->li_pos, "-> ", level); else lock_get_status(f, cur, iter->li_pos, "", level); if (!list_empty(&cur->flc_blocked_requests)) { /* Turn left */ cur = list_first_entry_or_null(&cur->flc_blocked_requests, struct file_lock_core, flc_blocked_member); level++; } else { /* Turn right */ tmp = get_next_blocked_member(cur); /* Fall back to parent node */ while (tmp == NULL && cur->flc_blocker != NULL) { cur = cur->flc_blocker; level--; tmp = get_next_blocked_member(cur); } cur = tmp; } } return 0; } static void __show_fd_locks(struct seq_file *f, struct list_head *head, int *id, struct file *filp, struct files_struct *files) { struct file_lock_core *fl; list_for_each_entry(fl, head, flc_list) { if (filp != fl->flc_file) continue; if (fl->flc_owner != files && fl->flc_owner != filp) continue; (*id)++; seq_puts(f, "lock:\t"); lock_get_status(f, fl, *id, "", 0); } } void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int id = 0; ctx = locks_inode_context(inode); if (!ctx) return; spin_lock(&ctx->flc_lock); __show_fd_locks(f, &ctx->flc_flock, &id, filp, files); __show_fd_locks(f, &ctx->flc_posix, &id, filp, files); __show_fd_locks(f, &ctx->flc_lease, &id, filp, files); spin_unlock(&ctx->flc_lock); } static void *locks_start(struct seq_file *f, loff_t *pos) __acquires(&blocked_lock_lock) { struct locks_iterator *iter = f->private; iter->li_pos = *pos + 1; percpu_down_write(&file_rwsem); spin_lock(&blocked_lock_lock); return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { struct locks_iterator *iter = f->private; ++iter->li_pos; return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) __releases(&blocked_lock_lock) { spin_unlock(&blocked_lock_lock); percpu_up_write(&file_rwsem); } static const struct seq_operations locks_seq_operations = { .start = locks_start, .next = locks_next, .stop = locks_stop, .show = locks_show, }; static int __init proc_locks_init(void) { proc_create_seq_private("locks", 0, NULL, &locks_seq_operations, sizeof(struct locks_iterator), NULL); return 0; } fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) { int i; flctx_cache = kmem_cache_create("file_lock_ctx", sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); filelease_cache = kmem_cache_create("file_lease_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); spin_lock_init(&fll->lock); INIT_HLIST_HEAD(&fll->hlist); } lease_notifier_chain_init(); return 0; } core_initcall(filelock_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; }; /* * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/mm/hmm.rst. * * MEMORY_DEVICE_COHERENT: * Device memory that is cache coherent from device and CPU point of view. This * is used on platforms that have an advanced system bus (like CAPI or CXL). A * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the folio refcount reaches 0. The reference count will be * reset to one by the core code after the method is called to prepare * for handing out the folio again. */ void (*folio_free)(struct folio *folio); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); /* * Handle the memory failure happens on a range of pfns. Notify the * processes who are using these pfns, and try to recover the data on * them if necessary. The mf_flags is finally passed to the recover * function through the whole notify routine. * * When this is not implemented, or it returns -EOPNOTSUPP, the caller * will fall back to a common handler called mf_generic_kill_procs(). */ int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags); /* * Used for private (un-addressable) device memory only. * This callback is used when a folio is split into * a smaller folio */ void (*folio_split)(struct folio *head, struct folio *tail); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref * @type: memory type: see MEMORY_* above in memremap.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. * A zero value (default) uses base pages as the vmemmap metadata * representation. A bigger value will set up compound struct pages * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; DECLARE_FLEX_ARRAY(struct range, ranges); }; }; static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) { return pgmap->ops && pgmap->ops->memory_failure; } static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) { return 1 << pgmap->vmemmap_shift; } static inline bool folio_is_device_private(const struct folio *folio) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && folio_is_device_private(page_folio(page)); } static inline bool folio_is_pci_p2pdma(const struct folio *folio) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline void *folio_zone_device_data(const struct folio *folio) { VM_WARN_ON_FOLIO(!folio_is_device_private(folio), folio); return folio->page.zone_device_data; } static inline void folio_set_zone_device_data(struct folio *folio, void *data) { VM_WARN_ON_FOLIO(!folio_is_device_private(folio), folio); folio->page.zone_device_data = data; } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && folio_is_pci_p2pdma(page_folio(page)); } static inline bool folio_is_device_coherent(const struct folio *folio) { return folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool is_device_coherent_page(const struct page *page) { return folio_is_device_coherent(page_folio(page)); } static inline bool folio_is_fsdax(const struct folio *folio) { return folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_FS_DAX; } static inline bool is_fsdax_page(const struct page *page) { return folio_is_fsdax(page_folio(page)); } #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page, struct dev_pagemap *pgmap, unsigned int order); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long memremap_compat_align(void); static inline void zone_device_folio_init(struct folio *folio, struct dev_pagemap *pgmap, unsigned int order) { zone_device_page_init(&folio->page, pgmap, order); if (order) folio_set_large_rmappable(folio); } static inline void zone_device_private_split_cb(struct folio *original_folio, struct folio *new_folio) { if (folio_is_device_private(original_folio)) { if (!original_folio->pgmap->ops->folio_split) { if (new_folio) { new_folio->pgmap = original_folio->pgmap; new_folio->page.mapping = original_folio->page.mapping; } } else { original_folio->pgmap->ops->folio_split(original_folio, new_folio); } } } #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } static inline void zone_device_private_split_cb(struct folio *original_folio, struct folio *new_folio) { } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ |
| 6 2 1 6 6 2 1 263 262 6 6 1 6 6 264 263 263 6 264 258 90 1 264 263 227 227 225 83 82 83 91 91 91 90 91 1 90 91 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/adjust_pc.h> #include <linux/compiler.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include "../../vgic/vgic.h" #define vtr_to_max_lr_idx(v) ((v) & 0xf) #define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1) #define vtr_to_nr_apr_regs(v) (1 << (vtr_to_nr_pre_bits(v) - 5)) u64 __gic_v3_get_lr(unsigned int lr) { switch (lr & 0xf) { case 0: return read_gicreg(ICH_LR0_EL2); case 1: return read_gicreg(ICH_LR1_EL2); case 2: return read_gicreg(ICH_LR2_EL2); case 3: return read_gicreg(ICH_LR3_EL2); case 4: return read_gicreg(ICH_LR4_EL2); case 5: return read_gicreg(ICH_LR5_EL2); case 6: return read_gicreg(ICH_LR6_EL2); case 7: return read_gicreg(ICH_LR7_EL2); case 8: return read_gicreg(ICH_LR8_EL2); case 9: return read_gicreg(ICH_LR9_EL2); case 10: return read_gicreg(ICH_LR10_EL2); case 11: return read_gicreg(ICH_LR11_EL2); case 12: return read_gicreg(ICH_LR12_EL2); case 13: return read_gicreg(ICH_LR13_EL2); case 14: return read_gicreg(ICH_LR14_EL2); case 15: return read_gicreg(ICH_LR15_EL2); } unreachable(); } void __gic_v3_set_lr(u64 val, int lr) { switch (lr & 0xf) { case 0: write_gicreg(val, ICH_LR0_EL2); break; case 1: write_gicreg(val, ICH_LR1_EL2); break; case 2: write_gicreg(val, ICH_LR2_EL2); break; case 3: write_gicreg(val, ICH_LR3_EL2); break; case 4: write_gicreg(val, ICH_LR4_EL2); break; case 5: write_gicreg(val, ICH_LR5_EL2); break; case 6: write_gicreg(val, ICH_LR6_EL2); break; case 7: write_gicreg(val, ICH_LR7_EL2); break; case 8: write_gicreg(val, ICH_LR8_EL2); break; case 9: write_gicreg(val, ICH_LR9_EL2); break; case 10: write_gicreg(val, ICH_LR10_EL2); break; case 11: write_gicreg(val, ICH_LR11_EL2); break; case 12: write_gicreg(val, ICH_LR12_EL2); break; case 13: write_gicreg(val, ICH_LR13_EL2); break; case 14: write_gicreg(val, ICH_LR14_EL2); break; case 15: write_gicreg(val, ICH_LR15_EL2); break; } } static void __vgic_v3_write_ap0rn(u32 val, int n) { switch (n) { case 0: write_gicreg(val, ICH_AP0R0_EL2); break; case 1: write_gicreg(val, ICH_AP0R1_EL2); break; case 2: write_gicreg(val, ICH_AP0R2_EL2); break; case 3: write_gicreg(val, ICH_AP0R3_EL2); break; } } static void __vgic_v3_write_ap1rn(u32 val, int n) { switch (n) { case 0: write_gicreg(val, ICH_AP1R0_EL2); break; case 1: write_gicreg(val, ICH_AP1R1_EL2); break; case 2: write_gicreg(val, ICH_AP1R2_EL2); break; case 3: write_gicreg(val, ICH_AP1R3_EL2); break; } } static u32 __vgic_v3_read_ap0rn(int n) { u32 val; switch (n) { case 0: val = read_gicreg(ICH_AP0R0_EL2); break; case 1: val = read_gicreg(ICH_AP0R1_EL2); break; case 2: val = read_gicreg(ICH_AP0R2_EL2); break; case 3: val = read_gicreg(ICH_AP0R3_EL2); break; default: unreachable(); } return val; } static u32 __vgic_v3_read_ap1rn(int n) { u32 val; switch (n) { case 0: val = read_gicreg(ICH_AP1R0_EL2); break; case 1: val = read_gicreg(ICH_AP1R1_EL2); break; case 2: val = read_gicreg(ICH_AP1R2_EL2); break; case 3: val = read_gicreg(ICH_AP1R3_EL2); break; default: unreachable(); } return val; } static u64 compute_ich_hcr(struct vgic_v3_cpu_if *cpu_if) { return cpu_if->vgic_hcr | vgic_ich_hcr_trap_bits(); } void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) { u64 used_lrs = cpu_if->used_lrs; /* * Make sure stores to the GIC via the memory mapped interface * are now visible to the system register interface when reading the * LRs, and when reading back the VMCR on non-VHE systems. */ if (used_lrs || !has_vhe()) { if (!cpu_if->vgic_sre) { dsb(sy); isb(); } } if (used_lrs) { int i; u32 elrsr; elrsr = read_gicreg(ICH_ELRSR_EL2); for (i = 0; i < used_lrs; i++) { if (elrsr & (1 << i)) cpu_if->vgic_lr[i] &= ~ICH_LR_STATE; else cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); __gic_v3_set_lr(0, i); } } cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); if (cpu_if->vgic_hcr & ICH_HCR_EL2_LRENPIE) { u64 val = read_gicreg(ICH_HCR_EL2); cpu_if->vgic_hcr &= ~ICH_HCR_EL2_EOIcount; cpu_if->vgic_hcr |= val & ICH_HCR_EL2_EOIcount; } write_gicreg(0, ICH_HCR_EL2); /* * Hack alert: On NV, this results in a trap so that the above write * actually takes effect... No synchronisation is necessary, as we * only care about the effects when this traps. */ read_gicreg(ICH_MISR_EL2); } void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) { u64 used_lrs = cpu_if->used_lrs; int i; write_gicreg(compute_ich_hcr(cpu_if), ICH_HCR_EL2); for (i = 0; i < used_lrs; i++) __gic_v3_set_lr(cpu_if->vgic_lr[i], i); /* * Ensure that writes to the LRs, and on non-VHE systems ensure that * the write to the VMCR in __vgic_v3_activate_traps(), will have * reached the (re)distributors. This ensure the guest will read the * correct values from the memory-mapped interface. */ if (used_lrs || !has_vhe()) { if (!cpu_if->vgic_sre) { isb(); dsb(sy); } } } void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) { /* * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a * Group0 interrupt (as generated in GICv2 mode) to be * delivered as a FIQ to the guest, with potentially fatal * consequences. So we must make sure that ICC_SRE_EL1 has * been actually programmed with the value we want before * starting to mess with the rest of the GIC, and VMCR_EL2 in * particular. This logic must be called before * __vgic_v3_restore_state(). * * However, if the vgic is disabled (ICH_HCR_EL2.EN==0), no GIC is * provisioned at all. In order to prevent illegal accesses to the * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1 * so that the trap bits can take effect. Yes, we *loves* the GIC. */ if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) { write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1); isb(); } else if (!cpu_if->vgic_sre) { write_gicreg(0, ICC_SRE_EL1); isb(); write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2); if (has_vhe()) { /* * Ensure that the write to the VMCR will have reached * the (re)distributors. This ensure the guest will * read the correct values from the memory-mapped * interface. */ isb(); dsb(sy); } } /* Only disable SRE if the host implements the GICv2 interface */ if (static_branch_unlikely(&vgic_v3_has_v2_compat)) { /* * Prevent the guest from touching the ICC_SRE_EL1 system * register. Note that this may not have any effect, as * ICC_SRE_EL2.Enable being RAO/WI is a valid implementation. */ write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); } /* * If we need to trap system registers, we must write ICH_HCR_EL2 * anyway, even if no interrupts are being injected. Note that this * also applies if we don't expect any system register access (no * vgic at all). In any case, no need to provide MI configuration. */ if (static_branch_unlikely(&vgic_v3_cpuif_trap) || cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre) write_gicreg(vgic_ich_hcr_trap_bits() | ICH_HCR_EL2_En, ICH_HCR_EL2); } void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) { u64 val; /* Only restore SRE if the host implements the GICv2 interface */ if (static_branch_unlikely(&vgic_v3_has_v2_compat)) { val = read_gicreg(ICC_SRE_EL2); write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); if (!cpu_if->vgic_sre) { /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ isb(); write_gicreg(1, ICC_SRE_EL1); } } /* * If we were trapping system registers, we enabled the VGIC even if * no interrupts were being injected, and we disable it again here. */ if (static_branch_unlikely(&vgic_v3_cpuif_trap) || cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre) write_gicreg(0, ICH_HCR_EL2); } void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) { u64 val; u32 nr_pre_bits; val = read_gicreg(ICH_VTR_EL2); nr_pre_bits = vtr_to_nr_pre_bits(val); switch (nr_pre_bits) { case 7: cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); fallthrough; case 6: cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); fallthrough; default: cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); } switch (nr_pre_bits) { case 7: cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); fallthrough; case 6: cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); fallthrough; default: cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); } } static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) { u64 val; u32 nr_pre_bits; val = read_gicreg(ICH_VTR_EL2); nr_pre_bits = vtr_to_nr_pre_bits(val); switch (nr_pre_bits) { case 7: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); fallthrough; case 6: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); fallthrough; default: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); } switch (nr_pre_bits) { case 7: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); fallthrough; case 6: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); fallthrough; default: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); } } void __vgic_v3_init_lrs(void) { int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2)); int i; for (i = 0; i <= max_lr_idx; i++) __gic_v3_set_lr(0, i); } /* * Return the GIC CPU configuration: * - [31:0] ICH_VTR_EL2 * - [62:32] RES0 * - [63] MMIO (GICv2) capable */ u64 __vgic_v3_get_gic_config(void) { u64 val, sre; unsigned long flags = 0; /* * In compat mode, we cannot access ICC_SRE_EL1 at any EL * other than EL1 itself; just return the * ICH_VTR_EL2. ICC_IDR0_EL1 is only implemented on a GICv5 * system, so we first check if we have GICv5 support. */ if (cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) return read_gicreg(ICH_VTR_EL2); sre = read_gicreg(ICC_SRE_EL1); /* * To check whether we have a MMIO-based (GICv2 compatible) * CPU interface, we need to disable the system register * view. * * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates * that to be able to set ICC_SRE_EL1.SRE to 0, all the * interrupt overrides must be set. You've got to love this. * * As we always run VHE with HCR_xMO set, no extra xMO * manipulation is required in that case. * * To safely disable SRE, we have to prevent any interrupt * from firing (which would be deadly). This only makes sense * on VHE, as interrupts are already masked for nVHE as part * of the exception entry to EL2. */ if (has_vhe()) { flags = local_daif_save(); } else { sysreg_clear_set_hcr(0, HCR_AMO | HCR_FMO | HCR_IMO); isb(); } write_gicreg(0, ICC_SRE_EL1); isb(); val = read_gicreg(ICC_SRE_EL1); write_gicreg(sre, ICC_SRE_EL1); isb(); if (has_vhe()) { local_daif_restore(flags); } else { sysreg_clear_set_hcr(HCR_AMO | HCR_FMO | HCR_IMO, 0); isb(); } val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63); val |= read_gicreg(ICH_VTR_EL2); return val; } static void __vgic_v3_compat_mode_enable(void) { if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) return; sysreg_clear_set_s(SYS_ICH_VCTLR_EL2, 0, ICH_VCTLR_EL2_V3); /* Wait for V3 to become enabled */ isb(); } static u64 __vgic_v3_read_vmcr(void) { return read_gicreg(ICH_VMCR_EL2); } static void __vgic_v3_write_vmcr(u32 vmcr) { write_gicreg(vmcr, ICH_VMCR_EL2); } void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if) { __vgic_v3_compat_mode_enable(); /* * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen * is dependent on ICC_SRE_EL1.SRE, and we have to perform the * VMCR_EL2 save/restore in the world switch. */ if (cpu_if->vgic_sre) __vgic_v3_write_vmcr(cpu_if->vgic_vmcr); __vgic_v3_restore_aprs(cpu_if); } static int __vgic_v3_bpr_min(void) { /* See Pseudocode for VPriorityGroup */ return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2)); } static int __vgic_v3_get_group(struct kvm_vcpu *vcpu) { u64 esr = kvm_vcpu_get_esr(vcpu); u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; return crm != 8; } #define GICv3_IDLE_PRIORITY 0xff static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr, u64 *lr_val) { unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; u8 priority = GICv3_IDLE_PRIORITY; int i, lr = -1; for (i = 0; i < used_lrs; i++) { u64 val = __gic_v3_get_lr(i); u8 lr_prio = (val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; /* Not pending in the state? */ if ((val & ICH_LR_STATE) != ICH_LR_PENDING_BIT) continue; /* Group-0 interrupt, but Group-0 disabled? */ if (!(val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_EL2_VENG0_MASK)) continue; /* Group-1 interrupt, but Group-1 disabled? */ if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_EL2_VENG1_MASK)) continue; /* Not the highest priority? */ if (lr_prio >= priority) continue; /* This is a candidate */ priority = lr_prio; *lr_val = val; lr = i; } if (lr == -1) *lr_val = ICC_IAR1_EL1_SPURIOUS; return lr; } static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid, u64 *lr_val) { unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; int i; for (i = 0; i < used_lrs; i++) { u64 val = __gic_v3_get_lr(i); if ((val & ICH_LR_VIRTUAL_ID_MASK) == intid && (val & ICH_LR_ACTIVE_BIT)) { *lr_val = val; return i; } } *lr_val = ICC_IAR1_EL1_SPURIOUS; return -1; } static int __vgic_v3_get_highest_active_priority(void) { u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); u32 hap = 0; int i; for (i = 0; i < nr_apr_regs; i++) { u32 val; /* * The ICH_AP0Rn_EL2 and ICH_AP1Rn_EL2 registers * contain the active priority levels for this VCPU * for the maximum number of supported priority * levels, and we return the full priority level only * if the BPR is programmed to its minimum, otherwise * we return a combination of the priority level and * subpriority, as determined by the setting of the * BPR, but without the full subpriority. */ val = __vgic_v3_read_ap0rn(i); val |= __vgic_v3_read_ap1rn(i); if (!val) { hap += 32; continue; } return (hap + __ffs(val)) << __vgic_v3_bpr_min(); } return GICv3_IDLE_PRIORITY; } static unsigned int __vgic_v3_get_bpr0(u32 vmcr) { return FIELD_GET(ICH_VMCR_EL2_VBPR0, vmcr); } static unsigned int __vgic_v3_get_bpr1(u32 vmcr) { unsigned int bpr; if (vmcr & ICH_VMCR_EL2_VCBPR_MASK) { bpr = __vgic_v3_get_bpr0(vmcr); if (bpr < 7) bpr++; } else { bpr = FIELD_GET(ICH_VMCR_EL2_VBPR1, vmcr); } return bpr; } /* * Convert a priority to a preemption level, taking the relevant BPR * into account by zeroing the sub-priority bits. */ static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) { unsigned int bpr; if (!grp) bpr = __vgic_v3_get_bpr0(vmcr) + 1; else bpr = __vgic_v3_get_bpr1(vmcr); return pri & (GENMASK(7, 0) << bpr); } /* * The priority value is independent of any of the BPR values, so we * normalize it using the minimal BPR value. This guarantees that no * matter what the guest does with its BPR, we can always set/get the * same value of a priority. */ static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) { u8 pre, ap; u32 val; int apr; pre = __vgic_v3_pri_to_pre(pri, vmcr, grp); ap = pre >> __vgic_v3_bpr_min(); apr = ap / 32; if (!grp) { val = __vgic_v3_read_ap0rn(apr); __vgic_v3_write_ap0rn(val | BIT(ap % 32), apr); } else { val = __vgic_v3_read_ap1rn(apr); __vgic_v3_write_ap1rn(val | BIT(ap % 32), apr); } } static int __vgic_v3_clear_highest_active_priority(void) { u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); u32 hap = 0; int i; for (i = 0; i < nr_apr_regs; i++) { u32 ap0, ap1; int c0, c1; ap0 = __vgic_v3_read_ap0rn(i); ap1 = __vgic_v3_read_ap1rn(i); if (!ap0 && !ap1) { hap += 32; continue; } c0 = ap0 ? __ffs(ap0) : 32; c1 = ap1 ? __ffs(ap1) : 32; /* Always clear the LSB, which is the highest priority */ if (c0 < c1) { ap0 &= ~BIT(c0); __vgic_v3_write_ap0rn(ap0, i); hap += c0; } else { ap1 &= ~BIT(c1); __vgic_v3_write_ap1rn(ap1, i); hap += c1; } /* Rescale to 8 bits of priority */ return hap << __vgic_v3_bpr_min(); } return GICv3_IDLE_PRIORITY; } static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 lr_val; u8 lr_prio, pmr; int lr, grp; grp = __vgic_v3_get_group(vcpu); lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); if (lr < 0) goto spurious; if (grp != !!(lr_val & ICH_LR_GROUP)) goto spurious; pmr = FIELD_GET(ICH_VMCR_EL2_VPMR, vmcr); lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; if (pmr <= lr_prio) goto spurious; if (__vgic_v3_get_highest_active_priority() <= __vgic_v3_pri_to_pre(lr_prio, vmcr, grp)) goto spurious; lr_val &= ~ICH_LR_STATE; lr_val |= ICH_LR_ACTIVE_BIT; __gic_v3_set_lr(lr_val, lr); __vgic_v3_set_active_priority(lr_prio, vmcr, grp); vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); return; spurious: vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS); } static void __vgic_v3_clear_active_lr(int lr, u64 lr_val) { lr_val &= ~ICH_LR_ACTIVE_BIT; if (lr_val & ICH_LR_HW) { u32 pid; pid = (lr_val & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT; gic_write_dir(pid); } __gic_v3_set_lr(lr_val, lr); } static void __vgic_v3_bump_eoicount(void) { u32 hcr; hcr = read_gicreg(ICH_HCR_EL2); hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT; write_gicreg(hcr, ICH_HCR_EL2); } static int ___vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vid = vcpu_get_reg(vcpu, rt); u64 lr_val; int lr; /* EOImode == 0, nothing to be done here */ if (!(vmcr & ICH_VMCR_EL2_VEOIM_MASK)) return 1; /* No deactivate to be performed on an LPI */ if (vid >= VGIC_MIN_LPI) return 1; lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); if (lr != -1) { __vgic_v3_clear_active_lr(lr, lr_val); return 1; } return 0; } static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { if (!___vgic_v3_write_dir(vcpu, vmcr, rt)) __vgic_v3_bump_eoicount(); } static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vid = vcpu_get_reg(vcpu, rt); u64 lr_val; u8 lr_prio, act_prio; int lr, grp; grp = __vgic_v3_get_group(vcpu); /* Drop priority in any case */ act_prio = __vgic_v3_clear_highest_active_priority(); lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); if (lr == -1) { /* Do not bump EOIcount for LPIs that aren't in the LRs */ if (!(vid >= VGIC_MIN_LPI)) __vgic_v3_bump_eoicount(); return; } /* EOImode == 1 and not an LPI, nothing to be done here */ if ((vmcr & ICH_VMCR_EL2_VEOIM_MASK) && !(vid >= VGIC_MIN_LPI)) return; lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; /* If priorities or group do not match, the guest has fscked-up. */ if (grp != !!(lr_val & ICH_LR_GROUP) || __vgic_v3_pri_to_pre(lr_prio, vmcr, grp) != act_prio) return; /* Let's now perform the deactivation */ __vgic_v3_clear_active_lr(lr, lr_val); } static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VENG0, vmcr)); } static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VENG1, vmcr)); } static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); FIELD_MODIFY(ICH_VMCR_EL2_VENG0, &vmcr, val & 1); __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); FIELD_MODIFY(ICH_VMCR_EL2_VENG1, &vmcr, val & 1); __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr)); } static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr)); } static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); u8 bpr_min = __vgic_v3_bpr_min() - 1; /* Enforce BPR limiting */ if (val < bpr_min) val = bpr_min; FIELD_MODIFY(ICH_VMCR_EL2_VBPR0, &vmcr, val); __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); u8 bpr_min = __vgic_v3_bpr_min(); if (FIELD_GET(ICH_VMCR_EL2_VCBPR, val)) return; /* Enforce BPR limiting */ if (val < bpr_min) val = bpr_min; FIELD_MODIFY(ICH_VMCR_EL2_VBPR1, &vmcr, val); __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n) { u32 val; if (!__vgic_v3_get_group(vcpu)) val = __vgic_v3_read_ap0rn(n); else val = __vgic_v3_read_ap1rn(n); vcpu_set_reg(vcpu, rt, val); } static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n) { u32 val = vcpu_get_reg(vcpu, rt); if (!__vgic_v3_get_group(vcpu)) __vgic_v3_write_ap0rn(val, n); else __vgic_v3_write_ap1rn(val, n); } static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 0); } static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 1); } static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 2); } static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 3); } static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 0); } static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 1); } static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 2); } static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 3); } static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 lr_val; int lr, lr_grp, grp; grp = __vgic_v3_get_group(vcpu); lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); if (lr == -1) goto spurious; lr_grp = !!(lr_val & ICH_LR_GROUP); if (lr_grp != grp) lr_val = ICC_IAR1_EL1_SPURIOUS; spurious: vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); } static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VPMR, vmcr)); } static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = vcpu_get_reg(vcpu, rt); FIELD_MODIFY(ICH_VMCR_EL2_VPMR, &vmcr, val); write_gicreg(vmcr, ICH_VMCR_EL2); } static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = __vgic_v3_get_highest_active_priority(); vcpu_set_reg(vcpu, rt, val); } static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vtr, val; vtr = read_gicreg(ICH_VTR_EL2); /* PRIbits */ val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT; /* IDbits */ val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT; /* A3V */ val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT; /* EOImode */ val |= FIELD_PREP(ICC_CTLR_EL1_EOImode_MASK, FIELD_GET(ICH_VMCR_EL2_VEOIM, vmcr)); /* CBPR */ val |= FIELD_PREP(ICC_CTLR_EL1_CBPR_MASK, FIELD_GET(ICH_VMCR_EL2_VCBPR, vmcr)); vcpu_set_reg(vcpu, rt, val); } static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = vcpu_get_reg(vcpu, rt); FIELD_MODIFY(ICH_VMCR_EL2_VCBPR, &vmcr, FIELD_GET(ICC_CTLR_EL1_CBPR_MASK, val)); FIELD_MODIFY(ICH_VMCR_EL2_VEOIM, &vmcr, FIELD_GET(ICC_CTLR_EL1_EOImode_MASK, val)); write_gicreg(vmcr, ICH_VMCR_EL2); } static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu, u32 sysreg, bool is_read) { u64 ich_hcr; if (!is_nested_ctxt(vcpu)) return false; ich_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2); switch (sysreg) { case SYS_ICC_IGRPEN0_EL1: if (is_read && (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1)) return true; if (!is_read && (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1)) return true; fallthrough; case SYS_ICC_AP0Rn_EL1(0): case SYS_ICC_AP0Rn_EL1(1): case SYS_ICC_AP0Rn_EL1(2): case SYS_ICC_AP0Rn_EL1(3): case SYS_ICC_BPR0_EL1: case SYS_ICC_EOIR0_EL1: case SYS_ICC_HPPIR0_EL1: case SYS_ICC_IAR0_EL1: return ich_hcr & ICH_HCR_EL2_TALL0; case SYS_ICC_IGRPEN1_EL1: if (is_read && (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1)) return true; if (!is_read && (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1)) return true; fallthrough; case SYS_ICC_AP1Rn_EL1(0): case SYS_ICC_AP1Rn_EL1(1): case SYS_ICC_AP1Rn_EL1(2): case SYS_ICC_AP1Rn_EL1(3): case SYS_ICC_BPR1_EL1: case SYS_ICC_EOIR1_EL1: case SYS_ICC_HPPIR1_EL1: case SYS_ICC_IAR1_EL1: return ich_hcr & ICH_HCR_EL2_TALL1; case SYS_ICC_DIR_EL1: if (ich_hcr & ICH_HCR_EL2_TDIR) return true; fallthrough; case SYS_ICC_RPR_EL1: case SYS_ICC_CTLR_EL1: case SYS_ICC_PMR_EL1: return ich_hcr & ICH_HCR_EL2_TC; default: return false; } } int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) { int rt; u64 esr; u32 vmcr; void (*fn)(struct kvm_vcpu *, u32, int); bool is_read; u32 sysreg; if (kern_hyp_va(vcpu->kvm)->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3) return 0; esr = kvm_vcpu_get_esr(vcpu); if (vcpu_mode_is_32bit(vcpu)) { if (!kvm_condition_valid(vcpu)) { __kvm_skip_instr(vcpu); return 1; } sysreg = esr_cp15_to_sysreg(esr); } else { sysreg = esr_sys64_to_sysreg(esr); } is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ; if (__vgic_v3_check_trap_forwarding(vcpu, sysreg, is_read)) return 0; switch (sysreg) { case SYS_ICC_IAR0_EL1: case SYS_ICC_IAR1_EL1: if (unlikely(!is_read)) return 0; fn = __vgic_v3_read_iar; break; case SYS_ICC_EOIR0_EL1: case SYS_ICC_EOIR1_EL1: if (unlikely(is_read)) return 0; fn = __vgic_v3_write_eoir; break; case SYS_ICC_IGRPEN1_EL1: if (is_read) fn = __vgic_v3_read_igrpen1; else fn = __vgic_v3_write_igrpen1; break; case SYS_ICC_BPR1_EL1: if (is_read) fn = __vgic_v3_read_bpr1; else fn = __vgic_v3_write_bpr1; break; case SYS_ICC_AP0Rn_EL1(0): case SYS_ICC_AP1Rn_EL1(0): if (is_read) fn = __vgic_v3_read_apxr0; else fn = __vgic_v3_write_apxr0; break; case SYS_ICC_AP0Rn_EL1(1): case SYS_ICC_AP1Rn_EL1(1): if (is_read) fn = __vgic_v3_read_apxr1; else fn = __vgic_v3_write_apxr1; break; case SYS_ICC_AP0Rn_EL1(2): case SYS_ICC_AP1Rn_EL1(2): if (is_read) fn = __vgic_v3_read_apxr2; else fn = __vgic_v3_write_apxr2; break; case SYS_ICC_AP0Rn_EL1(3): case SYS_ICC_AP1Rn_EL1(3): if (is_read) fn = __vgic_v3_read_apxr3; else fn = __vgic_v3_write_apxr3; break; case SYS_ICC_HPPIR0_EL1: case SYS_ICC_HPPIR1_EL1: if (unlikely(!is_read)) return 0; fn = __vgic_v3_read_hppir; break; case SYS_ICC_IGRPEN0_EL1: if (is_read) fn = __vgic_v3_read_igrpen0; else fn = __vgic_v3_write_igrpen0; break; case SYS_ICC_BPR0_EL1: if (is_read) fn = __vgic_v3_read_bpr0; else fn = __vgic_v3_write_bpr0; break; case SYS_ICC_DIR_EL1: if (unlikely(is_read)) return 0; /* * Full exit if required to handle overflow deactivation, * unless we can emulate it in the LRs (likely the majority * of the cases). */ if (vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr & ICH_HCR_EL2_TDIR) { int ret; ret = ___vgic_v3_write_dir(vcpu, __vgic_v3_read_vmcr(), kvm_vcpu_sys_get_rt(vcpu)); if (ret) __kvm_skip_instr(vcpu); return ret; } fn = __vgic_v3_write_dir; break; case SYS_ICC_RPR_EL1: if (unlikely(!is_read)) return 0; fn = __vgic_v3_read_rpr; break; case SYS_ICC_CTLR_EL1: if (is_read) fn = __vgic_v3_read_ctlr; else fn = __vgic_v3_write_ctlr; break; case SYS_ICC_PMR_EL1: if (is_read) fn = __vgic_v3_read_pmr; else fn = __vgic_v3_write_pmr; break; default: return 0; } vmcr = __vgic_v3_read_vmcr(); rt = kvm_vcpu_sys_get_rt(vcpu); fn(vcpu, vmcr, rt); __kvm_skip_instr(vcpu); return 1; } |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/macsec.c - MACsec device * * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net> */ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/module.h> #include <crypto/aead.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> #include <net/genetlink.h> #include <net/sock.h> #include <net/gro_cells.h> #include <net/macsec.h> #include <net/dst_metadata.h> #include <net/netdev_lock.h> #include <linux/phy.h> #include <linux/byteorder/generic.h> #include <linux/if_arp.h> #include <uapi/linux/if_macsec.h> /* SecTAG length = macsec_eth_header without the optional SCI */ #define MACSEC_TAG_LEN 6 struct macsec_eth_header { struct ethhdr eth; /* SecTAG */ u8 tci_an; #if defined(__LITTLE_ENDIAN_BITFIELD) u8 short_length:6, unused:2; #elif defined(__BIG_ENDIAN_BITFIELD) u8 unused:2, short_length:6; #else #error "Please fix <asm/byteorder.h>" #endif __be32 packet_number; u8 secure_channel_id[8]; /* optional */ } __packed; /* minimum secure data length deemed "not short", see IEEE 802.1AE-2006 9.7 */ #define MIN_NON_SHORT_LEN 48 #define GCM_AES_IV_LEN 12 #define for_each_rxsc(secy, sc) \ for (sc = rcu_dereference_bh(secy->rx_sc); \ sc; \ sc = rcu_dereference_bh(sc->next)) #define for_each_rxsc_rtnl(secy, sc) \ for (sc = rtnl_dereference(secy->rx_sc); \ sc; \ sc = rtnl_dereference(sc->next)) #define pn_same_half(pn1, pn2) (!(((pn1) >> 31) ^ ((pn2) >> 31))) struct gcm_iv_xpn { union { u8 short_secure_channel_id[4]; ssci_t ssci; }; __be64 pn; } __packed; struct gcm_iv { union { u8 secure_channel_id[8]; sci_t sci; }; __be32 pn; }; #define MACSEC_VALIDATE_DEFAULT MACSEC_VALIDATE_STRICT struct pcpu_secy_stats { struct macsec_dev_stats stats; struct u64_stats_sync syncp; }; /** * struct macsec_dev - private data * @secy: SecY config * @real_dev: pointer to underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @stats: MACsec device stats * @secys: linked list of SecY's on the underlying device * @gro_cells: pointer to the Generic Receive Offload cell * @offload: status of offloading on the MACsec device * @insert_tx_tag: when offloading, device requires to insert an * additional tag */ struct macsec_dev { struct macsec_secy secy; struct net_device *real_dev; netdevice_tracker dev_tracker; struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; enum macsec_offload offload; bool insert_tx_tag; }; /** * struct macsec_rxh_data - rx_handler private argument * @secys: linked list of SecY's on this underlying device */ struct macsec_rxh_data { struct list_head secys; }; static struct macsec_dev *macsec_priv(const struct net_device *dev) { return (struct macsec_dev *)netdev_priv(dev); } static struct macsec_rxh_data *macsec_data_rcu(const struct net_device *dev) { return rcu_dereference_bh(dev->rx_handler_data); } static struct macsec_rxh_data *macsec_data_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } struct macsec_cb { struct aead_request *req; union { struct macsec_tx_sa *tx_sa; struct macsec_rx_sa *rx_sa; }; u8 assoc_num; bool valid; bool has_sci; }; static struct macsec_rx_sa *macsec_rxsa_get(struct macsec_rx_sa __rcu *ptr) { struct macsec_rx_sa *sa = rcu_dereference_bh(ptr); if (!sa || !sa->active) return NULL; if (!refcount_inc_not_zero(&sa->refcnt)) return NULL; return sa; } static void free_rx_sc_rcu(struct rcu_head *head) { struct macsec_rx_sc *rx_sc = container_of(head, struct macsec_rx_sc, rcu_head); free_percpu(rx_sc->stats); kfree(rx_sc); } static struct macsec_rx_sc *macsec_rxsc_get(struct macsec_rx_sc *sc) { return refcount_inc_not_zero(&sc->refcnt) ? sc : NULL; } static void macsec_rxsc_put(struct macsec_rx_sc *sc) { if (refcount_dec_and_test(&sc->refcnt)) call_rcu(&sc->rcu_head, free_rx_sc_rcu); } static void free_rxsa(struct rcu_head *head) { struct macsec_rx_sa *sa = container_of(head, struct macsec_rx_sa, rcu); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); kfree(sa); } static void macsec_rxsa_put(struct macsec_rx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) call_rcu(&sa->rcu, free_rxsa); } static struct macsec_tx_sa *macsec_txsa_get(struct macsec_tx_sa __rcu *ptr) { struct macsec_tx_sa *sa = rcu_dereference_bh(ptr); if (!sa || !sa->active) return NULL; if (!refcount_inc_not_zero(&sa->refcnt)) return NULL; return sa; } static void free_txsa(struct rcu_head *head) { struct macsec_tx_sa *sa = container_of(head, struct macsec_tx_sa, rcu); crypto_free_aead(sa->key.tfm); free_percpu(sa->stats); kfree(sa); } static void macsec_txsa_put(struct macsec_tx_sa *sa) { if (refcount_dec_and_test(&sa->refcnt)) call_rcu(&sa->rcu, free_txsa); } static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct macsec_cb) > sizeof(skb->cb)); return (struct macsec_cb *)skb->cb; } #define MACSEC_PORT_SCB (0x0000) #define MACSEC_UNDEF_SCI ((__force sci_t)0xffffffffffffffffULL) #define MACSEC_UNDEF_SSCI ((__force ssci_t)0xffffffff) #define MACSEC_GCM_AES_128_SAK_LEN 16 #define MACSEC_GCM_AES_256_SAK_LEN 32 #define DEFAULT_SAK_LEN MACSEC_GCM_AES_128_SAK_LEN #define DEFAULT_XPN false #define DEFAULT_SEND_SCI true #define DEFAULT_ENCRYPT false #define DEFAULT_ENCODING_SA 0 #define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1)) static sci_t make_sci(const u8 *addr, __be16 port) { sci_t sci; memcpy(&sci, addr, ETH_ALEN); memcpy(((char *)&sci) + ETH_ALEN, &port, sizeof(port)); return sci; } static sci_t macsec_active_sci(struct macsec_secy *secy) { struct macsec_rx_sc *rx_sc = rcu_dereference_bh(secy->rx_sc); /* Case single RX SC */ if (rx_sc && !rcu_dereference_bh(rx_sc->next)) return (rx_sc->active) ? rx_sc->sci : 0; /* Case no RX SC or multiple */ else return 0; } static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present, struct macsec_rxh_data *rxd) { struct macsec_dev *macsec; sci_t sci = 0; /* SC = 1 */ if (sci_present) { memcpy(&sci, hdr->secure_channel_id, sizeof(hdr->secure_channel_id)); /* SC = 0; ES = 0 */ } else if ((!(hdr->tci_an & (MACSEC_TCI_ES | MACSEC_TCI_SC))) && (list_is_singular(&rxd->secys))) { /* Only one SECY should exist on this scenario */ macsec = list_first_or_null_rcu(&rxd->secys, struct macsec_dev, secys); if (macsec) return macsec_active_sci(&macsec->secy); } else { sci = make_sci(hdr->eth.h_source, MACSEC_PORT_ES); } return sci; } static unsigned int macsec_sectag_len(bool sci_present) { return MACSEC_TAG_LEN + (sci_present ? MACSEC_SCI_LEN : 0); } static unsigned int macsec_hdr_len(bool sci_present) { return macsec_sectag_len(sci_present) + ETH_HLEN; } static unsigned int macsec_extra_len(bool sci_present) { return macsec_sectag_len(sci_present) + sizeof(__be16); } /* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */ static void macsec_fill_sectag(struct macsec_eth_header *h, const struct macsec_secy *secy, u32 pn, bool sci_present) { const struct macsec_tx_sc *tx_sc = &secy->tx_sc; memset(&h->tci_an, 0, macsec_sectag_len(sci_present)); h->eth.h_proto = htons(ETH_P_MACSEC); if (sci_present) { h->tci_an |= MACSEC_TCI_SC; memcpy(&h->secure_channel_id, &secy->sci, sizeof(h->secure_channel_id)); } else { if (tx_sc->end_station) h->tci_an |= MACSEC_TCI_ES; if (tx_sc->scb) h->tci_an |= MACSEC_TCI_SCB; } h->packet_number = htonl(pn); /* with GCM, C/E clear for !encrypt, both set for encrypt */ if (tx_sc->encrypt) h->tci_an |= MACSEC_TCI_CONFID; else if (secy->icv_len != MACSEC_DEFAULT_ICV_LEN) h->tci_an |= MACSEC_TCI_C; h->tci_an |= tx_sc->encoding_sa; } static void macsec_set_shortlen(struct macsec_eth_header *h, size_t data_len) { if (data_len < MIN_NON_SHORT_LEN) h->short_length = data_len; } /* Checks if a MACsec interface is being offloaded to an hardware engine */ static bool macsec_is_offloaded(struct macsec_dev *macsec) { if (macsec->offload == MACSEC_OFFLOAD_MAC || macsec->offload == MACSEC_OFFLOAD_PHY) return true; return false; } /* Checks if underlying layers implement MACsec offloading functions. */ static bool macsec_check_offload(enum macsec_offload offload, struct macsec_dev *macsec) { if (!macsec || !macsec->real_dev) return false; if (offload == MACSEC_OFFLOAD_PHY) return macsec->real_dev->phydev && macsec->real_dev->phydev->macsec_ops; else if (offload == MACSEC_OFFLOAD_MAC) return macsec->real_dev->features & NETIF_F_HW_MACSEC && macsec->real_dev->macsec_ops; return false; } static const struct macsec_ops *__macsec_get_ops(enum macsec_offload offload, struct macsec_dev *macsec, struct macsec_context *ctx) { if (ctx) { memset(ctx, 0, sizeof(*ctx)); ctx->offload = offload; if (offload == MACSEC_OFFLOAD_PHY) ctx->phydev = macsec->real_dev->phydev; else if (offload == MACSEC_OFFLOAD_MAC) ctx->netdev = macsec->real_dev; } if (offload == MACSEC_OFFLOAD_PHY) return macsec->real_dev->phydev->macsec_ops; else return macsec->real_dev->macsec_ops; } /* Returns a pointer to the MACsec ops struct if any and updates the MACsec * context device reference if provided. */ static const struct macsec_ops *macsec_get_ops(struct macsec_dev *macsec, struct macsec_context *ctx) { if (!macsec_check_offload(macsec->offload, macsec)) return NULL; return __macsec_get_ops(macsec->offload, macsec, ctx); } /* validate MACsec packet according to IEEE 802.1AE-2018 9.12 */ static bool macsec_validate_skb(struct sk_buff *skb, u16 icv_len, bool xpn) { struct macsec_eth_header *h = (struct macsec_eth_header *)skb->data; int len = skb->len - 2 * ETH_ALEN; int extra_len = macsec_extra_len(!!(h->tci_an & MACSEC_TCI_SC)) + icv_len; /* a) It comprises at least 17 octets */ if (skb->len <= 16) return false; /* b) MACsec EtherType: already checked */ /* c) V bit is clear */ if (h->tci_an & MACSEC_TCI_VERSION) return false; /* d) ES or SCB => !SC */ if ((h->tci_an & MACSEC_TCI_ES || h->tci_an & MACSEC_TCI_SCB) && (h->tci_an & MACSEC_TCI_SC)) return false; /* e) Bits 7 and 8 of octet 4 of the SecTAG are clear */ if (h->unused) return false; /* rx.pn != 0 if not XPN (figure 10-5 with 802.11AEbw-2013 amendment) */ if (!h->packet_number && !xpn) return false; /* length check, f) g) h) i) */ if (h->short_length) return len == extra_len + h->short_length; return len >= extra_len + MIN_NON_SHORT_LEN; } #define MACSEC_NEEDED_HEADROOM (macsec_extra_len(true)) #define MACSEC_NEEDED_TAILROOM MACSEC_STD_ICV_LEN static void macsec_fill_iv_xpn(unsigned char *iv, ssci_t ssci, u64 pn, salt_t salt) { struct gcm_iv_xpn *gcm_iv = (struct gcm_iv_xpn *)iv; gcm_iv->ssci = ssci ^ salt.ssci; gcm_iv->pn = cpu_to_be64(pn) ^ salt.pn; } static void macsec_fill_iv(unsigned char *iv, sci_t sci, u32 pn) { struct gcm_iv *gcm_iv = (struct gcm_iv *)iv; gcm_iv->sci = sci; gcm_iv->pn = htonl(pn); } static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb) { return (struct macsec_eth_header *)skb_mac_header(skb); } static void __macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { pr_debug("PN wrapped, transitioning to !oper\n"); tx_sa->active = false; if (secy->protect_frames) secy->operational = false; } void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa) { spin_lock_bh(&tx_sa->lock); __macsec_pn_wrapped(secy, tx_sa); spin_unlock_bh(&tx_sa->lock); } EXPORT_SYMBOL_GPL(macsec_pn_wrapped); static pn_t tx_sa_update_pn(struct macsec_tx_sa *tx_sa, struct macsec_secy *secy) { pn_t pn; spin_lock_bh(&tx_sa->lock); pn = tx_sa->next_pn_halves; if (secy->xpn) tx_sa->next_pn++; else tx_sa->next_pn_halves.lower++; if (tx_sa->next_pn == 0) __macsec_pn_wrapped(secy, tx_sa); spin_unlock_bh(&tx_sa->lock); return pn; } static void macsec_encrypt_finish(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = netdev_priv(dev); skb->dev = macsec->real_dev; skb_reset_mac_header(skb); skb->protocol = eth_hdr(skb)->h_proto; } static unsigned int macsec_msdu_len(struct sk_buff *skb) { struct macsec_dev *macsec = macsec_priv(skb->dev); struct macsec_secy *secy = &macsec->secy; bool sci_present = macsec_skb_cb(skb)->has_sci; return skb->len - macsec_hdr_len(sci_present) - secy->icv_len; } static void macsec_count_tx(struct sk_buff *skb, struct macsec_tx_sc *tx_sc, struct macsec_tx_sa *tx_sa) { unsigned int msdu_len = macsec_msdu_len(skb); struct pcpu_tx_sc_stats *txsc_stats = this_cpu_ptr(tx_sc->stats); u64_stats_update_begin(&txsc_stats->syncp); if (tx_sc->encrypt) { txsc_stats->stats.OutOctetsEncrypted += msdu_len; txsc_stats->stats.OutPktsEncrypted++; this_cpu_inc(tx_sa->stats->OutPktsEncrypted); } else { txsc_stats->stats.OutOctetsProtected += msdu_len; txsc_stats->stats.OutPktsProtected++; this_cpu_inc(tx_sa->stats->OutPktsProtected); } u64_stats_update_end(&txsc_stats->syncp); } static void count_tx(struct net_device *dev, int ret, int len) { if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) dev_sw_netstats_tx_add(dev, 1, len); } static void macsec_encrypt_done(void *data, int err) { struct sk_buff *skb = data; struct net_device *dev = skb->dev; struct macsec_dev *macsec = macsec_priv(dev); struct macsec_tx_sa *sa = macsec_skb_cb(skb)->tx_sa; int len, ret; aead_request_free(macsec_skb_cb(skb)->req); rcu_read_lock_bh(); macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa); /* packet is encrypted/protected so tx_bytes must be calculated */ len = macsec_msdu_len(skb) + 2 * ETH_ALEN; macsec_encrypt_finish(skb, dev); ret = dev_queue_xmit(skb); count_tx(dev, ret, len); rcu_read_unlock_bh(); macsec_txsa_put(sa); dev_put(dev); } static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm, unsigned char **iv, struct scatterlist **sg, int num_frags) { size_t size, iv_offset, sg_offset; struct aead_request *req; void *tmp; size = sizeof(struct aead_request) + crypto_aead_reqsize(tfm); iv_offset = size; size += GCM_AES_IV_LEN; size = ALIGN(size, __alignof__(struct scatterlist)); sg_offset = size; size += sizeof(struct scatterlist) * num_frags; tmp = kmalloc(size, GFP_ATOMIC); if (!tmp) return NULL; *iv = (unsigned char *)(tmp + iv_offset); *sg = (struct scatterlist *)(tmp + sg_offset); req = tmp; aead_request_set_tfm(req, tfm); return req; } static struct sk_buff *macsec_encrypt(struct sk_buff *skb, struct net_device *dev) { int ret; struct scatterlist *sg; struct sk_buff *trailer; unsigned char *iv; struct ethhdr *eth; struct macsec_eth_header *hh; size_t unprotected_len; struct aead_request *req; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; struct macsec_dev *macsec = macsec_priv(dev); bool sci_present; pn_t pn; secy = &macsec->secy; tx_sc = &secy->tx_sc; /* 10.5.1 TX SA assignment */ tx_sa = macsec_txsa_get(tx_sc->sa[tx_sc->encoding_sa]); if (!tx_sa) { secy->operational = false; kfree_skb(skb); return ERR_PTR(-EINVAL); } if (unlikely(skb_headroom(skb) < MACSEC_NEEDED_HEADROOM || skb_tailroom(skb) < MACSEC_NEEDED_TAILROOM)) { struct sk_buff *nskb = skb_copy_expand(skb, MACSEC_NEEDED_HEADROOM, MACSEC_NEEDED_TAILROOM, GFP_ATOMIC); if (likely(nskb)) { consume_skb(skb); skb = nskb; } else { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } } else { skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { macsec_txsa_put(tx_sa); return ERR_PTR(-ENOMEM); } } unprotected_len = skb->len; eth = eth_hdr(skb); sci_present = macsec_send_sci(secy); hh = skb_push(skb, macsec_extra_len(sci_present)); memmove(hh, eth, 2 * ETH_ALEN); pn = tx_sa_update_pn(tx_sa, secy); if (pn.full64 == 0) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOLINK); } macsec_fill_sectag(hh, secy, pn.lower, sci_present); macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN); skb_put(skb, secy->icv_len); if (skb->len - ETH_HLEN > macsec_priv(dev)->real_dev->mtu) { struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats); u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsTooLong++; u64_stats_update_end(&secy_stats->syncp); macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-EINVAL); } ret = skb_cow_data(skb, 0, &trailer); if (unlikely(ret < 0)) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(ret); } req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret); if (!req) { macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(-ENOMEM); } if (secy->xpn) macsec_fill_iv_xpn(iv, tx_sa->ssci, pn.full64, tx_sa->key.salt); else macsec_fill_iv(iv, secy->sci, pn.lower); sg_init_table(sg, ret); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { aead_request_free(req); macsec_txsa_put(tx_sa); kfree_skb(skb); return ERR_PTR(ret); } if (tx_sc->encrypt) { int len = skb->len - macsec_hdr_len(sci_present) - secy->icv_len; aead_request_set_crypt(req, sg, sg, len, iv); aead_request_set_ad(req, macsec_hdr_len(sci_present)); } else { aead_request_set_crypt(req, sg, sg, 0, iv); aead_request_set_ad(req, skb->len - secy->icv_len); } macsec_skb_cb(skb)->req = req; macsec_skb_cb(skb)->tx_sa = tx_sa; macsec_skb_cb(skb)->has_sci = sci_present; aead_request_set_callback(req, 0, macsec_encrypt_done, skb); dev_hold(skb->dev); ret = crypto_aead_encrypt(req); if (ret == -EINPROGRESS) { return ERR_PTR(ret); } else if (ret != 0) { dev_put(skb->dev); kfree_skb(skb); aead_request_free(req); macsec_txsa_put(tx_sa); return ERR_PTR(-EINVAL); } dev_put(skb->dev); aead_request_free(req); macsec_txsa_put(tx_sa); return skb; } static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u32 pn) { struct macsec_rx_sa *rx_sa = macsec_skb_cb(skb)->rx_sa; struct pcpu_rx_sc_stats *rxsc_stats = this_cpu_ptr(rx_sa->sc->stats); struct macsec_eth_header *hdr = macsec_ethhdr(skb); u32 lowest_pn = 0; spin_lock(&rx_sa->lock); if (rx_sa->next_pn_halves.lower >= secy->replay_window) lowest_pn = rx_sa->next_pn_halves.lower - secy->replay_window; /* Now perform replay protection check again * (see IEEE 802.1AE-2006 figure 10-5) */ if (secy->replay_protect && pn < lowest_pn && (!secy->xpn || pn_same_half(pn, lowest_pn))) { spin_unlock(&rx_sa->lock); u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(secy->netdev, rx_dropped); return false; } if (secy->validate_frames != MACSEC_VALIDATE_DISABLED) { unsigned int msdu_len = macsec_msdu_len(skb); u64_stats_update_begin(&rxsc_stats->syncp); if (hdr->tci_an & MACSEC_TCI_E) rxsc_stats->stats.InOctetsDecrypted += msdu_len; else rxsc_stats->stats.InOctetsValidated += msdu_len; u64_stats_update_end(&rxsc_stats->syncp); } if (!macsec_skb_cb(skb)->valid) { spin_unlock(&rx_sa->lock); /* 10.6.5 */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); DEV_STATS_INC(secy->netdev, rx_errors); return false; } u64_stats_update_begin(&rxsc_stats->syncp); if (secy->validate_frames == MACSEC_VALIDATE_CHECK) { rxsc_stats->stats.InPktsInvalid++; this_cpu_inc(rx_sa->stats->InPktsInvalid); } else if (pn < lowest_pn) { rxsc_stats->stats.InPktsDelayed++; } else { rxsc_stats->stats.InPktsUnchecked++; } u64_stats_update_end(&rxsc_stats->syncp); } else { u64_stats_update_begin(&rxsc_stats->syncp); if (pn < lowest_pn) { rxsc_stats->stats.InPktsDelayed++; } else { rxsc_stats->stats.InPktsOK++; this_cpu_inc(rx_sa->stats->InPktsOK); } u64_stats_update_end(&rxsc_stats->syncp); // Instead of "pn >=" - to support pn overflow in xpn if (pn + 1 > rx_sa->next_pn_halves.lower) { rx_sa->next_pn_halves.lower = pn + 1; } else if (secy->xpn && !pn_same_half(pn, rx_sa->next_pn_halves.lower)) { rx_sa->next_pn_halves.upper++; rx_sa->next_pn_halves.lower = pn + 1; } spin_unlock(&rx_sa->lock); } return true; } static void macsec_reset_skb(struct sk_buff *skb, struct net_device *dev) { skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); } static void macsec_finalize_skb(struct sk_buff *skb, u8 icv_len, u8 hdr_len) { skb->ip_summed = CHECKSUM_NONE; memmove(skb->data + hdr_len, skb->data, 2 * ETH_ALEN); skb_pull(skb, hdr_len); pskb_trim_unique(skb, skb->len - icv_len); } static void count_rx(struct net_device *dev, int len) { dev_sw_netstats_rx_add(dev, len); } static void macsec_decrypt_done(void *data, int err) { struct sk_buff *skb = data; struct net_device *dev = skb->dev; struct macsec_dev *macsec = macsec_priv(dev); struct macsec_rx_sa *rx_sa = macsec_skb_cb(skb)->rx_sa; struct macsec_rx_sc *rx_sc = rx_sa->sc; int len; u32 pn; aead_request_free(macsec_skb_cb(skb)->req); if (!err) macsec_skb_cb(skb)->valid = true; rcu_read_lock_bh(); pn = ntohl(macsec_ethhdr(skb)->packet_number); if (!macsec_post_decrypt(skb, &macsec->secy, pn)) { rcu_read_unlock_bh(); kfree_skb(skb); goto out; } macsec_finalize_skb(skb, macsec->secy.icv_len, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); len = skb->len; macsec_reset_skb(skb, macsec->secy.netdev); if (gro_cells_receive(&macsec->gro_cells, skb) == NET_RX_SUCCESS) count_rx(dev, len); rcu_read_unlock_bh(); out: macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); dev_put(dev); } static struct sk_buff *macsec_decrypt(struct sk_buff *skb, struct net_device *dev, struct macsec_rx_sa *rx_sa, sci_t sci, struct macsec_secy *secy) { int ret; struct scatterlist *sg; struct sk_buff *trailer; unsigned char *iv; struct aead_request *req; struct macsec_eth_header *hdr; u32 hdr_pn; u16 icv_len = secy->icv_len; macsec_skb_cb(skb)->valid = false; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); ret = skb_cow_data(skb, 0, &trailer); if (unlikely(ret < 0)) { kfree_skb(skb); return ERR_PTR(ret); } req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret); if (!req) { kfree_skb(skb); return ERR_PTR(-ENOMEM); } hdr = (struct macsec_eth_header *)skb->data; hdr_pn = ntohl(hdr->packet_number); if (secy->xpn) { pn_t recovered_pn = rx_sa->next_pn_halves; recovered_pn.lower = hdr_pn; if (hdr_pn < rx_sa->next_pn_halves.lower && !pn_same_half(hdr_pn, rx_sa->next_pn_halves.lower)) recovered_pn.upper++; macsec_fill_iv_xpn(iv, rx_sa->ssci, recovered_pn.full64, rx_sa->key.salt); } else { macsec_fill_iv(iv, sci, hdr_pn); } sg_init_table(sg, ret); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { aead_request_free(req); kfree_skb(skb); return ERR_PTR(ret); } if (hdr->tci_an & MACSEC_TCI_E) { /* confidentiality: ethernet + macsec header * authenticated, encrypted payload */ int len = skb->len - macsec_hdr_len(macsec_skb_cb(skb)->has_sci); aead_request_set_crypt(req, sg, sg, len, iv); aead_request_set_ad(req, macsec_hdr_len(macsec_skb_cb(skb)->has_sci)); skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { aead_request_free(req); return ERR_PTR(-ENOMEM); } } else { /* integrity only: all headers + data authenticated */ aead_request_set_crypt(req, sg, sg, icv_len, iv); aead_request_set_ad(req, skb->len - icv_len); } macsec_skb_cb(skb)->req = req; skb->dev = dev; aead_request_set_callback(req, 0, macsec_decrypt_done, skb); dev_hold(dev); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) { return ERR_PTR(ret); } else if (ret != 0) { /* decryption/authentication failed * 10.6 if validateFrames is disabled, deliver anyway */ if (ret != -EBADMSG) { kfree_skb(skb); skb = ERR_PTR(ret); } } else { macsec_skb_cb(skb)->valid = true; } dev_put(dev); aead_request_free(req); return skb; } static struct macsec_rx_sc *find_rx_sc(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc; for_each_rxsc(secy, rx_sc) { if (rx_sc->sci == sci) return rx_sc; } return NULL; } static struct macsec_rx_sc *find_rx_sc_rtnl(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc; for_each_rxsc_rtnl(secy, rx_sc) { if (rx_sc->sci == sci) return rx_sc; } return NULL; } static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) { /* Deliver to the uncontrolled port by default */ enum rx_handler_result ret = RX_HANDLER_PASS; struct ethhdr *hdr = eth_hdr(skb); struct metadata_dst *md_dst; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; bool is_macsec_md_dst; rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); md_dst = skb_metadata_dst(skb); is_macsec_md_dst = md_dst && md_dst->type == METADATA_MACSEC; list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; struct pcpu_secy_stats *secy_stats = this_cpu_ptr(macsec->stats); struct net_device *ndev = macsec->secy.netdev; /* If h/w offloading is enabled, HW decodes frames and strips * the SecTAG, so we have to deduce which port to deliver to. */ if (macsec_is_offloaded(macsec) && netif_running(ndev)) { const struct macsec_ops *ops; ops = macsec_get_ops(macsec, NULL); if (ops->rx_uses_md_dst && !is_macsec_md_dst) continue; if (is_macsec_md_dst) { struct macsec_rx_sc *rx_sc; /* All drivers that implement MACsec offload * support using skb metadata destinations must * indicate that they do so. */ DEBUG_NET_WARN_ON_ONCE(!ops->rx_uses_md_dst); rx_sc = find_rx_sc(&macsec->secy, md_dst->u.macsec_info.sci); if (!rx_sc) continue; /* device indicated macsec offload occurred */ skb->dev = ndev; skb->pkt_type = PACKET_HOST; eth_skb_pkt_type(skb, ndev); ret = RX_HANDLER_ANOTHER; goto out; } /* This datapath is insecure because it is unable to * enforce isolation of broadcast/multicast traffic and * unicast traffic with promiscuous mode on the macsec * netdev. Since the core stack has no mechanism to * check that the hardware did indeed receive MACsec * traffic, it is possible that the response handling * done by the MACsec port was to a plaintext packet. * This violates the MACsec protocol standard. */ if (ether_addr_equal_64bits(hdr->h_dest, ndev->dev_addr)) { /* exact match, divert skb to this port */ skb->dev = ndev; skb->pkt_type = PACKET_HOST; ret = RX_HANDLER_ANOTHER; goto out; } else if (is_multicast_ether_addr_64bits( hdr->h_dest)) { /* multicast frame, deliver on this port too */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; nskb->dev = ndev; eth_skb_pkt_type(nskb, ndev); __netif_rx(nskb); } else if (ndev->flags & IFF_PROMISC) { skb->dev = ndev; skb->pkt_type = PACKET_HOST; ret = RX_HANDLER_ANOTHER; goto out; } continue; } /* 10.6 If the management control validateFrames is not * Strict, frames without a SecTAG are received, counted, and * delivered to the Controlled Port */ if (macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } /* deliver on this port */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; nskb->dev = ndev; if (__netif_rx(nskb) == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); } } out: rcu_read_unlock(); return ret; } static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct net_device *dev = skb->dev; struct macsec_eth_header *hdr; struct macsec_secy *secy = NULL; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; unsigned int len; sci_t sci = 0; u32 hdr_pn; bool cbit; struct pcpu_rx_sc_stats *rxsc_stats; struct pcpu_secy_stats *secy_stats; bool pulled_sci; int ret; if (skb_headroom(skb) < ETH_HLEN) goto drop_direct; hdr = macsec_ethhdr(skb); if (hdr->eth.h_proto != htons(ETH_P_MACSEC)) return handle_not_macsec(skb); skb = skb_unshare(skb, GFP_ATOMIC); *pskb = skb; if (!skb) return RX_HANDLER_CONSUMED; pulled_sci = pskb_may_pull(skb, macsec_extra_len(true)); if (!pulled_sci) { if (!pskb_may_pull(skb, macsec_extra_len(false))) goto drop_direct; } hdr = macsec_ethhdr(skb); /* Frames with a SecTAG that has the TCI E bit set but the C * bit clear are discarded, as this reserved encoding is used * to identify frames with a SecTAG that are not to be * delivered to the Controlled Port. */ if ((hdr->tci_an & (MACSEC_TCI_C | MACSEC_TCI_E)) == MACSEC_TCI_E) return RX_HANDLER_PASS; /* now, pull the extra length */ if (hdr->tci_an & MACSEC_TCI_SC) { if (!pulled_sci) goto drop_direct; } /* ethernet header is part of crypto processing */ skb_push(skb, ETH_HLEN); macsec_skb_cb(skb)->has_sci = !!(hdr->tci_an & MACSEC_TCI_SC); macsec_skb_cb(skb)->assoc_num = hdr->tci_an & MACSEC_AN_MASK; rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci, rxd); if (!sci) goto drop_nosc; list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci); sc = sc ? macsec_rxsc_get(sc) : NULL; if (sc) { secy = &macsec->secy; rx_sc = sc; break; } } if (!secy) goto nosci; dev = secy->netdev; macsec = macsec_priv(dev); secy_stats = this_cpu_ptr(macsec->stats); rxsc_stats = this_cpu_ptr(rx_sc->stats); if (!macsec_validate_skb(skb, secy->icv_len, secy->xpn)) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } rx_sa = macsec_rxsa_get(rx_sc->sa[macsec_skb_cb(skb)->assoc_num]); if (!rx_sa) { /* 10.6.1 if the SA is not in use */ /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } /* not Strict, the frame (with the SecTAG and ICV * removed) is delivered to the Controlled Port. */ u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsUnusedSA++; u64_stats_update_end(&rxsc_stats->syncp); goto deliver; } /* First, PN check to avoid decrypting obviously wrong packets */ hdr_pn = ntohl(hdr->packet_number); if (secy->replay_protect) { bool late; spin_lock(&rx_sa->lock); late = rx_sa->next_pn_halves.lower >= secy->replay_window && hdr_pn < (rx_sa->next_pn_halves.lower - secy->replay_window); if (secy->xpn) late = late && pn_same_half(rx_sa->next_pn_halves.lower, hdr_pn); spin_unlock(&rx_sa->lock); if (late) { u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } macsec_skb_cb(skb)->rx_sa = rx_sa; /* Disabled && !changed text => skip validation */ if (hdr->tci_an & MACSEC_TCI_C || secy->validate_frames != MACSEC_VALIDATE_DISABLED) skb = macsec_decrypt(skb, dev, rx_sa, sci, secy); if (IS_ERR(skb)) { /* the decrypt callback needs the reference */ if (PTR_ERR(skb) != -EINPROGRESS) { macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); } rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; } if (!macsec_post_decrypt(skb, secy, hdr_pn)) goto drop; deliver: macsec_finalize_skb(skb, secy->icv_len, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); len = skb->len; macsec_reset_skb(skb, secy->netdev); if (rx_sa) macsec_rxsa_put(rx_sa); macsec_rxsc_put(rx_sc); skb_orphan(skb); ret = gro_cells_receive(&macsec->gro_cells, skb); if (ret == NET_RX_SUCCESS) count_rx(dev, len); else DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; drop: macsec_rxsa_put(rx_sa); drop_nosa: macsec_rxsc_put(rx_sc); drop_nosc: rcu_read_unlock(); drop_direct: kfree_skb(skb); *pskb = NULL; return RX_HANDLER_CONSUMED; nosci: /* 10.6.1 if the SC is not found */ cbit = !!(hdr->tci_an & MACSEC_TCI_C); if (!cbit) macsec_finalize_skb(skb, MACSEC_DEFAULT_ICV_LEN, macsec_extra_len(macsec_skb_cb(skb)->has_sci)); list_for_each_entry_rcu(macsec, &rxd->secys, secys) { struct sk_buff *nskb; secy_stats = this_cpu_ptr(macsec->stats); /* If validateFrames is Strict or the C bit in the * SecTAG is set, discard */ if (cbit || macsec->secy.validate_frames == MACSEC_VALIDATE_STRICT) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } /* not strict, the frame (with the SecTAG and ICV * removed) is delivered to the Controlled Port. */ nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) break; macsec_reset_skb(nskb, macsec->secy.netdev); ret = __netif_rx(nskb); if (ret == NET_RX_SUCCESS) { u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } rcu_read_unlock(); *pskb = skb; return RX_HANDLER_PASS; } static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) { struct crypto_aead *tfm; int ret; tfm = crypto_alloc_aead("gcm(aes)", 0, 0); if (IS_ERR(tfm)) return tfm; ret = crypto_aead_setkey(tfm, key, key_len); if (ret < 0) goto fail; ret = crypto_aead_setauthsize(tfm, icv_len); if (ret < 0) goto fail; return tfm; fail: crypto_free_aead(tfm); return ERR_PTR(ret); } static int init_rx_sa(struct macsec_rx_sa *rx_sa, char *sak, int key_len, int icv_len) { rx_sa->stats = alloc_percpu(struct macsec_rx_sa_stats); if (!rx_sa->stats) return -ENOMEM; rx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); if (IS_ERR(rx_sa->key.tfm)) { free_percpu(rx_sa->stats); return PTR_ERR(rx_sa->key.tfm); } rx_sa->ssci = MACSEC_UNDEF_SSCI; rx_sa->active = false; rx_sa->next_pn = 1; refcount_set(&rx_sa->refcnt, 1); spin_lock_init(&rx_sa->lock); return 0; } static void clear_rx_sa(struct macsec_rx_sa *rx_sa) { rx_sa->active = false; macsec_rxsa_put(rx_sa); } static void free_rx_sc(struct macsec_rx_sc *rx_sc) { int i; for (i = 0; i < MACSEC_NUM_AN; i++) { struct macsec_rx_sa *sa = rtnl_dereference(rx_sc->sa[i]); RCU_INIT_POINTER(rx_sc->sa[i], NULL); if (sa) clear_rx_sa(sa); } macsec_rxsc_put(rx_sc); } static struct macsec_rx_sc *del_rx_sc(struct macsec_secy *secy, sci_t sci) { struct macsec_rx_sc *rx_sc, __rcu **rx_scp; for (rx_scp = &secy->rx_sc, rx_sc = rtnl_dereference(*rx_scp); rx_sc; rx_scp = &rx_sc->next, rx_sc = rtnl_dereference(*rx_scp)) { if (rx_sc->sci == sci) { if (rx_sc->active) secy->n_rx_sc--; rcu_assign_pointer(*rx_scp, rx_sc->next); return rx_sc; } } return NULL; } static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci, bool active) { struct macsec_rx_sc *rx_sc; struct macsec_dev *macsec; struct net_device *real_dev = macsec_priv(dev)->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); struct macsec_secy *secy; list_for_each_entry(macsec, &rxd->secys, secys) { if (find_rx_sc_rtnl(&macsec->secy, sci)) return ERR_PTR(-EEXIST); } rx_sc = kzalloc_obj(*rx_sc); if (!rx_sc) return ERR_PTR(-ENOMEM); rx_sc->stats = netdev_alloc_pcpu_stats(struct pcpu_rx_sc_stats); if (!rx_sc->stats) { kfree(rx_sc); return ERR_PTR(-ENOMEM); } rx_sc->sci = sci; rx_sc->active = active; refcount_set(&rx_sc->refcnt, 1); secy = &macsec_priv(dev)->secy; rcu_assign_pointer(rx_sc->next, secy->rx_sc); rcu_assign_pointer(secy->rx_sc, rx_sc); if (rx_sc->active) secy->n_rx_sc++; return rx_sc; } static int init_tx_sa(struct macsec_tx_sa *tx_sa, char *sak, int key_len, int icv_len) { tx_sa->stats = alloc_percpu(struct macsec_tx_sa_stats); if (!tx_sa->stats) return -ENOMEM; tx_sa->key.tfm = macsec_alloc_tfm(sak, key_len, icv_len); if (IS_ERR(tx_sa->key.tfm)) { free_percpu(tx_sa->stats); return PTR_ERR(tx_sa->key.tfm); } tx_sa->ssci = MACSEC_UNDEF_SSCI; tx_sa->active = false; refcount_set(&tx_sa->refcnt, 1); spin_lock_init(&tx_sa->lock); return 0; } static void clear_tx_sa(struct macsec_tx_sa *tx_sa) { tx_sa->active = false; macsec_txsa_put(tx_sa); } static struct genl_family macsec_fam; static struct net_device *get_dev_from_nl(struct net *net, struct nlattr **attrs) { int ifindex = nla_get_u32(attrs[MACSEC_ATTR_IFINDEX]); struct net_device *dev; dev = __dev_get_by_index(net, ifindex); if (!dev) return ERR_PTR(-ENODEV); if (!netif_is_macsec(dev)) return ERR_PTR(-ENODEV); return dev; } static enum macsec_offload nla_get_offload(const struct nlattr *nla) { return (__force enum macsec_offload)nla_get_u8(nla); } static sci_t nla_get_sci(const struct nlattr *nla) { return (__force sci_t)nla_get_u64(nla); } static int nla_put_sci(struct sk_buff *skb, int attrtype, sci_t value, int padattr) { return nla_put_u64_64bit(skb, attrtype, (__force u64)value, padattr); } static ssci_t nla_get_ssci(const struct nlattr *nla) { return (__force ssci_t)nla_get_u32(nla); } static int nla_put_ssci(struct sk_buff *skb, int attrtype, ssci_t value) { return nla_put_u32(skb, attrtype, (__force u64)value); } static struct macsec_tx_sa *get_txsa_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_sa, struct net_device **devp, struct macsec_secy **secyp, struct macsec_tx_sc **scp, u8 *assoc_num) { struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; if (!tb_sa[MACSEC_SA_ATTR_AN]) return ERR_PTR(-EINVAL); *assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); dev = get_dev_from_nl(net, attrs); if (IS_ERR(dev)) return ERR_CAST(dev); secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; tx_sa = rtnl_dereference(tx_sc->sa[*assoc_num]); if (!tx_sa) return ERR_PTR(-ENODEV); *devp = dev; *scp = tx_sc; *secyp = secy; return tx_sa; } static struct macsec_rx_sc *get_rxsc_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_rxsc, struct net_device **devp, struct macsec_secy **secyp) { struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; sci_t sci; dev = get_dev_from_nl(net, attrs); if (IS_ERR(dev)) return ERR_CAST(dev); secy = &macsec_priv(dev)->secy; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return ERR_PTR(-EINVAL); sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); rx_sc = find_rx_sc_rtnl(secy, sci); if (!rx_sc) return ERR_PTR(-ENODEV); *secyp = secy; *devp = dev; return rx_sc; } static struct macsec_rx_sa *get_rxsa_from_nl(struct net *net, struct nlattr **attrs, struct nlattr **tb_rxsc, struct nlattr **tb_sa, struct net_device **devp, struct macsec_secy **secyp, struct macsec_rx_sc **scp, u8 *assoc_num) { struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; if (!tb_sa[MACSEC_SA_ATTR_AN]) return ERR_PTR(-EINVAL); *assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); rx_sc = get_rxsc_from_nl(net, attrs, tb_rxsc, devp, secyp); if (IS_ERR(rx_sc)) return ERR_CAST(rx_sc); rx_sa = rtnl_dereference(rx_sc->sa[*assoc_num]); if (!rx_sa) return ERR_PTR(-ENODEV); *scp = rx_sc; return rx_sa; } static const struct nla_policy macsec_genl_policy[NUM_MACSEC_ATTR] = { [MACSEC_ATTR_IFINDEX] = { .type = NLA_U32 }, [MACSEC_ATTR_RXSC_CONFIG] = { .type = NLA_NESTED }, [MACSEC_ATTR_SA_CONFIG] = { .type = NLA_NESTED }, [MACSEC_ATTR_OFFLOAD] = { .type = NLA_NESTED }, }; static const struct nla_policy macsec_genl_rxsc_policy[NUM_MACSEC_RXSC_ATTR] = { [MACSEC_RXSC_ATTR_SCI] = { .type = NLA_U64 }, [MACSEC_RXSC_ATTR_ACTIVE] = NLA_POLICY_MAX(NLA_U8, 1), }; static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_AN] = NLA_POLICY_MAX(NLA_U8, MACSEC_NUM_AN - 1), [MACSEC_SA_ATTR_ACTIVE] = NLA_POLICY_MAX(NLA_U8, 1), [MACSEC_SA_ATTR_PN] = NLA_POLICY_MIN(NLA_UINT, 1), [MACSEC_SA_ATTR_KEYID] = NLA_POLICY_EXACT_LEN(MACSEC_KEYID_LEN), [MACSEC_SA_ATTR_KEY] = NLA_POLICY_MAX_LEN(MACSEC_MAX_KEY_LEN), [MACSEC_SA_ATTR_SSCI] = { .type = NLA_U32 }, [MACSEC_SA_ATTR_SALT] = NLA_POLICY_EXACT_LEN(MACSEC_SALT_LEN), }; static const struct nla_policy macsec_genl_offload_policy[NUM_MACSEC_OFFLOAD_ATTR] = { [MACSEC_OFFLOAD_ATTR_TYPE] = NLA_POLICY_MAX(NLA_U8, MACSEC_OFFLOAD_MAX), }; /* Offloads an operation to a device driver */ static int macsec_offload(int (* const func)(struct macsec_context *), struct macsec_context *ctx) { int ret; if (unlikely(!func)) return 0; if (ctx->offload == MACSEC_OFFLOAD_PHY) mutex_lock(&ctx->phydev->lock); ret = (*func)(ctx); if (ctx->offload == MACSEC_OFFLOAD_PHY) mutex_unlock(&ctx->phydev->lock); return ret; } static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa) { if (!attrs[MACSEC_ATTR_SA_CONFIG]) return -EINVAL; if (nla_parse_nested_deprecated(tb_sa, MACSEC_SA_ATTR_MAX, attrs[MACSEC_ATTR_SA_CONFIG], macsec_genl_sa_policy, NULL)) return -EINVAL; return 0; } static int parse_rxsc_config(struct nlattr **attrs, struct nlattr **tb_rxsc) { if (!attrs[MACSEC_ATTR_RXSC_CONFIG]) return -EINVAL; if (nla_parse_nested_deprecated(tb_rxsc, MACSEC_RXSC_ATTR_MAX, attrs[MACSEC_ATTR_RXSC_CONFIG], macsec_genl_rxsc_policy, NULL)) return -EINVAL; return 0; } static bool validate_add_rxsa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || !attrs[MACSEC_SA_ATTR_KEY] || !attrs[MACSEC_SA_ATTR_KEYID]) return false; return true; } static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct nlattr **attrs = info->attrs; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; unsigned char assoc_num; int pn_len; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!validate_add_rxsa(tb_sa)) return -EINVAL; rtnl_lock(); rx_sc = get_rxsc_from_nl(genl_info_net(info), attrs, tb_rxsc, &dev, &secy); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (nla_len(tb_sa[MACSEC_SA_ATTR_KEY]) != secy->key_len) { pr_notice("macsec: nl: add_rxsa: bad key length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); rtnl_unlock(); return -EINVAL; } pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (tb_sa[MACSEC_SA_ATTR_PN] && nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } if (secy->xpn) { if (!tb_sa[MACSEC_SA_ATTR_SSCI] || !tb_sa[MACSEC_SA_ATTR_SALT]) { rtnl_unlock(); return -EINVAL; } } rx_sa = rtnl_dereference(rx_sc->sa[assoc_num]); if (rx_sa) { rtnl_unlock(); return -EBUSY; } rx_sa = kmalloc_obj(*rx_sa); if (!rx_sa) { rtnl_unlock(); return -ENOMEM; } err = init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len); if (err < 0) { kfree(rx_sa); rtnl_unlock(); return err; } if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); rx_sa->sc = rx_sc; if (secy->xpn) { rx_sa->ssci = nla_get_ssci(tb_sa[MACSEC_SA_ATTR_SSCI]); nla_memcpy(rx_sa->key.salt.bytes, tb_sa[MACSEC_SA_ATTR_SALT], MACSEC_SALT_LEN); } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); err = macsec_offload(ops->mdo_add_rxsa, &ctx); memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } nla_memcpy(rx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); rcu_assign_pointer(rx_sc->sa[assoc_num], rx_sa); rtnl_unlock(); return 0; cleanup: macsec_rxsa_put(rx_sa); rtnl_unlock(); return err; } static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; sci_t sci = MACSEC_UNDEF_SCI; struct nlattr **attrs = info->attrs; struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct macsec_secy *secy; bool active = true; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) active = nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); rx_sc = create_rx_sc(dev, sci, active); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_add_rxsc, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: del_rx_sc(secy, sci); free_rx_sc(rx_sc); rtnl_unlock(); return ret; } static bool validate_add_txsa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || !attrs[MACSEC_SA_ATTR_PN] || !attrs[MACSEC_SA_ATTR_KEY] || !attrs[MACSEC_SA_ATTR_KEYID]) return false; return true; } static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct nlattr **attrs = info->attrs; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; unsigned char assoc_num; int pn_len; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_operational; int err; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_add_txsa(tb_sa)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; assoc_num = nla_get_u8(tb_sa[MACSEC_SA_ATTR_AN]); if (nla_len(tb_sa[MACSEC_SA_ATTR_KEY]) != secy->key_len) { pr_notice("macsec: nl: add_txsa: bad key length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); rtnl_unlock(); return -EINVAL; } pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_txsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } if (secy->xpn) { if (!tb_sa[MACSEC_SA_ATTR_SSCI] || !tb_sa[MACSEC_SA_ATTR_SALT]) { rtnl_unlock(); return -EINVAL; } } tx_sa = rtnl_dereference(tx_sc->sa[assoc_num]); if (tx_sa) { rtnl_unlock(); return -EBUSY; } tx_sa = kmalloc_obj(*tx_sa); if (!tx_sa) { rtnl_unlock(); return -ENOMEM; } err = init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len); if (err < 0) { kfree(tx_sa); rtnl_unlock(); return err; } spin_lock_bh(&tx_sa->lock); tx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) tx_sa->active = !!nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); was_operational = secy->operational; if (assoc_num == tx_sc->encoding_sa && tx_sa->active) secy->operational = true; if (secy->xpn) { tx_sa->ssci = nla_get_ssci(tb_sa[MACSEC_SA_ATTR_SSCI]); nla_memcpy(tx_sa->key.salt.bytes, tb_sa[MACSEC_SA_ATTR_SALT], MACSEC_SALT_LEN); } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len); err = macsec_offload(ops->mdo_add_txsa, &ctx); memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } nla_memcpy(tx_sa->key.id, tb_sa[MACSEC_SA_ATTR_KEYID], MACSEC_KEYID_LEN); rcu_assign_pointer(tx_sc->sa[assoc_num], tx_sa); rtnl_unlock(); return 0; cleanup: secy->operational = was_operational; macsec_txsa_put(tx_sa); rtnl_unlock(); return err; } static int macsec_del_rxsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; u8 assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; rtnl_lock(); rx_sa = get_rxsa_from_nl(genl_info_net(info), attrs, tb_rxsc, tb_sa, &dev, &secy, &rx_sc, &assoc_num); if (IS_ERR(rx_sa)) { rtnl_unlock(); return PTR_ERR(rx_sa); } if (rx_sa->active) { rtnl_unlock(); return -EBUSY; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_rxsa, &ctx); if (ret) goto cleanup; } RCU_INIT_POINTER(rx_sc->sa[assoc_num], NULL); clear_rx_sa(rx_sa); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static int macsec_del_rxsc(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; sci_t sci; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), info->attrs); if (IS_ERR(dev)) { rtnl_unlock(); return PTR_ERR(dev); } secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); rx_sc = del_rx_sc(secy, sci); if (!rx_sc) { rtnl_unlock(); return -ENODEV; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_rxsc, &ctx); if (ret) goto cleanup; } free_rx_sc(rx_sc); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static int macsec_del_txsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; u8 assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; rtnl_lock(); tx_sa = get_txsa_from_nl(genl_info_net(info), attrs, tb_sa, &dev, &secy, &tx_sc, &assoc_num); if (IS_ERR(tx_sa)) { rtnl_unlock(); return PTR_ERR(tx_sa); } if (tx_sa->active) { rtnl_unlock(); return -EBUSY; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.secy = secy; ret = macsec_offload(ops->mdo_del_txsa, &ctx); if (ret) goto cleanup; } RCU_INIT_POINTER(tx_sc->sa[assoc_num], NULL); clear_tx_sa(tx_sa); rtnl_unlock(); return 0; cleanup: rtnl_unlock(); return ret; } static bool validate_upd_sa(struct nlattr **attrs) { if (!attrs[MACSEC_SA_ATTR_AN] || attrs[MACSEC_SA_ATTR_KEY] || attrs[MACSEC_SA_ATTR_KEYID] || attrs[MACSEC_SA_ATTR_SSCI] || attrs[MACSEC_SA_ATTR_SALT]) return false; return true; } static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; struct macsec_tx_sa *tx_sa; u8 assoc_num; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_operational, was_active; pn_t prev_pn; int ret = 0; prev_pn.full64 = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_upd_sa(tb_sa)) return -EINVAL; rtnl_lock(); tx_sa = get_txsa_from_nl(genl_info_net(info), attrs, tb_sa, &dev, &secy, &tx_sc, &assoc_num); if (IS_ERR(tx_sa)) { rtnl_unlock(); return PTR_ERR(tx_sa); } if (tb_sa[MACSEC_SA_ATTR_PN]) { int pn_len; pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: upd_txsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } spin_lock_bh(&tx_sa->lock); prev_pn = tx_sa->next_pn_halves; tx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); } was_active = tx_sa->active; if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) tx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); was_operational = secy->operational; if (assoc_num == tx_sc->encoding_sa) secy->operational = tx_sa->active; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.tx_sa = tx_sa; ctx.sa.update_pn = !!prev_pn.full64; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_txsa, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&tx_sa->lock); tx_sa->next_pn_halves = prev_pn; spin_unlock_bh(&tx_sa->lock); } tx_sa->active = was_active; secy->operational = was_operational; rtnl_unlock(); return ret; } static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct macsec_rx_sa *rx_sa; u8 assoc_num; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct nlattr *tb_sa[MACSEC_SA_ATTR_MAX + 1]; bool was_active; pn_t prev_pn; int ret = 0; prev_pn.full64 = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (parse_sa_config(attrs, tb_sa)) return -EINVAL; if (!validate_upd_sa(tb_sa)) return -EINVAL; rtnl_lock(); rx_sa = get_rxsa_from_nl(genl_info_net(info), attrs, tb_rxsc, tb_sa, &dev, &secy, &rx_sc, &assoc_num); if (IS_ERR(rx_sa)) { rtnl_unlock(); return PTR_ERR(rx_sa); } if (tb_sa[MACSEC_SA_ATTR_PN]) { int pn_len; pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: upd_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock(); return -EINVAL; } spin_lock_bh(&rx_sa->lock); prev_pn = rx_sa->next_pn_halves; rx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } was_active = rx_sa->active; if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) rx_sa->active = nla_get_u8(tb_sa[MACSEC_SA_ATTR_ACTIVE]); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.sa.assoc_num = assoc_num; ctx.sa.rx_sa = rx_sa; ctx.sa.update_pn = !!prev_pn.full64; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_rxsa, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); rx_sa->next_pn_halves = prev_pn; spin_unlock_bh(&rx_sa->lock); } rx_sa->active = was_active; rtnl_unlock(); return ret; } static int macsec_upd_rxsc(struct sk_buff *skb, struct genl_info *info) { struct nlattr **attrs = info->attrs; struct net_device *dev; struct macsec_secy *secy; struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; unsigned int prev_n_rx_sc; bool was_active; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (parse_rxsc_config(attrs, tb_rxsc)) return -EINVAL; if (!tb_rxsc[MACSEC_RXSC_ATTR_SCI]) return -EINVAL; rtnl_lock(); rx_sc = get_rxsc_from_nl(genl_info_net(info), attrs, tb_rxsc, &dev, &secy); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } was_active = rx_sc->active; prev_n_rx_sc = secy->n_rx_sc; if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) { bool new = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); if (rx_sc->active != new) secy->n_rx_sc += new ? 1 : -1; rx_sc->active = new; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.rx_sc = rx_sc; ctx.secy = secy; ret = macsec_offload(ops->mdo_upd_rxsc, &ctx); if (ret) goto cleanup; } rtnl_unlock(); return 0; cleanup: secy->n_rx_sc = prev_n_rx_sc; rx_sc->active = was_active; rtnl_unlock(); return ret; } static bool macsec_is_configured(struct macsec_dev *macsec) { struct macsec_secy *secy = &macsec->secy; struct macsec_tx_sc *tx_sc = &secy->tx_sc; int i; if (secy->rx_sc) return true; for (i = 0; i < MACSEC_NUM_AN; i++) if (tx_sc->sa[i]) return true; return false; } static bool macsec_needs_tx_tag(struct macsec_dev *macsec, const struct macsec_ops *ops) { return macsec->offload == MACSEC_OFFLOAD_PHY && ops->mdo_insert_tx_tag; } static void macsec_set_head_tail_room(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int needed_headroom, needed_tailroom; const struct macsec_ops *ops; ops = macsec_get_ops(macsec, NULL); if (ops) { needed_headroom = ops->needed_headroom; needed_tailroom = ops->needed_tailroom; } else { needed_headroom = MACSEC_NEEDED_HEADROOM; needed_tailroom = MACSEC_NEEDED_TAILROOM; } dev->needed_headroom = real_dev->needed_headroom + needed_headroom; dev->needed_tailroom = real_dev->needed_tailroom + needed_tailroom; } static void macsec_inherit_tso_max(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); /* if macsec is offloaded, we need to follow the lower * device's capabilities. otherwise, we can ignore them. */ if (macsec_is_offloaded(macsec)) netif_inherit_tso_max(dev, macsec->real_dev); } static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload) { enum macsec_offload prev_offload; const struct macsec_ops *ops; struct macsec_context ctx; struct macsec_dev *macsec; int ret = 0; macsec = macsec_priv(dev); /* Check if the offloading mode is supported by the underlying layers */ if (offload != MACSEC_OFFLOAD_OFF && !macsec_check_offload(offload, macsec)) return -EOPNOTSUPP; /* Check if the net device is busy. */ if (netif_running(dev)) return -EBUSY; /* Check if the device already has rules configured: we do not support * rules migration. */ if (macsec_is_configured(macsec)) return -EBUSY; prev_offload = macsec->offload; ops = __macsec_get_ops(offload == MACSEC_OFFLOAD_OFF ? prev_offload : offload, macsec, &ctx); if (!ops) return -EOPNOTSUPP; macsec->offload = offload; ctx.secy = &macsec->secy; ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx) : macsec_offload(ops->mdo_add_secy, &ctx); if (ret) { macsec->offload = prev_offload; return ret; } macsec_set_head_tail_room(dev); macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops); macsec_inherit_tso_max(dev); netdev_update_features(dev); return ret; } static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb_offload[MACSEC_OFFLOAD_ATTR_MAX + 1]; struct nlattr **attrs = info->attrs; enum macsec_offload offload; struct macsec_dev *macsec; struct net_device *dev; int ret = 0; if (!attrs[MACSEC_ATTR_IFINDEX]) return -EINVAL; if (!attrs[MACSEC_ATTR_OFFLOAD]) return -EINVAL; if (nla_parse_nested_deprecated(tb_offload, MACSEC_OFFLOAD_ATTR_MAX, attrs[MACSEC_ATTR_OFFLOAD], macsec_genl_offload_policy, NULL)) return -EINVAL; rtnl_lock(); dev = get_dev_from_nl(genl_info_net(info), attrs); if (IS_ERR(dev)) { ret = PTR_ERR(dev); goto out; } macsec = macsec_priv(dev); if (!tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]) { ret = -EINVAL; goto out; } offload = nla_get_u8(tb_offload[MACSEC_OFFLOAD_ATTR_TYPE]); if (macsec->offload != offload) ret = macsec_update_offload(dev, offload); out: rtnl_unlock(); return ret; } static void get_tx_sa_stats(struct net_device *dev, int an, struct macsec_tx_sa *tx_sa, struct macsec_tx_sa_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.sa.assoc_num = an; ctx.sa.tx_sa = tx_sa; ctx.stats.tx_sa_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_tx_sa_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct macsec_tx_sa_stats *stats = per_cpu_ptr(tx_sa->stats, cpu); sum->OutPktsProtected += stats->OutPktsProtected; sum->OutPktsEncrypted += stats->OutPktsEncrypted; } } static int copy_tx_sa_stats(struct sk_buff *skb, struct macsec_tx_sa_stats *sum) { if (nla_put_u32(skb, MACSEC_SA_STATS_ATTR_OUT_PKTS_PROTECTED, sum->OutPktsProtected) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_OUT_PKTS_ENCRYPTED, sum->OutPktsEncrypted)) return -EMSGSIZE; return 0; } static void get_rx_sa_stats(struct net_device *dev, struct macsec_rx_sc *rx_sc, int an, struct macsec_rx_sa *rx_sa, struct macsec_rx_sa_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.sa.assoc_num = an; ctx.sa.rx_sa = rx_sa; ctx.stats.rx_sa_stats = sum; ctx.secy = &macsec_priv(dev)->secy; ctx.rx_sc = rx_sc; macsec_offload(ops->mdo_get_rx_sa_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct macsec_rx_sa_stats *stats = per_cpu_ptr(rx_sa->stats, cpu); sum->InPktsOK += stats->InPktsOK; sum->InPktsInvalid += stats->InPktsInvalid; sum->InPktsNotValid += stats->InPktsNotValid; sum->InPktsNotUsingSA += stats->InPktsNotUsingSA; sum->InPktsUnusedSA += stats->InPktsUnusedSA; } } static int copy_rx_sa_stats(struct sk_buff *skb, struct macsec_rx_sa_stats *sum) { if (nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_OK, sum->InPktsOK) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_INVALID, sum->InPktsInvalid) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_VALID, sum->InPktsNotValid) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_NOT_USING_SA, sum->InPktsNotUsingSA) || nla_put_u32(skb, MACSEC_SA_STATS_ATTR_IN_PKTS_UNUSED_SA, sum->InPktsUnusedSA)) return -EMSGSIZE; return 0; } static void get_rx_sc_stats(struct net_device *dev, struct macsec_rx_sc *rx_sc, struct macsec_rx_sc_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.rx_sc_stats = sum; ctx.secy = &macsec_priv(dev)->secy; ctx.rx_sc = rx_sc; macsec_offload(ops->mdo_get_rx_sc_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_rx_sc_stats *stats; struct macsec_rx_sc_stats tmp; unsigned int start; stats = per_cpu_ptr(rx_sc->stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); u64_stats_copy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry(&stats->syncp, start)); sum->InOctetsValidated += tmp.InOctetsValidated; sum->InOctetsDecrypted += tmp.InOctetsDecrypted; sum->InPktsUnchecked += tmp.InPktsUnchecked; sum->InPktsDelayed += tmp.InPktsDelayed; sum->InPktsOK += tmp.InPktsOK; sum->InPktsInvalid += tmp.InPktsInvalid; sum->InPktsLate += tmp.InPktsLate; sum->InPktsNotValid += tmp.InPktsNotValid; sum->InPktsNotUsingSA += tmp.InPktsNotUsingSA; sum->InPktsUnusedSA += tmp.InPktsUnusedSA; } } static int copy_rx_sc_stats(struct sk_buff *skb, struct macsec_rx_sc_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_OCTETS_VALIDATED, sum->InOctetsValidated, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_OCTETS_DECRYPTED, sum->InOctetsDecrypted, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNCHECKED, sum->InPktsUnchecked, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_DELAYED, sum->InPktsDelayed, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_OK, sum->InPktsOK, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_INVALID, sum->InPktsInvalid, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_LATE, sum->InPktsLate, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_VALID, sum->InPktsNotValid, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_NOT_USING_SA, sum->InPktsNotUsingSA, MACSEC_RXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_RXSC_STATS_ATTR_IN_PKTS_UNUSED_SA, sum->InPktsUnusedSA, MACSEC_RXSC_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static void get_tx_sc_stats(struct net_device *dev, struct macsec_tx_sc_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.tx_sc_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_tx_sc_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_tx_sc_stats *stats; struct macsec_tx_sc_stats tmp; unsigned int start; stats = per_cpu_ptr(macsec_priv(dev)->secy.tx_sc.stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); u64_stats_copy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry(&stats->syncp, start)); sum->OutPktsProtected += tmp.OutPktsProtected; sum->OutPktsEncrypted += tmp.OutPktsEncrypted; sum->OutOctetsProtected += tmp.OutOctetsProtected; sum->OutOctetsEncrypted += tmp.OutOctetsEncrypted; } } static int copy_tx_sc_stats(struct sk_buff *skb, struct macsec_tx_sc_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_PKTS_PROTECTED, sum->OutPktsProtected, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_PKTS_ENCRYPTED, sum->OutPktsEncrypted, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_PROTECTED, sum->OutOctetsProtected, MACSEC_TXSC_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_TXSC_STATS_ATTR_OUT_OCTETS_ENCRYPTED, sum->OutOctetsEncrypted, MACSEC_TXSC_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static void get_secy_stats(struct net_device *dev, struct macsec_dev_stats *sum) { struct macsec_dev *macsec = macsec_priv(dev); int cpu; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.stats.dev_stats = sum; ctx.secy = &macsec_priv(dev)->secy; macsec_offload(ops->mdo_get_dev_stats, &ctx); } return; } for_each_possible_cpu(cpu) { const struct pcpu_secy_stats *stats; struct macsec_dev_stats tmp; unsigned int start; stats = per_cpu_ptr(macsec_priv(dev)->stats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); u64_stats_copy(&tmp, &stats->stats, sizeof(tmp)); } while (u64_stats_fetch_retry(&stats->syncp, start)); sum->OutPktsUntagged += tmp.OutPktsUntagged; sum->InPktsUntagged += tmp.InPktsUntagged; sum->OutPktsTooLong += tmp.OutPktsTooLong; sum->InPktsNoTag += tmp.InPktsNoTag; sum->InPktsBadTag += tmp.InPktsBadTag; sum->InPktsUnknownSCI += tmp.InPktsUnknownSCI; sum->InPktsNoSCI += tmp.InPktsNoSCI; sum->InPktsOverrun += tmp.InPktsOverrun; } } static int copy_secy_stats(struct sk_buff *skb, struct macsec_dev_stats *sum) { if (nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_OUT_PKTS_UNTAGGED, sum->OutPktsUntagged, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_UNTAGGED, sum->InPktsUntagged, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_OUT_PKTS_TOO_LONG, sum->OutPktsTooLong, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_TAG, sum->InPktsNoTag, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_BAD_TAG, sum->InPktsBadTag, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_UNKNOWN_SCI, sum->InPktsUnknownSCI, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_NO_SCI, sum->InPktsNoSCI, MACSEC_SECY_STATS_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_STATS_ATTR_IN_PKTS_OVERRUN, sum->InPktsOverrun, MACSEC_SECY_STATS_ATTR_PAD)) return -EMSGSIZE; return 0; } static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) { struct macsec_tx_sc *tx_sc = &secy->tx_sc; struct nlattr *secy_nest = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY); u64 csid; if (!secy_nest) return 1; switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256; break; default: goto cancel; } if (nla_put_sci(skb, MACSEC_SECY_ATTR_SCI, secy->sci, MACSEC_SECY_ATTR_PAD) || nla_put_u64_64bit(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, csid, MACSEC_SECY_ATTR_PAD) || nla_put_u8(skb, MACSEC_SECY_ATTR_ICV_LEN, secy->icv_len) || nla_put_u8(skb, MACSEC_SECY_ATTR_OPER, secy->operational) || nla_put_u8(skb, MACSEC_SECY_ATTR_PROTECT, secy->protect_frames) || nla_put_u8(skb, MACSEC_SECY_ATTR_REPLAY, secy->replay_protect) || nla_put_u8(skb, MACSEC_SECY_ATTR_VALIDATE, secy->validate_frames) || nla_put_u8(skb, MACSEC_SECY_ATTR_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, MACSEC_SECY_ATTR_INC_SCI, tx_sc->send_sci) || nla_put_u8(skb, MACSEC_SECY_ATTR_ES, tx_sc->end_station) || nla_put_u8(skb, MACSEC_SECY_ATTR_SCB, tx_sc->scb) || nla_put_u8(skb, MACSEC_SECY_ATTR_ENCODING_SA, tx_sc->encoding_sa)) goto cancel; if (secy->replay_protect) { if (nla_put_u32(skb, MACSEC_SECY_ATTR_WINDOW, secy->replay_window)) goto cancel; } nla_nest_end(skb, secy_nest); return 0; cancel: nla_nest_cancel(skb, secy_nest); return 1; } static noinline_for_stack int dump_secy(struct macsec_secy *secy, struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct macsec_tx_sc_stats tx_sc_stats = {0, }; struct macsec_tx_sa_stats tx_sa_stats = {0, }; struct macsec_rx_sc_stats rx_sc_stats = {0, }; struct macsec_rx_sa_stats rx_sa_stats = {0, }; struct macsec_dev *macsec = netdev_priv(dev); struct macsec_dev_stats dev_stats = {0, }; struct macsec_tx_sc *tx_sc = &secy->tx_sc; struct nlattr *txsa_list, *rxsc_list; struct macsec_rx_sc *rx_sc; struct nlattr *attr; void *hdr; int i, j; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &macsec_fam, NLM_F_MULTI, MACSEC_CMD_GET_TXSC); if (!hdr) return -EMSGSIZE; genl_dump_check_consistent(cb, hdr); if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; attr = nla_nest_start_noflag(skb, MACSEC_ATTR_OFFLOAD); if (!attr) goto nla_put_failure; if (nla_put_u8(skb, MACSEC_OFFLOAD_ATTR_TYPE, macsec->offload)) goto nla_put_failure; nla_nest_end(skb, attr); if (nla_put_secy(secy, skb)) goto nla_put_failure; attr = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSC_STATS); if (!attr) goto nla_put_failure; get_tx_sc_stats(dev, &tx_sc_stats); if (copy_tx_sc_stats(skb, &tx_sc_stats)) { nla_nest_cancel(skb, attr); goto nla_put_failure; } nla_nest_end(skb, attr); attr = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY_STATS); if (!attr) goto nla_put_failure; get_secy_stats(dev, &dev_stats); if (copy_secy_stats(skb, &dev_stats)) { nla_nest_cancel(skb, attr); goto nla_put_failure; } nla_nest_end(skb, attr); txsa_list = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSA_LIST); if (!txsa_list) goto nla_put_failure; for (i = 0, j = 1; i < MACSEC_NUM_AN; i++) { struct macsec_tx_sa *tx_sa = rtnl_dereference(tx_sc->sa[i]); struct nlattr *txsa_nest; u64 pn; int pn_len; if (!tx_sa) continue; txsa_nest = nla_nest_start_noflag(skb, j++); if (!txsa_nest) { nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } memset(&tx_sa_stats, 0, sizeof(tx_sa_stats)); get_tx_sa_stats(dev, i, tx_sa, &tx_sa_stats); if (copy_tx_sa_stats(skb, &tx_sa_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } nla_nest_end(skb, attr); if (secy->xpn) { pn = tx_sa->next_pn; pn_len = MACSEC_XPN_PN_LEN; } else { pn = tx_sa->next_pn_halves.lower; pn_len = MACSEC_DEFAULT_PN_LEN; } if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put(skb, MACSEC_SA_ATTR_PN, pn_len, &pn) || nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, tx_sa->key.id) || (secy->xpn && nla_put_ssci(skb, MACSEC_SA_ATTR_SSCI, tx_sa->ssci)) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, tx_sa->active)) { nla_nest_cancel(skb, txsa_nest); nla_nest_cancel(skb, txsa_list); goto nla_put_failure; } nla_nest_end(skb, txsa_nest); } nla_nest_end(skb, txsa_list); rxsc_list = nla_nest_start_noflag(skb, MACSEC_ATTR_RXSC_LIST); if (!rxsc_list) goto nla_put_failure; j = 1; for_each_rxsc_rtnl(secy, rx_sc) { int k; struct nlattr *rxsa_list; struct nlattr *rxsc_nest = nla_nest_start_noflag(skb, j++); if (!rxsc_nest) { nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } if (nla_put_u8(skb, MACSEC_RXSC_ATTR_ACTIVE, rx_sc->active) || nla_put_sci(skb, MACSEC_RXSC_ATTR_SCI, rx_sc->sci, MACSEC_RXSC_ATTR_PAD)) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } memset(&rx_sc_stats, 0, sizeof(rx_sc_stats)); get_rx_sc_stats(dev, rx_sc, &rx_sc_stats); if (copy_rx_sc_stats(skb, &rx_sc_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, attr); rxsa_list = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_SA_LIST); if (!rxsa_list) { nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } for (i = 0, k = 1; i < MACSEC_NUM_AN; i++) { struct macsec_rx_sa *rx_sa = rtnl_dereference(rx_sc->sa[i]); struct nlattr *rxsa_nest; u64 pn; int pn_len; if (!rx_sa) continue; rxsa_nest = nla_nest_start_noflag(skb, k++); if (!rxsa_nest) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS); if (!attr) { nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } memset(&rx_sa_stats, 0, sizeof(rx_sa_stats)); get_rx_sa_stats(dev, rx_sc, i, rx_sa, &rx_sa_stats); if (copy_rx_sa_stats(skb, &rx_sa_stats)) { nla_nest_cancel(skb, attr); nla_nest_cancel(skb, rxsa_list); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, attr); if (secy->xpn) { pn = rx_sa->next_pn; pn_len = MACSEC_XPN_PN_LEN; } else { pn = rx_sa->next_pn_halves.lower; pn_len = MACSEC_DEFAULT_PN_LEN; } if (nla_put_u8(skb, MACSEC_SA_ATTR_AN, i) || nla_put(skb, MACSEC_SA_ATTR_PN, pn_len, &pn) || nla_put(skb, MACSEC_SA_ATTR_KEYID, MACSEC_KEYID_LEN, rx_sa->key.id) || (secy->xpn && nla_put_ssci(skb, MACSEC_SA_ATTR_SSCI, rx_sa->ssci)) || nla_put_u8(skb, MACSEC_SA_ATTR_ACTIVE, rx_sa->active)) { nla_nest_cancel(skb, rxsa_nest); nla_nest_cancel(skb, rxsc_nest); nla_nest_cancel(skb, rxsc_list); goto nla_put_failure; } nla_nest_end(skb, rxsa_nest); } nla_nest_end(skb, rxsa_list); nla_nest_end(skb, rxsc_nest); } nla_nest_end(skb, rxsc_list); genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int macsec_generation = 1; /* protected by RTNL */ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct net_device *dev; int dev_idx, d; dev_idx = cb->args[0]; d = 0; rtnl_lock(); cb->seq = macsec_generation; for_each_netdev(net, dev) { struct macsec_secy *secy; if (d < dev_idx) goto next; if (!netif_is_macsec(dev)) goto next; secy = &macsec_priv(dev)->secy; if (dump_secy(secy, dev, skb, cb) < 0) goto done; next: d++; } done: rtnl_unlock(); cb->args[0] = d; return skb->len; } static const struct genl_small_ops macsec_genl_ops[] = { { .cmd = MACSEC_CMD_GET_TXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = macsec_dump_txsc, }, { .cmd = MACSEC_CMD_ADD_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_rxsc, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_TXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_txsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_ADD_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_add_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_DEL_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_del_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_RXSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_rxsa, .flags = GENL_ADMIN_PERM, }, { .cmd = MACSEC_CMD_UPD_OFFLOAD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = macsec_upd_offload, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family macsec_fam __ro_after_init = { .name = MACSEC_GENL_NAME, .hdrsize = 0, .version = MACSEC_GENL_VERSION, .maxattr = MACSEC_ATTR_MAX, .policy = macsec_genl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = macsec_genl_ops, .n_small_ops = ARRAY_SIZE(macsec_genl_ops), .resv_start_op = MACSEC_CMD_UPD_OFFLOAD + 1, }; static struct sk_buff *macsec_insert_tx_tag(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); const struct macsec_ops *ops; struct phy_device *phydev; struct macsec_context ctx; int skb_final_len; int err; ops = macsec_get_ops(macsec, &ctx); skb_final_len = skb->len - ETH_HLEN + ops->needed_headroom + ops->needed_tailroom; if (unlikely(skb_final_len > macsec->real_dev->mtu)) { err = -EINVAL; goto cleanup; } phydev = macsec->real_dev->phydev; err = skb_ensure_writable_head_tail(skb, dev); if (unlikely(err < 0)) goto cleanup; err = ops->mdo_insert_tx_tag(phydev, skb); if (unlikely(err)) goto cleanup; return skb; cleanup: kfree_skb(skb); return ERR_PTR(err); } static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macsec_dev *macsec = netdev_priv(dev); struct macsec_secy *secy = &macsec->secy; struct pcpu_secy_stats *secy_stats; int ret, len; if (macsec_is_offloaded(netdev_priv(dev))) { struct metadata_dst *md_dst = secy->tx_sc.md_dst; skb_dst_drop(skb); dst_hold(&md_dst->dst); skb_dst_set(skb, &md_dst->dst); if (macsec->insert_tx_tag) { skb = macsec_insert_tx_tag(skb, dev); if (IS_ERR(skb)) { DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } } skb->dev = macsec->real_dev; return dev_queue_xmit(skb); } /* 10.5 */ if (!secy->protect_frames) { secy_stats = this_cpu_ptr(macsec->stats); u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.OutPktsUntagged++; u64_stats_update_end(&secy_stats->syncp); skb->dev = macsec->real_dev; len = skb->len; ret = dev_queue_xmit(skb); count_tx(dev, ret, len); return ret; } if (!secy->operational) { kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } len = skb->len; skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa); macsec_encrypt_finish(skb, dev); ret = dev_queue_xmit(skb); count_tx(dev, ret, len); return ret; } #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) #define MACSEC_OFFLOAD_FEATURES \ (MACSEC_FEATURES | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES | \ NETIF_F_LRO | NETIF_F_RXHASH | NETIF_F_CSUM_MASK | NETIF_F_RXCSUM) static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int err; err = gro_cells_init(&macsec->gro_cells, dev); if (err) return err; macsec_inherit_tso_max(dev); dev->hw_features = real_dev->hw_features & MACSEC_OFFLOAD_FEATURES; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->features = real_dev->features & MACSEC_OFFLOAD_FEATURES; dev->features |= NETIF_F_GSO_SOFTWARE; dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; macsec_set_head_tail_room(dev); if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, real_dev); if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); /* Get macsec's reference to real_dev */ netdev_hold(real_dev, &macsec->dev_tracker, GFP_KERNEL); return 0; } static void macsec_dev_uninit(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); gro_cells_destroy(&macsec->gro_cells); } static netdev_features_t macsec_fix_features(struct net_device *dev, netdev_features_t features) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; netdev_features_t mask; mask = macsec_is_offloaded(macsec) ? MACSEC_OFFLOAD_FEATURES : MACSEC_FEATURES; features &= (real_dev->features & mask) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; return features; } static int macsec_dev_open(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; int err; err = dev_uc_add(real_dev, dev->dev_addr); if (err < 0) return err; if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(real_dev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(real_dev, 1); if (err < 0) goto clear_allmulti; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { err = -EOPNOTSUPP; goto clear_allmulti; } ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_dev_open, &ctx); if (err) goto clear_allmulti; } if (netif_carrier_ok(real_dev)) netif_carrier_on(dev); return 0; clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); del_unicast: dev_uc_del(real_dev, dev->dev_addr); netif_carrier_off(dev); return err; } static int macsec_dev_stop(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; netif_carrier_off(dev); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_dev_stop, &ctx); } } dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(real_dev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(real_dev, -1); dev_uc_del(real_dev, dev->dev_addr); return 0; } static void macsec_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = macsec_priv(dev)->real_dev; if (!(dev->flags & IFF_UP)) return; if (change & IFF_ALLMULTI) dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); } static void macsec_dev_set_rx_mode(struct net_device *dev) { struct net_device *real_dev = macsec_priv(dev)->real_dev; dev_mc_sync(real_dev, dev); dev_uc_sync(real_dev, dev); } static int macsec_set_mac_address(struct net_device *dev, void *p) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct sockaddr *addr = p; u8 old_addr[ETH_ALEN]; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (dev->flags & IFF_UP) { err = dev_uc_add(real_dev, addr->sa_data); if (err < 0) return err; } ether_addr_copy(old_addr, dev->dev_addr); eth_hw_addr_set(dev, addr->sa_data); /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (!ops) { err = -EOPNOTSUPP; goto restore_old_addr; } ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_upd_secy, &ctx); if (err) goto restore_old_addr; } if (dev->flags & IFF_UP) dev_uc_del(real_dev, old_addr); return 0; restore_old_addr: if (dev->flags & IFF_UP) dev_uc_del(real_dev, addr->sa_data); eth_hw_addr_set(dev, old_addr); return err; } static int macsec_change_mtu(struct net_device *dev, int new_mtu) { struct macsec_dev *macsec = macsec_priv(dev); unsigned int extra = macsec->secy.icv_len + macsec_extra_len(true); if (macsec->real_dev->mtu - extra < new_mtu) return -ERANGE; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static void macsec_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { if (!dev->tstats) return; dev_fetch_sw_netstats(s, dev->tstats); s->rx_dropped = DEV_STATS_READ(dev, rx_dropped); s->tx_dropped = DEV_STATS_READ(dev, tx_dropped); s->rx_errors = DEV_STATS_READ(dev, rx_errors); } static int macsec_get_iflink(const struct net_device *dev) { return READ_ONCE(macsec_priv(dev)->real_dev->ifindex); } static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, .ndo_open = macsec_dev_open, .ndo_stop = macsec_dev_stop, .ndo_fix_features = macsec_fix_features, .ndo_change_mtu = macsec_change_mtu, .ndo_set_rx_mode = macsec_dev_set_rx_mode, .ndo_change_rx_flags = macsec_dev_change_rx_flags, .ndo_set_mac_address = macsec_set_mac_address, .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, }; static const struct device_type macsec_type = { .name = "macsec", }; static int validate_cipher_suite(const struct nlattr *attr, struct netlink_ext_ack *extack); static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCI] = { .type = NLA_U64 }, [IFLA_MACSEC_PORT] = { .type = NLA_U16 }, [IFLA_MACSEC_ICV_LEN] = NLA_POLICY_RANGE(NLA_U8, MACSEC_MIN_ICV_LEN, MACSEC_STD_ICV_LEN), [IFLA_MACSEC_CIPHER_SUITE] = NLA_POLICY_VALIDATE_FN(NLA_U64, validate_cipher_suite), [IFLA_MACSEC_WINDOW] = { .type = NLA_U32 }, [IFLA_MACSEC_ENCODING_SA] = NLA_POLICY_MAX(NLA_U8, MACSEC_NUM_AN - 1), [IFLA_MACSEC_ENCRYPT] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_MACSEC_PROTECT] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_MACSEC_INC_SCI] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_MACSEC_ES] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_MACSEC_SCB] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_MACSEC_REPLAY_PROTECT] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_MACSEC_VALIDATION] = NLA_POLICY_MAX(NLA_U8, MACSEC_VALIDATE_MAX), [IFLA_MACSEC_OFFLOAD] = NLA_POLICY_MAX(NLA_U8, MACSEC_OFFLOAD_MAX), }; static void macsec_free_netdev(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); dst_release(&macsec->secy.tx_sc.md_dst->dst); free_percpu(macsec->stats); free_percpu(macsec->secy.tx_sc.stats); /* Get rid of the macsec's reference to real_dev */ netdev_put(macsec->real_dev, &macsec->dev_tracker); } static void macsec_setup(struct net_device *dev) { ether_setup(dev); dev->min_mtu = 0; dev->max_mtu = ETH_MAX_MTU; dev->priv_flags |= IFF_NO_QUEUE | IFF_UNICAST_FLT; dev->netdev_ops = &macsec_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macsec_free_netdev; SET_NETDEV_DEVTYPE(dev, &macsec_type); eth_zero_addr(dev->broadcast); } static int macsec_changelink_common(struct net_device *dev, struct nlattr *data[]) { struct macsec_secy *secy; struct macsec_tx_sc *tx_sc; secy = &macsec_priv(dev)->secy; tx_sc = &secy->tx_sc; if (data[IFLA_MACSEC_ENCODING_SA]) { struct macsec_tx_sa *tx_sa; tx_sc->encoding_sa = nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]); tx_sa = rtnl_dereference(tx_sc->sa[tx_sc->encoding_sa]); secy->operational = tx_sa && tx_sa->active; } if (data[IFLA_MACSEC_ENCRYPT]) tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]); if (data[IFLA_MACSEC_PROTECT]) secy->protect_frames = !!nla_get_u8(data[IFLA_MACSEC_PROTECT]); if (data[IFLA_MACSEC_INC_SCI]) tx_sc->send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); if (data[IFLA_MACSEC_ES]) tx_sc->end_station = !!nla_get_u8(data[IFLA_MACSEC_ES]); if (data[IFLA_MACSEC_SCB]) tx_sc->scb = !!nla_get_u8(data[IFLA_MACSEC_SCB]); if (data[IFLA_MACSEC_REPLAY_PROTECT]) secy->replay_protect = !!nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT]); if (data[IFLA_MACSEC_VALIDATION]) secy->validate_frames = nla_get_u8(data[IFLA_MACSEC_VALIDATION]); if (data[IFLA_MACSEC_CIPHER_SUITE]) { switch (nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE])) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_DEFAULT_CIPHER_ID: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; secy->xpn = false; break; case MACSEC_CIPHER_ID_GCM_AES_256: secy->key_len = MACSEC_GCM_AES_256_SAK_LEN; secy->xpn = false; break; case MACSEC_CIPHER_ID_GCM_AES_XPN_128: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; secy->xpn = true; break; case MACSEC_CIPHER_ID_GCM_AES_XPN_256: secy->key_len = MACSEC_GCM_AES_256_SAK_LEN; secy->xpn = true; break; default: return -EINVAL; } } if (data[IFLA_MACSEC_WINDOW]) { secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]); /* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window * for XPN cipher suites */ if (secy->xpn && secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW) return -EINVAL; } return 0; } static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); bool macsec_offload_state_change = false; enum macsec_offload offload; struct macsec_tx_sc tx_sc; struct macsec_secy secy; int ret; if (!data) return 0; if (data[IFLA_MACSEC_CIPHER_SUITE] || data[IFLA_MACSEC_ICV_LEN] || data[IFLA_MACSEC_SCI] || data[IFLA_MACSEC_PORT]) return -EINVAL; /* Keep a copy of unmodified secy and tx_sc, in case the offload * propagation fails, to revert macsec_changelink_common. */ memcpy(&secy, &macsec->secy, sizeof(secy)); memcpy(&tx_sc, &macsec->secy.tx_sc, sizeof(tx_sc)); ret = macsec_changelink_common(dev, data); if (ret) goto cleanup; if (data[IFLA_MACSEC_OFFLOAD]) { offload = nla_get_u8(data[IFLA_MACSEC_OFFLOAD]); if (macsec->offload != offload) { macsec_offload_state_change = true; ret = macsec_update_offload(dev, offload); if (ret) goto cleanup; } } /* If h/w offloading is available, propagate to the device */ if (!macsec_offload_state_change && macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (!ops) { ret = -EOPNOTSUPP; goto cleanup; } ctx.secy = &macsec->secy; ret = macsec_offload(ops->mdo_upd_secy, &ctx); if (ret) goto cleanup; } return 0; cleanup: memcpy(&macsec->secy.tx_sc, &tx_sc, sizeof(tx_sc)); memcpy(&macsec->secy, &secy, sizeof(secy)); return ret; } static void macsec_del_dev(struct macsec_dev *macsec) { int i; while (macsec->secy.rx_sc) { struct macsec_rx_sc *rx_sc = rtnl_dereference(macsec->secy.rx_sc); rcu_assign_pointer(macsec->secy.rx_sc, rx_sc->next); free_rx_sc(rx_sc); } for (i = 0; i < MACSEC_NUM_AN; i++) { struct macsec_tx_sa *sa = rtnl_dereference(macsec->secy.tx_sc.sa[i]); if (sa) { RCU_INIT_POINTER(macsec->secy.tx_sc.sa[i], NULL); clear_tx_sa(sa); } } } static void macsec_common_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(netdev_priv(dev), &ctx); if (ops) { ctx.secy = &macsec->secy; macsec_offload(ops->mdo_del_secy, &ctx); } } unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); macsec_del_dev(macsec); netdev_upper_dev_unlink(real_dev, dev); macsec_generation++; } static void macsec_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); macsec_common_dellink(dev, head); if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); kfree(rxd); } } static int register_macsec_dev(struct net_device *real_dev, struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); if (!rxd) { int err; rxd = kmalloc_obj(*rxd); if (!rxd) return -ENOMEM; INIT_LIST_HEAD(&rxd->secys); err = netdev_rx_handler_register(real_dev, macsec_handle_frame, rxd); if (err < 0) { kfree(rxd); return err; } } list_add_tail_rcu(&macsec->secys, &rxd->secys); return 0; } static bool sci_exists(struct net_device *dev, sci_t sci) { struct macsec_rxh_data *rxd = macsec_data_rtnl(dev); struct macsec_dev *macsec; list_for_each_entry(macsec, &rxd->secys, secys) { if (macsec->secy.sci == sci) return true; } return false; } static sci_t dev_to_sci(struct net_device *dev, __be16 port) { return make_sci(dev->dev_addr, port); } static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) { struct macsec_dev *macsec = macsec_priv(dev); struct macsec_secy *secy = &macsec->secy; macsec->stats = netdev_alloc_pcpu_stats(struct pcpu_secy_stats); if (!macsec->stats) return -ENOMEM; secy->tx_sc.stats = netdev_alloc_pcpu_stats(struct pcpu_tx_sc_stats); if (!secy->tx_sc.stats) return -ENOMEM; secy->tx_sc.md_dst = metadata_dst_alloc(0, METADATA_MACSEC, GFP_KERNEL); if (!secy->tx_sc.md_dst) /* macsec and secy percpu stats will be freed when unregistering * net_device in macsec_free_netdev() */ return -ENOMEM; if (sci == MACSEC_UNDEF_SCI) sci = dev_to_sci(dev, MACSEC_PORT_ES); secy->netdev = dev; secy->operational = true; secy->key_len = DEFAULT_SAK_LEN; secy->icv_len = icv_len; secy->validate_frames = MACSEC_VALIDATE_DEFAULT; secy->protect_frames = true; secy->replay_protect = false; secy->xpn = DEFAULT_XPN; secy->sci = sci; secy->tx_sc.md_dst->u.macsec_info.sci = sci; secy->tx_sc.active = true; secy->tx_sc.encoding_sa = DEFAULT_ENCODING_SA; secy->tx_sc.encrypt = DEFAULT_ENCRYPT; secy->tx_sc.send_sci = DEFAULT_SEND_SCI; secy->tx_sc.end_station = false; secy->tx_sc.scb = false; return 0; } static struct lock_class_key macsec_netdev_addr_lock_key; static int macsec_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct macsec_dev *macsec = macsec_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; rx_handler_func_t *rx_handler; u8 icv_len = MACSEC_DEFAULT_ICV_LEN; struct net_device *real_dev; int err, mtu; sci_t sci; if (!tb[IFLA_LINK]) return -EINVAL; real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; if (real_dev->type != ARPHRD_ETHER) return -EINVAL; dev->priv_flags |= IFF_MACSEC; macsec->real_dev = real_dev; if (data && data[IFLA_MACSEC_OFFLOAD]) macsec->offload = nla_get_offload(data[IFLA_MACSEC_OFFLOAD]); else /* MACsec offloading is off by default */ macsec->offload = MACSEC_OFFLOAD_OFF; /* Check if the offloading mode is supported by the underlying layers */ if (macsec->offload != MACSEC_OFFLOAD_OFF && !macsec_check_offload(macsec->offload, macsec)) return -EOPNOTSUPP; /* send_sci must be set to true when transmit sci explicitly is set */ if ((data && data[IFLA_MACSEC_SCI]) && (data && data[IFLA_MACSEC_INC_SCI])) { u8 send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); if (!send_sci) return -EINVAL; } if (data && data[IFLA_MACSEC_ICV_LEN]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); mtu = real_dev->mtu - icv_len - macsec_extra_len(true); if (mtu < 0) dev->mtu = 0; else dev->mtu = mtu; rx_handler = rtnl_dereference(real_dev->rx_handler); if (rx_handler && rx_handler != macsec_handle_frame) return -EBUSY; err = register_netdevice(dev); if (err < 0) return err; netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macsec_netdev_addr_lock_key); err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; /* need to be already registered so that ->init has run and * the MAC addr is set */ if (data && data[IFLA_MACSEC_SCI]) sci = nla_get_sci(data[IFLA_MACSEC_SCI]); else if (data && data[IFLA_MACSEC_PORT]) sci = dev_to_sci(dev, nla_get_be16(data[IFLA_MACSEC_PORT])); else sci = dev_to_sci(dev, MACSEC_PORT_ES); if (rx_handler && sci_exists(real_dev, sci)) { err = -EBUSY; goto unlink; } err = macsec_add_dev(dev, sci, icv_len); if (err) goto unlink; if (data) { err = macsec_changelink_common(dev, data); if (err) goto del_dev; } /* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) { const struct macsec_ops *ops; struct macsec_context ctx; ops = macsec_get_ops(macsec, &ctx); if (ops) { ctx.secy = &macsec->secy; err = macsec_offload(ops->mdo_add_secy, &ctx); if (err) goto del_dev; macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops); } } err = register_macsec_dev(real_dev, dev); if (err < 0) goto del_dev; netdev_update_features(dev); netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); macsec_generation++; return 0; del_dev: macsec_del_dev(macsec); unlink: netdev_upper_dev_unlink(real_dev, dev); unregister: unregister_netdevice(dev); return err; } static int validate_cipher_suite(const struct nlattr *attr, struct netlink_ext_ack *extack) { switch (nla_get_u64(attr)) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_CIPHER_ID_GCM_AES_256: case MACSEC_CIPHER_ID_GCM_AES_XPN_128: case MACSEC_CIPHER_ID_GCM_AES_XPN_256: case MACSEC_DEFAULT_CIPHER_ID: return 0; default: return -EINVAL; } } static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 icv_len = MACSEC_DEFAULT_ICV_LEN; bool es, scb, sci; if (!data) return 0; if (data[IFLA_MACSEC_ICV_LEN]) { icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); if (icv_len != MACSEC_DEFAULT_ICV_LEN) { char dummy_key[DEFAULT_SAK_LEN] = { 0 }; struct crypto_aead *dummy_tfm; dummy_tfm = macsec_alloc_tfm(dummy_key, DEFAULT_SAK_LEN, icv_len); if (IS_ERR(dummy_tfm)) return PTR_ERR(dummy_tfm); crypto_free_aead(dummy_tfm); } } es = nla_get_u8_default(data[IFLA_MACSEC_ES], false); sci = nla_get_u8_default(data[IFLA_MACSEC_INC_SCI], false); scb = nla_get_u8_default(data[IFLA_MACSEC_SCB], false); if ((sci && (scb || es)) || (scb && es)) return -EINVAL; if ((data[IFLA_MACSEC_REPLAY_PROTECT] && nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT])) && !data[IFLA_MACSEC_WINDOW]) return -EINVAL; return 0; } static struct net *macsec_get_link_net(const struct net_device *dev) { return dev_net(macsec_priv(dev)->real_dev); } struct net_device *macsec_get_real_dev(const struct net_device *dev) { return macsec_priv(dev)->real_dev; } EXPORT_SYMBOL_GPL(macsec_get_real_dev); bool macsec_netdev_is_offloaded(struct net_device *dev) { return macsec_is_offloaded(macsec_priv(dev)); } EXPORT_SYMBOL_GPL(macsec_netdev_is_offloaded); static size_t macsec_get_size(const struct net_device *dev) { return nla_total_size_64bit(8) + /* IFLA_MACSEC_SCI */ nla_total_size(1) + /* IFLA_MACSEC_ICV_LEN */ nla_total_size_64bit(8) + /* IFLA_MACSEC_CIPHER_SUITE */ nla_total_size(4) + /* IFLA_MACSEC_WINDOW */ nla_total_size(1) + /* IFLA_MACSEC_ENCODING_SA */ nla_total_size(1) + /* IFLA_MACSEC_ENCRYPT */ nla_total_size(1) + /* IFLA_MACSEC_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_INC_SCI */ nla_total_size(1) + /* IFLA_MACSEC_ES */ nla_total_size(1) + /* IFLA_MACSEC_SCB */ nla_total_size(1) + /* IFLA_MACSEC_REPLAY_PROTECT */ nla_total_size(1) + /* IFLA_MACSEC_VALIDATION */ nla_total_size(1) + /* IFLA_MACSEC_OFFLOAD */ 0; } static int macsec_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macsec_tx_sc *tx_sc; struct macsec_dev *macsec; struct macsec_secy *secy; u64 csid; macsec = macsec_priv(dev); secy = &macsec->secy; tx_sc = &secy->tx_sc; switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_128 : MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = secy->xpn ? MACSEC_CIPHER_ID_GCM_AES_XPN_256 : MACSEC_CIPHER_ID_GCM_AES_256; break; default: goto nla_put_failure; } if (nla_put_sci(skb, IFLA_MACSEC_SCI, secy->sci, IFLA_MACSEC_PAD) || nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) || nla_put_u64_64bit(skb, IFLA_MACSEC_CIPHER_SUITE, csid, IFLA_MACSEC_PAD) || nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) || nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) || nla_put_u8(skb, IFLA_MACSEC_INC_SCI, tx_sc->send_sci) || nla_put_u8(skb, IFLA_MACSEC_ES, tx_sc->end_station) || nla_put_u8(skb, IFLA_MACSEC_SCB, tx_sc->scb) || nla_put_u8(skb, IFLA_MACSEC_REPLAY_PROTECT, secy->replay_protect) || nla_put_u8(skb, IFLA_MACSEC_VALIDATION, secy->validate_frames) || nla_put_u8(skb, IFLA_MACSEC_OFFLOAD, macsec->offload) || 0) goto nla_put_failure; if (secy->replay_protect) { if (nla_put_u32(skb, IFLA_MACSEC_WINDOW, secy->replay_window)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops macsec_link_ops __read_mostly = { .kind = "macsec", .priv_size = sizeof(struct macsec_dev), .maxtype = IFLA_MACSEC_MAX, .policy = macsec_rtnl_policy, .setup = macsec_setup, .validate = macsec_validate_attr, .newlink = macsec_newlink, .changelink = macsec_changelink, .dellink = macsec_dellink, .get_size = macsec_get_size, .fill_info = macsec_fill_info, .get_link_net = macsec_get_link_net, }; static bool is_macsec_master(struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == macsec_handle_frame; } static int macsec_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *real_dev = netdev_notifier_info_to_dev(ptr); struct macsec_rxh_data *rxd; struct macsec_dev *m, *n; LIST_HEAD(head); if (!is_macsec_master(real_dev)) return NOTIFY_DONE; rxd = macsec_data_rtnl(real_dev); switch (event) { case NETDEV_DOWN: case NETDEV_UP: case NETDEV_CHANGE: list_for_each_entry_safe(m, n, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; netif_stacked_transfer_operstate(real_dev, dev); } break; case NETDEV_UNREGISTER: list_for_each_entry_safe(m, n, &rxd->secys, secys) { macsec_common_dellink(m->secy.netdev, &head); } netdev_rx_handler_unregister(real_dev); kfree(rxd); unregister_netdevice_many(&head); break; case NETDEV_CHANGEMTU: list_for_each_entry(m, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; unsigned int mtu = real_dev->mtu - (m->secy.icv_len + macsec_extra_len(true)); if (dev->mtu > mtu) dev_set_mtu(dev, mtu); } break; case NETDEV_FEAT_CHANGE: list_for_each_entry(m, &rxd->secys, secys) { macsec_inherit_tso_max(m->secy.netdev); netdev_update_features(m->secy.netdev); } break; } return NOTIFY_OK; } static struct notifier_block macsec_notifier = { .notifier_call = macsec_notify, }; static int __init macsec_init(void) { int err; pr_info("MACsec IEEE 802.1AE\n"); err = register_netdevice_notifier(&macsec_notifier); if (err) return err; err = rtnl_link_register(&macsec_link_ops); if (err) goto notifier; err = genl_register_family(&macsec_fam); if (err) goto rtnl; return 0; rtnl: rtnl_link_unregister(&macsec_link_ops); notifier: unregister_netdevice_notifier(&macsec_notifier); return err; } static void __exit macsec_exit(void) { genl_unregister_family(&macsec_fam); rtnl_link_unregister(&macsec_link_ops); unregister_netdevice_notifier(&macsec_notifier); rcu_barrier(); } module_init(macsec_init); module_exit(macsec_exit); MODULE_ALIAS_RTNL_LINK("macsec"); MODULE_ALIAS_GENL_FAMILY("macsec"); MODULE_DESCRIPTION("MACsec IEEE 802.1AE"); MODULE_LICENSE("GPL v2"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Common values and helper functions for the ChaCha and XChaCha stream ciphers. * * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's * security. Here they share the same key size, tfm context, and setkey * function; only their IV size and encrypt/decrypt function differ. * * The ChaCha paper specifies 20, 12, and 8-round variants. In general, it is * recommended to use the 20-round variant ChaCha20. However, the other * variants can be needed in some performance-sensitive scenarios. The generic * ChaCha code currently allows only the 20 and 12-round variants. */ #ifndef _CRYPTO_CHACHA_H #define _CRYPTO_CHACHA_H #include <linux/unaligned.h> #include <linux/string.h> #include <linux/types.h> /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ #define CHACHA_IV_SIZE 16 #define CHACHA_KEY_SIZE 32 #define CHACHA_BLOCK_SIZE 64 #define CHACHAPOLY_IV_SIZE 12 #define CHACHA_KEY_WORDS 8 #define CHACHA_STATE_WORDS 16 #define HCHACHA_OUT_WORDS 8 /* 192-bit nonce, then 64-bit stream position */ #define XCHACHA_IV_SIZE 32 struct chacha_state { u32 x[CHACHA_STATE_WORDS]; }; void chacha_block_generic(struct chacha_state *state, u8 out[at_least CHACHA_BLOCK_SIZE], int nrounds); static inline void chacha20_block(struct chacha_state *state, u8 out[at_least CHACHA_BLOCK_SIZE]) { chacha_block_generic(state, out, 20); } void hchacha_block_generic(const struct chacha_state *state, u32 out[at_least HCHACHA_OUT_WORDS], int nrounds); void hchacha_block(const struct chacha_state *state, u32 out[at_least HCHACHA_OUT_WORDS], int nrounds); enum chacha_constants { /* expand 32-byte k */ CHACHA_CONSTANT_EXPA = 0x61707865U, CHACHA_CONSTANT_ND_3 = 0x3320646eU, CHACHA_CONSTANT_2_BY = 0x79622d32U, CHACHA_CONSTANT_TE_K = 0x6b206574U }; static inline void chacha_init_consts(struct chacha_state *state) { state->x[0] = CHACHA_CONSTANT_EXPA; state->x[1] = CHACHA_CONSTANT_ND_3; state->x[2] = CHACHA_CONSTANT_2_BY; state->x[3] = CHACHA_CONSTANT_TE_K; } static inline void chacha_init(struct chacha_state *state, const u32 key[at_least CHACHA_KEY_WORDS], const u8 iv[at_least CHACHA_IV_SIZE]) { chacha_init_consts(state); state->x[4] = key[0]; state->x[5] = key[1]; state->x[6] = key[2]; state->x[7] = key[3]; state->x[8] = key[4]; state->x[9] = key[5]; state->x[10] = key[6]; state->x[11] = key[7]; state->x[12] = get_unaligned_le32(iv + 0); state->x[13] = get_unaligned_le32(iv + 4); state->x[14] = get_unaligned_le32(iv + 8); state->x[15] = get_unaligned_le32(iv + 12); } void chacha_crypt(struct chacha_state *state, u8 *dst, const u8 *src, unsigned int bytes, int nrounds); static inline void chacha20_crypt(struct chacha_state *state, u8 *dst, const u8 *src, unsigned int bytes) { chacha_crypt(state, dst, src, bytes, 20); } static inline void chacha_zeroize_state(struct chacha_state *state) { memzero_explicit(state, sizeof(*state)); } #endif /* _CRYPTO_CHACHA_H */ |
| 4 32 58 53 3 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_HANDLE_EXIT_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HANDLE_EXIT_ARM64_KVM_H #include <linux/tracepoint.h> #include "sys_regs.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm TRACE_EVENT(kvm_wfx_arm64, TP_PROTO(unsigned long vcpu_pc, bool is_wfe), TP_ARGS(vcpu_pc, is_wfe), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(bool, is_wfe) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->is_wfe = is_wfe; ), TP_printk("guest executed wf%c at: 0x%016lx", __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) ); TRACE_EVENT(kvm_hvc_arm64, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(unsigned long, r0) __field(unsigned long, imm) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->r0 = r0; __entry->imm = imm; ), TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)", __entry->vcpu_pc, __entry->r0, __entry->imm) ); /* * The dreg32 name is a leftover from a distant past. This will really * output a 64bit value... */ TRACE_EVENT(kvm_arm_set_dreg32, TP_PROTO(const char *name, __u64 value), TP_ARGS(name, value), TP_STRUCT__entry( __field(const char *, name) __field(__u64, value) ), TP_fast_assign( __entry->name = name; __entry->value = value; ), TP_printk("%s: 0x%llx", __entry->name, __entry->value) ); TRACE_EVENT(kvm_handle_sys_reg, TP_PROTO(unsigned long hsr), TP_ARGS(hsr), TP_STRUCT__entry( __field(unsigned long, hsr) ), TP_fast_assign( __entry->hsr = hsr; ), TP_printk("HSR 0x%08lx", __entry->hsr) ); TRACE_EVENT(kvm_sys_access, TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg), TP_ARGS(vcpu_pc, params, reg), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(bool, is_write) __field(const char *, name) __field(u8, Op0) __field(u8, Op1) __field(u8, CRn) __field(u8, CRm) __field(u8, Op2) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->is_write = params->is_write; __entry->name = reg->name; __entry->Op0 = reg->Op0; __entry->Op0 = reg->Op0; __entry->Op1 = reg->Op1; __entry->CRn = reg->CRn; __entry->CRm = reg->CRm; __entry->Op2 = reg->Op2; ), TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s", __entry->vcpu_pc, __entry->name ?: "UNKN", __entry->Op0, __entry->Op1, __entry->CRn, __entry->CRm, __entry->Op2, str_write_read(__entry->is_write)) ); TRACE_EVENT(kvm_set_guest_debug, TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), TP_ARGS(vcpu, guest_debug), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(__u32, guest_debug) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->guest_debug = guest_debug; ), TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) ); #endif /* _TRACE_HANDLE_EXIT_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace_handle_exit /* This part must be outside protection */ #include <trace/define_trace.h> |
| 39 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Authors: Thiébaud Weksteen <tweek@google.com> * Peter Enderborg <Peter.Enderborg@sony.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM avc #if !defined(_TRACE_SELINUX_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SELINUX_H #include <linux/tracepoint.h> TRACE_EVENT(selinux_audited, TP_PROTO(struct selinux_audit_data *sad, char *scontext, char *tcontext, const char *tclass ), TP_ARGS(sad, scontext, tcontext, tclass), TP_STRUCT__entry( __field(u32, requested) __field(u32, denied) __field(u32, audited) __field(int, result) __string(scontext, scontext) __string(tcontext, tcontext) __string(tclass, tclass) ), TP_fast_assign( __entry->requested = sad->requested; __entry->denied = sad->denied; __entry->audited = sad->audited; __entry->result = sad->result; __assign_str(tcontext); __assign_str(scontext); __assign_str(tclass); ), TP_printk("requested=0x%x denied=0x%x audited=0x%x result=%d scontext=%s tcontext=%s tclass=%s", __entry->requested, __entry->denied, __entry->audited, __entry->result, __get_str(scontext), __get_str(tcontext), __get_str(tclass) ) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 239 236 236 236 236 236 239 239 2 112 236 208 211 211 239 238 211 211 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> #include <net/busy_poll.h> /* * LOCKING: * There are three level of locking required by epoll : * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) * 3) ep->lock (spinlock) * * The acquire order is the one listed above, from 1 to 3. * We need a spinlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need * a spinlock. During the event transfer loop (from kernel to * user space) we could end up sleeping due a copy_to_user(), so * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). * The epnested_mutex is acquired when inserting an epoll fd onto another * epoll fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two * simultaneous inserts (A into B and B into A) from racing and * constructing a cycle without either insert observing that it is * going to. * It is necessary to acquire multiple "ep->mtx"es at once in the * case when one epoll fd is added to another. In this case, we * always acquire the locks in the order of nesting (i.e. after * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired * before e2->mtx). Since we disallow cycles of epoll file * descriptors, this ensures that the mutexes are well-ordered. In * order to communicate this nesting to lockdep, when walking a tree * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global * mutex "epnested_mutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. * Events that require holding "epnested_mutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee * a better scalability. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) struct epoll_filefd { struct file *file; int fd; } __packed; /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct eppoll_entry *next; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* List header used to link this structure to the eventpoll ready list */ struct list_head rdllink; /* * Works together "struct eventpoll"->ovflist in keeping the * single linked chain of items. */ struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; /* * Protected by file->f_lock, true for to-be-released epitem already * removed from the "struct file" items list; together with * eventpoll->refcount orchestrates "struct eventpoll" disposal */ bool dying; /* List containing poll wait queues */ struct eppoll_entry *pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct hlist_node fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ spinlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; u8 loop_check_depth; /* * usage count, used together with epitem->dying to * orchestrate the disposal of this struct */ refcount_t refcount; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; /* busy poll timeout */ u32 busy_poll_usecs; /* busy poll packet budget */ u16 busy_poll_budget; bool prefer_busy_poll; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* Used for cycles detection */ static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; /* Used to check for epoll file descriptor inclusion loops */ static struct eventpoll *inserting_into; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __ro_after_init; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __ro_after_init; /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epnested_mutex. */ struct epitems_head { struct hlist_head epitems; struct epitems_head *next; }; static struct epitems_head *tfile_check_list = EP_UNACTIVE_PTR; static struct kmem_cache *ephead_cache __ro_after_init; static inline void free_ephead(struct epitems_head *head) { if (head) kmem_cache_free(ephead_cache, head); } static void list_file(struct file *file) { struct epitems_head *head; head = container_of(file->f_ep, struct epitems_head, epitems); if (!head->next) { head->next = tfile_check_list; tfile_check_list = head; } } static void unlist_file(struct epitems_head *head) { struct epitems_head *to_free = head; struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems)); if (p) { struct epitem *epi= container_of(p, struct epitem, fllink); spin_lock(&epi->ffd.file->f_lock); if (!hlist_empty(&head->epitems)) to_free = NULL; head->next = NULL; spin_unlock(&epi->ffd.file->f_lock); } free_ephead(to_free); } #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, }; static void __init epoll_sysctls_init(void) { register_sysctl("fs/epoll", epoll_table); } #else #define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; static inline int is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Setup the structure that is used as key for the RB tree */ static inline void ep_set_ffd(struct epoll_filefd *ffd, struct file *file, int fd) { ffd->file = file; ffd->fd = fd; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_filefd *p1, struct epoll_filefd *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* Tells us if the item is currently linked */ static inline int ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /** * ep_events_available - Checks if ready events might be available. * * @ep: Pointer to the eventpoll context. * * Return: a value different than %zero if ready events are available, * or %zero otherwise. */ static inline int ep_events_available(struct eventpoll *ep) { return !list_empty_careful(&ep->rdllist) || READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL /** * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value * from the epoll instance ep is preferred, but if it is not set fallback to * the system-wide global via busy_loop_timeout. * * @start_time: The start time used to compute the remaining time until timeout. * @ep: Pointer to the eventpoll context. * * Return: true if the timeout has expired, false otherwise. */ static bool busy_loop_ep_timeout(unsigned long start_time, struct eventpoll *ep) { unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } else { return busy_loop_timeout(start_time); } } static bool ep_busy_loop_on(struct eventpoll *ep) { return !!READ_ONCE(ep->busy_poll_usecs) || READ_ONCE(ep->prefer_busy_poll) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static bool ep_busy_loop(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); u16 budget = READ_ONCE(ep->busy_poll_budget); bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (!budget) budget = BUSY_POLL_BUDGET; if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) return true; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ if (prefer_busy_poll) napi_resume_irqs(napi_id); ep->napi_id = 0; return false; } return false; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep = epi->ep; unsigned int napi_id; struct socket *sock; struct sock *sk; if (!ep_busy_loop_on(ep)) return; sock = sock_from_file(epi->ffd.file); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (!napi_id_valid(napi_id) || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct eventpoll *ep = file->private_data; void __user *uarg = (void __user *)arg; struct epoll_params epoll_params; switch (cmd) { case EPIOCSPARAMS: if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) return -EFAULT; /* pad byte must be zero */ if (epoll_params.__pad) return -EINVAL; if (epoll_params.busy_poll_usecs > S32_MAX) return -EINVAL; if (epoll_params.prefer_busy_poll > 1) return -EINVAL; if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && !capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); return 0; case EPIOCGPARAMS: memset(&epoll_params, 0, sizeof(epoll_params)); epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) return -EFAULT; return 0; default: return -ENOIOCTLCMD; } } static void ep_suspend_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_suspend_irqs(napi_id); } static void ep_resume_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_resume_irqs(napi_id); } #else static inline bool ep_busy_loop(struct eventpoll *ep) { return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } static void ep_suspend_napi_irqs(struct eventpoll *ep) { } static void ep_resume_napi_irqs(struct eventpoll *ep) { } #endif /* CONFIG_NET_RX_BUSY_POLL */ /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * If it is cleared by POLLFREE, it should be rcu-safe. * If we read NULL we need a barrier paired with * smp_store_release() in ep_poll_callback(), otherwise * we rely on whead->lock. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct eppoll_entry **p = &epi->pwqlist; struct eppoll_entry *pwq; while ((pwq = *p) != NULL) { *p = pwq->next; ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /* * ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) { /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ lockdep_assert_irqs_enabled(); spin_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); spin_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, struct list_head *txlist) { struct epitem *epi, *nepi; spin_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { /* * We need to check if the item is already in the list. * During the "sproc" callback execution time, items are * queued into ->ovflist but the "txlist" might already * contain them, and the list_splice() below takes care of them. */ if (!ep_is_linked(epi)) { /* * ->ovflist is LIFO, so we have to reverse it in order * to keep in FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } /* * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after * releasing the lock, events will be queued in the normal way inside * ep->rdllist. */ WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); /* * Quickly re-inject items left on "txlist". */ list_splice(txlist, &ep->rdllist); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } spin_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); } /* * Returns true if the event poll can be disposed */ static bool ep_refcount_dec_and_test(struct eventpoll *ep) { if (!refcount_dec_and_test(&ep->refcount)) return false; WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); return true; } static void ep_free(struct eventpoll *ep) { ep_resume_napi_irqs(ep); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); kfree(ep); } /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. * If the dying flag is set, do the removal only if force is true. * This prevents ep_clear_and_put() from dropping all the ep references * while running concurrently with eventpoll_release_file(). * Returns true if the eventpoll can be disposed. */ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; struct epitems_head *to_free; struct hlist_head *head; lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. */ ep_unregister_pollwait(ep, epi); /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); if (epi->dying && !force) { spin_unlock(&file->f_lock); return false; } to_free = NULL; head = file->f_ep; if (head->first == &epi->fllink && !epi->fllink.next) { /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, NULL); if (!is_file_epoll(file)) { struct epitems_head *v; v = container_of(head, struct epitems_head, epitems); if (!smp_load_acquire(&v->next)) to_free = v; } } hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); rb_erase_cached(&epi->rbn, &ep->rbr); spin_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); spin_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); return true; } /* * ep_remove variant for callers owing an additional reference to the ep */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { if (__ep_remove(ep, epi, false)) WARN_ON_ONCE(ep_refcount_dec_and_test(ep)); } static void ep_clear_and_put(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); mutex_lock(&ep->mtx); /* * Walks through the whole tree by unregistering poll callbacks. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } /* * Walks through the whole tree and try to free each "struct epitem". * Note that ep_remove_safe() will not remove the epitem in case of a * racing eventpoll_release_file(); the latter will do the removal. * At this point we are sure no poll callbacks will be lingering around. * Since we still own a reference to the eventpoll struct, the loop can't * dispose it. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); ep_remove_safe(ep, epi); cond_resched(); } mutex_unlock(&ep->mtx); if (ep_refcount_dec_and_test(ep)) ep_free(ep); } static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (!is_file_epoll(file)) return -EINVAL; switch (cmd) { case EPIOCSPARAMS: case EPIOCGPARAMS: ret = ep_eventpoll_bp_ioctl(file, cmd, arg); break; default: ret = -EINVAL; break; } return ret; } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_clear_and_put(ep); return 0; } static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth); static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; LIST_HEAD(txlist); struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; init_poll_funcptr(&pt, NULL); /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ mutex_lock_nested(&ep->mtx, depth); ep_start_scan(ep, &txlist); list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; break; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } /* * The ffd.file pointer may be in the process of being torn down due to * being closed, but we may not have finished eventpoll_release() yet. * * Normally, even with the atomic_long_inc_not_zero, the file may have * been free'd and then gotten re-allocated to something else (since * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). * * But for epoll, users hold the ep->mtx mutex, and as such any file in * the process of being free'd will block in eventpoll_release_file() * and thus the underlying file allocation will not be free'd, and the * file re-use cannot happen. * * For the same reason we can avoid a rcu_read_lock() around the * operation - 'ffd.file' cannot go away even if the refcount has * reached zero (but we must still not call out to ->poll() functions * etc). */ static struct file *epi_fget(const struct epitem *epi) { struct file *file; file = epi->ffd.file; if (!file_ref_get(&file->f_ref)) file = NULL; return file; } /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct file *file = epi_fget(epi); __poll_t res; /* * We could return EPOLLERR | EPOLLHUP or something, but let's * treat this more as "file doesn't exist, poll didn't happen". */ if (!file) return 0; pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); fput(file); return res & epi->event.events; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { return __ep_eventpoll_poll(file, wait, 0); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, .unlocked_ioctl = ep_eventpoll_ioctl, .compat_ioctl = compat_ptr_ioctl, }; /* * This is called from eventpoll_release() to unlink files from the eventpoll * interface. We need to have this facility to cleanup correctly files that are * closed without being removed from the eventpoll interface. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; bool dispose; /* * Use the 'dying' flag to prevent a concurrent ep_clear_and_put() from * touching the epitems list before eventpoll_release_file() can access * the ep->mtx. */ again: spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); epi->dying = true; spin_unlock(&file->f_lock); /* * ep access is safe as we still own a reference to the ep * struct */ ep = epi->ep; mutex_lock(&ep->mtx); dispose = __ep_remove(ep, epi, true); mutex_unlock(&ep->mtx); if (dispose && ep_refcount_dec_and_test(ep)) ep_free(ep); goto again; } spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) { struct eventpoll *ep; ep = kzalloc_obj(*ep); if (unlikely(!ep)) return -ENOMEM; mutex_init(&ep->mtx); spin_lock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = get_current_user(); refcount_set(&ep->refcount, 1); *pep = ep; return 0; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; struct epoll_filefd ffd; ep_set_ffd(&ffd, file, fd); for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { if (epi->next == EP_UNACTIVE_PTR) { epi->next = READ_ONCE(ep->ovflist); WRITE_ONCE(ep->ovflist, epi); ep_pm_stay_awake_rcu(epi); } } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } if (sync) wake_up_sync(&ep->wq); else wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: spin_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * If we race with ep_remove_wait_queue() it can miss * ->whead = NULL and do another remove_wait_queue() after * us, so we can't use __remove_wait_queue(). */ list_del_init(&wait->entry); /* * ->whead != NULL protects us from the race with * ep_clear_and_put() or ep_remove(), ep_remove_wait_queue() * takes whead->lock held by the caller. Once we nullify it, * nothing protects ep/epi or even wait. */ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt); struct epitem *epi = epq->epi; struct eppoll_entry *pwq; if (unlikely(!epi)) // an earlier allocation has failed return; pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL); if (unlikely(!pwq)) { epq->epi = NULL; return; } init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); pwq->next = epi->pwqlist; epi->pwqlist = pwq; } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate * from a single file of interest. For example, we allow 1000 paths of length * 1, to emanate from each file of interest. This essentially represents the * potential wakeup paths, which need to be limited in order to avoid massive * uncontrolled wakeup storms. The common use case should be a single ep which * is connected to n file sources. In this case each file source has 1 path * of length 1. Thus, the numbers below should be more than sufficient. These * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify * and delete can't add additional paths. Protected by the epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count[PATH_ARR_SIZE]; static int path_count_inc(int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(void) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) path_count[i] = 0; } static int reverse_path_check_proc(struct hlist_head *refs, int depth) { int error = 0; struct epitem *epi; if (depth > EP_MAX_NESTS) /* too deep nesting */ return -1; /* CTL_DEL can remove links here, but that can't increase our count */ hlist_for_each_entry_rcu(epi, refs, fllink) { struct hlist_head *refs = &epi->ep->refs; if (hlist_empty(refs)) error = path_count_inc(depth); else error = reverse_path_check_proc(refs, depth + 1); if (error != 0) break; } return error; } /** * reverse_path_check - The tfile_check_list is list of epitem_head, which have * links that are proposed to be newly added. We need to * make sure that those added links don't add too many * paths such that we will spend all our time waking up * eventpoll objects. * * Return: %zero if the proposed links don't create too many paths, * %-1 otherwise. */ static int reverse_path_check(void) { struct epitems_head *p; for (p = tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) { int error; path_count_init(); rcu_read_lock(); error = reverse_path_check_proc(&p->epitems, 0); rcu_read_unlock(); if (error) return error; } return 0; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } static int attach_epitem(struct file *file, struct epitem *epi) { struct epitems_head *to_free = NULL; struct hlist_head *head = NULL; struct eventpoll *ep = NULL; if (is_file_epoll(file)) ep = file->private_data; if (ep) { head = &ep->refs; } else if (!READ_ONCE(file->f_ep)) { allocate: to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL); if (!to_free) return -ENOMEM; head = &to_free->epitems; } spin_lock(&file->f_lock); if (!file->f_ep) { if (unlikely(!head)) { spin_unlock(&file->f_lock); goto allocate; } /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, head); to_free = NULL; } hlist_add_head_rcu(&epi->fllink, file->f_ep); spin_unlock(&file->f_lock); free_ephead(to_free); return 0; } /* * Must be called with "mtx" held. */ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, struct file *tfile, int fd, int full_check) { int error, pwake = 0; __poll_t revents; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; if (is_file_epoll(tfile)) tep = tfile->private_data; lockdep_assert_irqs_enabled(); if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return -ENOSPC; percpu_counter_inc(&ep->user->epoll_watches); if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) { percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } /* Item initialization follow here ... */ INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; epi->next = EP_UNACTIVE_PTR; if (tep) mutex_lock_nested(&tep->mtx, 1); /* Add the current item to the list of active epoll hook for this file */ if (unlikely(attach_epitem(tfile, epi) < 0)) { if (tep) mutex_unlock(&tep->mtx); kmem_cache_free(epi_cache, epi); percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } if (full_check && !tep) list_file(tfile); /* * Add the current item to the RB tree. All RB tree operations are * protected by "mtx", and ep_insert() is called with "mtx" held. */ ep_rbtree_insert(ep, epi); if (tep) mutex_unlock(&tep->mtx); /* * ep_remove_safe() calls in the later error paths can't lead to * ep_free() as the ep file itself still holds an ep reference. */ ep_get(ep); /* now check if we've created too many backpaths */ if (unlikely(full_check && reverse_path_check())) { ep_remove_safe(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { ep_remove_safe(ep, epi); return error; } } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* * We have to check if something went wrong during the poll wait queue * install process. Namely an allocation for a wait queue failed due * high memory pressure. */ if (unlikely(!epq.epi)) { ep_remove_safe(ep, epi); return -ENOMEM; } /* We have to drop the new item inside our item list to keep track of it */ spin_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } spin_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { spin_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } spin_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; LIST_HEAD(txlist); poll_table pt; int res = 0; /* * Always short-circuit for fatal signals to allow threads to make a * timely exit without the chance of finding more events available and * fetching repeatedly. */ if (fatal_signal_pending(current)) return -EINTR; init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); ep_start_scan(ep, &txlist); /* * We can loop without lock because we are passed a task private list. * Items cannot vanish during the loop we are holding ep->mtx. */ list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { struct wakeup_source *ws; __poll_t revents; if (res >= maxevents) break; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws * below). * * This could be rearranged to delay the deactivation of epi->ws * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, we are holding ep->mtx, * so no operations coming from userspace can change the item. */ revents = ep_item_poll(epi, &pt, 1); if (!revents) continue; events = epoll_put_uevent(revents, epi->event.data, events); if (!events) { list_add(&epi->rdllink, &txlist); ep_pm_stay_awake(epi); if (!res) res = -EFAULT; break; } res++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; else if (!(epi->event.events & EPOLLET)) { /* * If this file has been added with Level * Trigger mode, we need to insert back inside * the ready list, so that the next call to * epoll_wait() will check again the events * availability. At this point, no one can insert * into ep->rdllist besides us. The epoll_ctl() * callers are locked out by * ep_send_events() holding "mtx" and the * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { struct timespec64 now; if (ms < 0) return NULL; if (!ms) { to->tv_sec = 0; to->tv_nsec = 0; return to; } to->tv_sec = ms / MSEC_PER_SEC; to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); *to = timespec64_add_safe(now, *to); return to; } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } static int ep_try_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { int res; /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of * more luck. */ res = ep_send_events(ep, events, maxevents); if (res > 0) ep_suspend_napi_irqs(ep); return res; } static int ep_schedule_timeout(ktime_t *to) { if (to) return ktime_after(*to, ktime_get()); else return 1; } /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * timespec. If the timeout is zero, the function will not block, * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * * Return: the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout) { int res, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; *to = timespec64_to_ktime(*timeout); } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. */ timed_out = 1; } /* * This call is racy: We may or may not see events that are being added * to the ready list under the lock (e.g., in IRQ callbacks). For cases * with a non-zero timeout, this thread will check the ready list under * lock and will add to the wait queue. For cases with a zero * timeout, the user by definition should not care and will have to * recheck again. */ eavail = ep_events_available(ep); while (1) { if (eavail) { res = ep_try_send_events(ep, events, maxevents); if (res) return res; } if (timed_out) return 0; eavail = ep_busy_loop(ep); if (eavail) continue; if (signal_pending(current)) return -EINTR; /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; spin_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); spin_unlock_irq(&ep->lock); if (!eavail) timed_out = !ep_schedule_timeout(to) || !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = 1; if (!list_empty_careful(&wait.entry)) { spin_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its * timeout expired before it could reacquire the lock. * Thus, when wait.entry is empty, it needs to harvest * events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); spin_unlock_irq(&ep->lock); } } } /** * ep_loop_check_proc - verify that adding an epoll file @ep inside another * epoll file does not create closed loops, and * determine the depth of the subtree starting at @ep * * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * * Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found * a loop or went too deep. */ static int ep_loop_check_proc(struct eventpoll *ep, int depth) { int result = 0; struct rb_node *rbp; struct epitem *epi; if (ep->gen == loop_check_gen) return ep->loop_check_depth; mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS) result = EP_MAX_NESTS+1; else result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1); if (result > EP_MAX_NESTS) break; } else { /* * If we've reached a file that is not associated with * an ep, then we need to check if the newly added * links are going to add too many wakeup paths. We do * this by adding it to the tfile_check_list, if it's * not already there, and calling reverse_path_check() * during ep_insert(). */ list_file(epi->ffd.file); } } ep->loop_check_depth = result; mutex_unlock(&ep->mtx); return result; } /* ep_get_upwards_depth_proc - determine depth of @ep when traversed upwards */ static int ep_get_upwards_depth_proc(struct eventpoll *ep, int depth) { int result = 0; struct epitem *epi; if (ep->gen == loop_check_gen) return ep->loop_check_depth; hlist_for_each_entry_rcu(epi, &ep->refs, fllink) result = max(result, ep_get_upwards_depth_proc(epi->ep, depth + 1) + 1); ep->gen = loop_check_gen; ep->loop_check_depth = result; return result; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@to) * into another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ep: Pointer to the epoll we are inserting into. * @to: Pointer to the epoll to be inserted. * * Return: %zero if adding the epoll @to inside the epoll @from * does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to) { int depth, upwards_depth; inserting_into = ep; /* * Check how deep down we can get from @to, and whether it is possible * to loop up to @ep. */ depth = ep_loop_check_proc(to, 0); if (depth > EP_MAX_NESTS) return -1; /* Check how far up we can go from @ep. */ rcu_read_lock(); upwards_depth = ep_get_upwards_depth_proc(ep, 0); rcu_read_unlock(); return (depth+1+upwards_depth > EP_MAX_NESTS) ? -1 : 0; } static void clear_tfile_check_list(void) { rcu_read_lock(); while (tfile_check_list != EP_UNACTIVE_PTR) { struct epitems_head *head = tfile_check_list; tfile_check_list = head->next; unlist_file(head); } rcu_read_unlock(); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error; struct eventpoll *ep; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ FD_PREPARE(fdf, O_RDWR | (flags & O_CLOEXEC), anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC))); if (fdf.err) { ep_clear_and_put(ep); return fdf.err; } ep->file = fd_prepare_file(fdf); return fd_publish(fdf); } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif static inline int epoll_mutex_lock(struct mutex *mutex, int depth, bool nonblock) { if (!nonblock) { mutex_lock_nested(mutex, depth); return 0; } if (mutex_trylock(mutex)) return 0; return -EAGAIN; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { int error; int full_check = 0; struct eventpoll *ep; struct epitem *epi; struct eventpoll *tep = NULL; CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; /* Get the "struct file *" for the target file */ CLASS(fd, tf)(fd); if (fd_empty(tf)) return -EBADF; /* The target file descriptor must support poll */ if (!file_can_poll(fd_file(tf))) return -EPERM; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * We have to check that the file structure underneath the file descriptor * the user passed to us _is_ an eventpoll file. And also we do not permit * adding an epoll file descriptor inside itself. */ error = -EINVAL; if (fd_file(f) == fd_file(tf) || !is_file_epoll(fd_file(f))) goto error_tgt_fput; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; if (op == EPOLL_CTL_ADD && (is_file_epoll(fd_file(tf)) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) goto error_tgt_fput; } /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* * When we insert an epoll file descriptor inside another epoll file * descriptor, there is the chance of creating closed loops, which are * better be handled here, than in more critical paths. While we are * checking for loops we also determine the list of files reachable * and hang them on the tfile_check_list, so we can check that we * haven't created too many possible wakeup paths. * * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when * the epoll file descriptor is attaching directly to a wakeup source, * unless the epoll file descriptor is nested. The purpose of taking the * 'epnested_mutex' on add is to prevent complex toplogies such as loops and * deep wakeup paths from forming in parallel through multiple * EPOLL_CTL_ADD operations. */ error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (READ_ONCE(fd_file(f)->f_ep) || ep->gen == loop_check_gen || is_file_epoll(fd_file(tf))) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; full_check = 1; if (is_file_epoll(fd_file(tf))) { tep = fd_file(tf)->private_data; error = -ELOOP; if (ep_loop_check(ep, tep) != 0) goto error_tgt_fput; } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; } } /* * Try to lookup the file inside our RB tree. Since we grabbed "mtx" * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ epi = ep_find(ep, fd_file(tf), fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(ep, epds, fd_file(tf), fd, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) { /* * The eventpoll itself is still alive: the refcount * can't go to zero here. */ ep_remove_safe(ep, epi); error = 0; } else { error = -ENOENT; } break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } mutex_unlock(&ep->mtx); error_tgt_fput: if (full_check) { clear_tfile_check_list(); loop_check_gen++; mutex_unlock(&epnested_mutex); } return error; } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } static int ep_check_params(struct file *file, struct epoll_event __user *evs, int maxevents) { /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(evs, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ if (!is_file_epoll(file)) return -EINVAL; return 0; } int epoll_sendevents(struct file *file, struct epoll_event __user *events, int maxevents) { struct eventpoll *ep; int ret; ret = ep_check_params(file, events, maxevents); if (unlikely(ret)) return ret; ep = file->private_data; /* * Racy call, but that's ok - it should get retried based on * poll readiness anyway. */ if (ep_events_available(ep)) return ep_try_send_events(ep, events, maxevents); return 0; } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to) { struct eventpoll *ep; int ret; /* Get the "struct file *" for the eventpoll file */ CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; ret = ep_check_params(fd_file(f), events, maxevents); if (unlikely(ret)) return ret; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* Time to fish for events ... */ return ep_poll(ep, events, maxevents, to); } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { struct timespec64 to; return do_epoll_wait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ static int do_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to, const sigset_t __user *sigmask, size_t sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, to); restore_saved_sigmask_unless(error == -EINTR); return error; } SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 to; return do_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #ifdef CONFIG_COMPAT static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 to; return do_compat_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_compat_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 235 22 222 235 | 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-only /* * Copyright (C) 2013 Huawei Ltd. * Author: Jiang Liu <liuj97@gmail.com> * * Based on arch/arm/kernel/jump_label.c */ #include <linux/kernel.h> #include <linux/jump_label.h> #include <linux/smp.h> #include <asm/insn.h> #include <asm/text-patching.h> bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { void *addr = (void *)jump_entry_code(entry); u32 insn; if (type == JUMP_LABEL_JMP) { insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry), jump_entry_target(entry), AARCH64_INSN_BRANCH_NOLINK); } else { insn = aarch64_insn_gen_nop(); } aarch64_insn_patch_text_nosync(addr, insn); return true; } void arch_jump_label_transform_apply(void) { kick_all_cpus_sync(); } |
| 1 1 1 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <crypto/sha2.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> #include <linux/bsearch.h> #include <linux/btf.h> #include <linux/hex.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/sort.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> #include <linux/tracepoint.h> #include <linux/overflow.h> #include <linux/cookie.h> #include <linux/verification.h> #include <net/netfilter/nf_bpf_link.h> #include <net/netkit.h> #include <net/tcx.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) #define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); DEFINE_COOKIE(bpf_map_cookie); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, .map_mem_usage = bpf_map_offload_map_mem_usage, }; static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); } static void bpf_map_write_active_dec(struct bpf_map *map) { atomic64_dec(&map->writecnt); } bool bpf_map_write_active(const struct bpf_map *map) { return atomic64_read(&map->writecnt) != 0; } static u32 bpf_map_value_size(const struct bpf_map *map, u64 flags) { if (flags & (BPF_F_CPU | BPF_F_ALL_CPUS)) return map->value_size; else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) return sizeof(u32); else return map->value_size; } static void maybe_wait_bpf_programs(struct bpf_map *map) { /* Wait for any running non-sleepable BPF programs to complete so that * userspace, when we return to it, knows that all non-sleepable * programs that could be running use the new map value. For sleepable * BPF programs, synchronize_rcu_tasks_trace() should be used to wait * for the completions of these programs, but considering the waiting * time can be very long and userspace may think it will hang forever, * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) synchronize_rcu_expedited(); } static void unpin_uptr_kaddr(void *kaddr) { if (kaddr) unpin_user_page(virt_to_page(kaddr)); } static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj) { const struct btf_field *field; void **uptr_addr; int i; for (i = 0, field = rec->fields; i < cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; unpin_uptr_kaddr(*uptr_addr); } } static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj) { if (!btf_record_has_field(rec, BPF_UPTR)) return; __bpf_obj_unpin_uptrs(rec, rec->cnt, obj); } static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj) { const struct btf_field *field; const struct btf_type *t; unsigned long start, end; struct page *page; void **uptr_addr; int i, err; if (!btf_record_has_field(rec, BPF_UPTR)) return 0; for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; start = *(unsigned long *)uptr_addr; if (!start) continue; t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); /* t->size was checked for zero before */ if (check_add_overflow(start, t->size - 1, &end)) { err = -EFAULT; goto unpin_all; } /* The uptr's struct cannot span across two pages */ if ((start & PAGE_MASK) != (end & PAGE_MASK)) { err = -EOPNOTSUPP; goto unpin_all; } err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page); if (err != 1) goto unpin_all; if (PageHighMem(page)) { err = -EOPNOTSUPP; unpin_user_page(page); goto unpin_all; } *uptr_addr = page_address(page) + offset_in_page(start); } return 0; unpin_all: __bpf_obj_unpin_uptrs(rec, i, obj); return err; } static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, void *key, void *value, __u64 flags) { int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { err = bpf_obj_pin_uptrs(map->record, value); if (!err) { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); if (err) bpf_obj_unpin_uptrs(map->record, value); } } bpf_enable_instrumentation(); return err; } static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, __u64 flags) { void *ptr; int err; if (bpf_map_is_offloaded(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_copy(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_extract(map, key, value, false); } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); } else { rcu_read_lock(); if (map->ops->map_lookup_elem_sys_only) ptr = map->ops->map_lookup_elem_sys_only(map, key); else ptr = map->ops->map_lookup_elem(map, key); if (IS_ERR(ptr)) { err = PTR_ERR(ptr); } else if (!ptr) { err = -ENOENT; } else { err = 0; if (flags & BPF_F_LOCK) /* lock 'ptr' and copy everything but lock */ copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); /* mask lock and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); return err; } /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, false); } void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, true); } void bpf_map_area_free(void *area) { kvfree(area); } static u32 bpf_map_flags_retain_permanent(u32 flags) { /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); } void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root * memory cgroup, get_obj_cgroup_from_current() will return NULL. * So we have to check map->objcg for being NULL each time it's * being used. */ if (memcg_bpf_enabled()) map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) { if (map->objcg) obj_cgroup_put(map->objcg); } static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) { if (map->objcg) return get_mem_cgroup_from_objcg(map->objcg); return root_mem_cgroup; } void bpf_map_memcg_enter(const struct bpf_map *map, struct mem_cgroup **old_memcg, struct mem_cgroup **new_memcg) { *new_memcg = bpf_map_get_memcg(map); *old_memcg = set_active_memcg(*new_memcg); } void bpf_map_memcg_exit(struct mem_cgroup *old_memcg, struct mem_cgroup *new_memcg) { set_active_memcg(old_memcg); mem_cgroup_put(new_memcg); } void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kmalloc_nolock(size, flags | __GFP_ACCOUNT, node); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void __percpu *ptr; bpf_map_memcg_enter(map, &old_memcg, &memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); bpf_map_memcg_exit(old_memcg, memcg); return ptr; } #else static void bpf_map_save_memcg(struct bpf_map *map) { } static void bpf_map_release_memcg(struct bpf_map *map) { } #endif static bool can_alloc_pages(void) { return preempt_count() == 0 && !irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT); } static struct page *__bpf_alloc_page(int nid) { if (!can_alloc_pages()) return alloc_pages_nolock(__GFP_ACCOUNT, nid, 0); return alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT | __GFP_NOWARN, 0); } int bpf_map_alloc_pages(const struct bpf_map *map, int nid, unsigned long nr_pages, struct page **pages) { unsigned long i, j; struct page *pg; int ret = 0; for (i = 0; i < nr_pages; i++) { pg = __bpf_alloc_page(nid); if (pg) { pages[i] = pg; continue; } for (j = 0; j < i; j++) free_pages_nolock(pages[j], 0); ret = -ENOMEM; break; } return ret; } static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; if (f1->offset < f2->offset) return -1; else if (f1->offset > f2->offset) return 1; return 0; } struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask) { struct btf_field *field; if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & field_mask)) return NULL; field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); if (!field || !(field->type & field_mask)) return NULL; return field; } void btf_record_free(struct btf_record *rec) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); if (btf_is_kernel(rec->fields[i].kptr.btf)) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: case BPF_TASK_WORK: /* Nothing to release */ break; default: WARN_ON_ONCE(1); continue; } } kfree(rec); } void bpf_map_free_record(struct bpf_map *map) { btf_record_free(map->record); map->record = NULL; } struct btf_record *btf_record_dup(const struct btf_record *rec) { const struct btf_field *fields; struct btf_record *new_rec; int ret, size, i; if (IS_ERR_OR_NULL(rec)) return NULL; size = struct_size(rec, fields, rec->cnt); new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); if (!new_rec) return ERR_PTR(-ENOMEM); /* Do a deep copy of the btf_record */ fields = rec->fields; new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (btf_is_kernel(fields[i].kptr.btf)) btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { ret = -ENXIO; goto free; } break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: case BPF_TASK_WORK: /* Nothing to acquire */ break; default: ret = -EFAULT; WARN_ON_ONCE(1); goto free; } new_rec->cnt++; } return new_rec; free: btf_record_free(new_rec); return ERR_PTR(ret); } bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) { bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); int size; if (!a_has_fields && !b_has_fields) return true; if (a_has_fields != b_has_fields) return false; if (rec_a->cnt != rec_b->cnt) return false; size = struct_size(rec_a, fields, rec_a->cnt); /* btf_parse_fields uses kzalloc to allocate a btf_record, so unused * members are zeroed out. So memcmp is safe to do without worrying * about padding/unused fields. * * While spin_lock, timer, and kptr have no relation to map BTF, * list_head metadata is specific to map BTF, the btf and value_rec * members in particular. btf is the map BTF, while value_rec points to * btf_record in that map BTF. * * So while by default, we don't rely on the map BTF (which the records * were parsed from) matching for both records, which is not backwards * compatible, in case list_head is part of it, we implicitly rely on * that by way of depending on memcmp succeeding for it. */ return !memcmp(rec_a, rec_b, size); } void bpf_obj_free_timer(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) return; bpf_timer_cancel_and_free(obj + rec->timer_off); } void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_WORKQUEUE))) return; bpf_wq_cancel_and_free(obj + rec->wq_off); } void bpf_obj_free_task_work(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TASK_WORK))) return; bpf_task_work_cancel_and_free(obj + rec->task_work_off); } void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; int i; if (IS_ERR_OR_NULL(rec)) return; fields = rec->fields; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *pointee_struct_meta; const struct btf_field *field = &fields[i]; void *field_ptr = obj + field->offset; void *xchgd_field; switch (fields[i].type) { case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: break; case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; case BPF_WORKQUEUE: bpf_wq_cancel_and_free(field_ptr); break; case BPF_TASK_WORK: bpf_task_work_cancel_and_free(field_ptr); break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: case BPF_KPTR_PERCPU: xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); if (!xchgd_field) break; if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : NULL, fields[i].type == BPF_KPTR_PERCPU); } else { field->kptr.dtor(xchgd_field); } break; case BPF_UPTR: /* The caller ensured that no one is using the uptr */ unpin_uptr_kaddr(*(void **)field_ptr); break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_RB_ROOT: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: break; default: WARN_ON_ONCE(1); continue; } } } static void bpf_map_free(struct bpf_map *map) { struct btf_record *rec = map->record; struct btf *btf = map->btf; /* implementation dependent freeing. Disabling migration to simplify * the free of values or special fields allocated from bpf memory * allocator. */ kfree(map->excl_prog_sha); migrate_disable(); map->ops->map_free(map); migrate_enable(); /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. * * Note that the btf_record stashed in map->inner_map_meta->record was * already freed using the map_free callback for map in map case which * eventually calls bpf_map_free_meta, since inner_map_meta is only a * template bpf_map struct used during verification. */ btf_record_free(rec); /* Delay freeing of btf for maps, as map_free callback may need * struct_meta info which will be freed with btf_put(). */ btf_put(btf); } /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); bpf_map_release_memcg(map); bpf_map_owner_free(map); bpf_map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) { if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } } static void bpf_map_free_in_work(struct bpf_map *map) { INIT_WORK(&map->work, bpf_map_free_deferred); /* Avoid spawning kworkers, since they all might contend * for the same mutex like slab_mutex. */ queue_work(system_dfl_wq, &map->work); } static void bpf_map_free_rcu_gp(struct rcu_head *rcu) { bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); } static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_map_free_rcu_gp(rcu); else call_rcu(rcu, bpf_map_free_rcu_gp); } /* decrement map refcnt and schedule it for freeing via workqueue * (underlying map implementation ops->map_free() might sleep) */ void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map); WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); else if (READ_ONCE(map->free_after_rcu_gp)) call_rcu(&map->rcu, bpf_map_free_rcu_gp); else bpf_map_free_in_work(map); } } EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); } static int bpf_map_release(struct inode *inode, struct file *filp) { struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); return 0; } static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { fmode_t mode = fd_file(f)->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. */ if (READ_ONCE(map->frozen)) mode &= ~FMODE_CAN_WRITE; return mode; } #ifdef CONFIG_PROC_FS /* Show the memory usage of a bpf map */ static u64 bpf_map_memory_usage(const struct bpf_map *map) { return map->ops->map_mem_usage(map); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; spin_lock(&map->owner_lock); if (map->owner) { type = map->owner->type; jited = map->owner->jited; } spin_unlock(&map->owner_lock); seq_printf(m, "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" "map_extra:\t%#llx\n" "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, (unsigned long long)map->map_extra, bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { seq_printf(m, "owner_prog_type:\t%u\n", type); seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_READ. */ return -EINVAL; } static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_WRITE. */ return -EINVAL; } /* called for any extra memory-mapped regions (except initial) */ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { .open = bpf_map_mmap_open, .close = bpf_map_mmap_close, }; static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; int err = 0; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; mutex_lock(&map->freeze_mutex); if (vma->vm_flags & VM_WRITE) { if (map->frozen) { err = -EPERM; goto out; } /* map is meant to be read-only, so do not allow mapping as * writable, because it's possible to leak a writable page * reference and allows user-space to still modify it after * freezing, while verifier will assume contents do not change */ if (map->map_flags & BPF_F_RDONLY_PROG) { err = -EACCES; goto out; } bpf_map_write_active_inc(map); } out: mutex_unlock(&map->freeze_mutex); if (err) return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); /* If mapping is read-only, then disallow potentially re-mapping with * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing * means that as far as BPF map's memory-mapped VMAs are concerned, * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, * both should be set, so we can forget about VM_MAYWRITE and always * check just VM_WRITE */ if (!(vma->vm_flags & VM_WRITE)) vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) { if (vma->vm_flags & VM_WRITE) bpf_map_write_active_dec(map); } return err; } static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) { struct bpf_map *map = filp->private_data; if (map->ops->map_poll) return map->ops->map_poll(map, filp, pts); return EPOLLERR; } static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct bpf_map *map = filp->private_data; if (map->ops->map_get_unmapped_area) return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); #ifdef CONFIG_MMU return mm_get_unmapped_area(filp, addr, len, pgoff, flags); #else return addr; #endif } const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) { int ret; ret = security_bpf_map(map, OPEN_FMODE(flags)); if (ret < 0) return ret; return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); } int bpf_get_file_flag(int flags) { if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) return -EINVAL; if (flags & BPF_F_RDONLY) return O_RDONLY; if (flags & BPF_F_WRONLY) return O_WRONLY; return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ #define CHECK_ATTR(CMD) \ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ sizeof(attr->CMD##_LAST_FIELD), 0, \ sizeof(*attr) - \ offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL /* dst and src must have at least "size" number of bytes. * Return strlen on success and < 0 on error. */ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) { const char *end = src + size; const char *orig_src = src; memset(dst, 0, size); /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { if (!isalnum(*src) && *src != '_' && *src != '.') return -EINVAL; *dst++ = *src++; } /* No '\0' found in "size" number of bytes */ if (src == end) return -EINVAL; return src - orig_src; } EXPORT_SYMBOL_GPL(bpf_obj_name_cpy); int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return -ENOTSUPP; } static int map_check_btf(struct bpf_map *map, struct bpf_token *token, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; int ret = 0; /* Some maps allow key to be unspecified. */ if (btf_key_id) { key_type = btf_type_id_size(btf, &btf_key_id, &key_size); if (!key_type || key_size != map->key_size) return -EINVAL; } else { key_type = btf_type_by_id(btf, 0); if (!map->ops->map_check_btf) return -EINVAL; } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) return -EINVAL; map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR | BPF_TASK_WORK, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { ret = -EACCES; goto free_map_tab; } for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { switch (map->record->field_mask & (1 << i)) { case 0: continue; case BPF_SPIN_LOCK: case BPF_RES_SPIN_LOCK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_TIMER: case BPF_WORKQUEUE: case BPF_TASK_WORK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_REFCOUNT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_UPTR: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_LIST_HEAD: case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; default: /* Fail if map_type checks are missing for a field type */ ret = -EOPNOTSUPP; goto free_map_tab; } } } ret = btf_check_and_fixup_fields(btf, map->record); if (ret < 0) goto free_map_tab; if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) goto free_map_tab; } return ret; free_map_tab: bpf_map_free_record(map); return ret; } #define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size /* called via syscall */ static int map_create(union bpf_attr *attr, bpfptr_t uattr) { const struct bpf_map_ops *ops; struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; bool token_flag; int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it * to avoid per-map type checks tripping on unknown flag */ token_flag = attr->map_flags & BPF_F_TOKEN_FD; attr->map_flags &= ~BPF_F_TOKEN_FD; if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) return -EINVAL; } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { return -EINVAL; } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map_type = attr->map_type; if (map_type >= ARRAY_SIZE(bpf_map_types)) return -EINVAL; map_type = array_index_nospec(map_type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[map_type]; if (!ops) return -EINVAL; if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return err; } if (attr->map_ifindex) ops = &bpf_map_offload_ops; if (!ops->map_mem_usage) return -EINVAL; if (token_flag) { token = bpf_token_get_from_fd(attr->map_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant map creation permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || !bpf_token_allow_map_type(token, attr->map_type)) { bpf_token_put(token); token = NULL; } } err = -EPERM; /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) goto put_token; /* check privileged map type permissions */ switch (map_type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: case BPF_MAP_TYPE_CGROUP_ARRAY: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: /* unprivileged */ break; case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_BLOOM_FILTER: case BPF_MAP_TYPE_LPM_TRIE: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: case BPF_MAP_TYPE_STACK_TRACE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_ARENA: case BPF_MAP_TYPE_INSN_ARRAY: if (!bpf_token_capable(token, CAP_BPF)) goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: if (!bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); goto put_token; } map = ops->map_alloc(attr); if (IS_ERR(map)) { err = PTR_ERR(map); goto put_token; } map->ops = ops; map->map_type = map_type; err = bpf_obj_name_cpy(map->name, attr->map_name, sizeof(attr->map_name)); if (err < 0) goto free_map; preempt_disable(); map->cookie = gen_cookie_next(&bpf_map_cookie); preempt_enable(); atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); spin_lock_init(&map->owner_lock); if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with * to figure out the corresponding kernel's * counter part. Thus, attr->btf_fd has * to be valid also. */ attr->btf_vmlinux_value_type_id) { struct btf *btf; btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } if (btf_is_kernel(btf)) { btf_put(btf); err = -EACCES; goto free_map; } map->btf = btf; if (attr->btf_value_type_id) { err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; } map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; map->btf_vmlinux_value_type_id = attr->btf_vmlinux_value_type_id; } if (attr->excl_prog_hash) { bpfptr_t uprog_hash = make_bpfptr(attr->excl_prog_hash, uattr.is_kernel); if (attr->excl_prog_hash_size != SHA256_DIGEST_SIZE) { err = -EINVAL; goto free_map; } map->excl_prog_sha = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL); if (!map->excl_prog_sha) { err = -ENOMEM; goto free_map; } if (copy_from_bpfptr(map->excl_prog_sha, uprog_hash, SHA256_DIGEST_SIZE)) { err = -EFAULT; goto free_map; } } else if (attr->excl_prog_hash_size) { err = -EINVAL; goto free_map; } err = security_bpf_map_create(map, attr, token, uattr.is_kernel); if (err) goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ bpf_map_put_with_uref(map); return err; } return err; free_map_sec: security_bpf_map_free(map); free_map: bpf_map_free(map); put_token: bpf_token_put(token); return err; } void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); void bpf_map_inc_with_uref(struct bpf_map *map) { atomic64_inc(&map->refcnt); atomic64_inc(&map->usercnt); } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc(map); return map; } EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL"); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc_with_uref(map); return map; } /* map_idr_lock should have been held or the map should have been * protected by rcu read lock. */ struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); if (uref) atomic64_inc(&map->usercnt); return map; } struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { lockdep_assert(rcu_read_lock_held()); return __bpf_map_inc_not_zero(map, false); } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); int __weak bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, bool delete) { return -ENOTSUPP; } static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); return NULL; } static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) { if (key_size) return kvmemdup_bpfptr(ukey, key_size); if (!bpfptr_is_null(ukey)) return ERR_PTR(-EINVAL); return NULL; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK | BPF_F_CPU); if (err) return err; key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); value_size = bpf_map_value_size(map, attr->flags); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { if (copy_from_user(value, uvalue, value_size)) err = -EFAULT; else err = bpf_map_copy_value(map, key, value, attr->flags); goto free_value; } err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; err = -EFAULT; if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; free_value: kvfree(value); free_key: kvfree(key); return err; } #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } err = bpf_map_check_op_flags(map, attr->flags, ~0); if (err) goto err_put; key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map, attr->flags); value = kvmemdup_bpfptr(uvalue, value_size); if (IS_ERR(value)) { err = PTR_ERR(value); goto free_key; } err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); if (!err) maybe_wait_bpf_programs(map); kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); struct bpf_map *map; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* These maps require sleepable context */ err = map->ops->map_delete_elem(map, key); goto out; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (!err) maybe_wait_bpf_programs(map); out: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); struct bpf_map *map; void *key, *next_key; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; if (ukey) { key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); } else { key = NULL; } err = -ENOMEM; next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); out: if (err) goto free_next_key; err = -EFAULT; if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; err = 0; free_next_key: kvfree(next_key); free_key: kvfree(key); return err; } int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 cp, max_count; int err = 0; void *key; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size)) break; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); break; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(key); return err; } int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; void *key, *value; int err = 0; err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK | BPF_F_CPU | BPF_F_ALL_CPUS); if (err) return err; value_size = bpf_map_value_size(map, attr->batch.elem_flags); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { kvfree(key); return -ENOMEM; } for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size) || copy_from_user(value, values + cp * value_size, value_size)) break; err = bpf_map_update_value(map, map_file, key, value, attr->batch.elem_flags); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(value); kvfree(key); return err; } int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; u32 value_size, cp, max_count; int err; err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK | BPF_F_CPU); if (err) return err; value_size = bpf_map_value_size(map, attr->batch.elem_flags); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { kvfree(buf_prevkey); return -ENOMEM; } err = -EFAULT; prev_key = NULL; if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) goto free_buf; key = buf; value = key + map->key_size; if (ubatch) prev_key = buf_prevkey; for (cp = 0; cp < max_count;) { rcu_read_lock(); err = map->ops->map_get_next_key(map, prev_key, key); rcu_read_unlock(); if (err) break; err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); if (err == -ENOENT) goto next_key; if (err) goto free_buf; if (copy_to_user(keys + cp * map->key_size, key, map->key_size)) { err = -EFAULT; goto free_buf; } if (copy_to_user(values + cp * value_size, value, value_size)) { err = -EFAULT; goto free_buf; } cp++; next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); cond_resched(); } if (err == -EFAULT) goto free_buf; if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || (cp && copy_to_user(uobatch, prev_key, map->key_size)))) err = -EFAULT; free_buf: kvfree(buf_prevkey); kvfree(buf); return err; } #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (attr->flags && (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK)) { err = -EINVAL; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map, 0); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_STACK_TRACE) { if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); rcu_read_unlock(); bpf_enable_instrumentation(); } } if (err) goto free_value; if (copy_to_user(uvalue, value, value_size) != 0) { err = -EFAULT; goto free_value; } err = 0; free_value: kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_FREEZE_LAST_FIELD map_fd static int map_freeze(const union bpf_attr *attr) { int err = 0; struct bpf_map *map; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) return -EPERM; mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; } WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); return err; } static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { const struct bpf_prog_ops *ops; if (type >= ARRAY_SIZE(bpf_prog_types)) return -EINVAL; type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); ops = bpf_prog_types[type]; if (!ops) return -EINVAL; if (!bpf_prog_is_offloaded(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } enum bpf_audit { BPF_AUDIT_LOAD, BPF_AUDIT_UNLOAD, BPF_AUDIT_MAX, }; static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { [BPF_AUDIT_LOAD] = "LOAD", [BPF_AUDIT_UNLOAD] = "UNLOAD", }; static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) { struct audit_context *ctx = NULL; struct audit_buffer *ab; if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) return; if (audit_enabled == AUDIT_OFF) return; if (!in_hardirq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) return; audit_log_format(ab, "prog-id=%u op=%s", prog->aux->id, bpf_audit_str[op]); audit_log_end(ab); } static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&prog_idr_lock); id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); if (id > 0) prog->aux->id = id; spin_unlock_bh(&prog_idr_lock); idr_preload_end(); /* id is in [1, INT_MAX) */ if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_prog_free_id(struct bpf_prog *prog) { unsigned long flags; /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, * simply waiting for refcnt to drop to be freed. */ if (!prog->aux->id) return; spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); module_put(prog->aux->mod); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); kfree(prog->aux->ctx_arg_info); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); if (deferred) { if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } else { __bpf_prog_put_rcu(&prog->aux->rcu); } } static void bpf_prog_put_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; struct bpf_prog *prog; aux = container_of(work, struct bpf_prog_aux, work); prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); bpf_prog_free_id(prog); __bpf_prog_put_noref(prog, true); } static void __bpf_prog_put(struct bpf_prog *prog) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { if (in_hardirq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); } else { bpf_prog_put_deferred(&aux->work); } } } void bpf_prog_put(struct bpf_prog *prog) { __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; bpf_prog_put(prog); return 0; } struct bpf_prog_kstats { u64 nsecs; u64 cnt; u64 misses; }; void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; unsigned int flags; if (unlikely(!prog->stats)) return; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); u64_stats_update_end_irqrestore(&stats->syncp, flags); } static void bpf_prog_get_stats(const struct bpf_prog *prog, struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; u64 tnsecs, tcnt, tmisses; st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin(&st->syncp); tnsecs = u64_stats_read(&st->nsecs); tcnt = u64_stats_read(&st->cnt); tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; stats->misses = misses; } #ifdef CONFIG_PROC_FS static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" "recursion_misses:\t%llu\n" "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, stats.cnt, stats.misses, prog->aux->verified_insns); } #endif const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { int ret; ret = security_bpf_prog(prog); if (ret < 0) return ret; return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } void bpf_prog_add(struct bpf_prog *prog, int i) { atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); void bpf_prog_sub(struct bpf_prog *prog, int i) { /* Only to be used for undoing previous bpf_prog_add() in some * error path. We still know that another entity in our call * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); void bpf_prog_inc(struct bpf_prog *prog) { atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); /* prog_idr_lock should have been held */ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); return prog; } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ if (!attach_type) return true; if (prog->type != *attach_type) return false; if (bpf_prog_is_offloaded(prog->aux) && !attach_drv) return false; return true; } static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, bool attach_drv) { CLASS(fd, f)(ufd); struct bpf_prog *prog; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_prog_fops) return ERR_PTR(-EINVAL); prog = fd_file(f)->private_data; if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) return ERR_PTR(-EINVAL); bpf_prog_inc(prog); return prog; } struct bpf_prog *bpf_prog_get(u32 ufd) { return __bpf_prog_get(ufd, NULL, false); } struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* Initially all BPF programs could be loaded w/o specifying * expected_attach_type. Later for some of them specifying expected_attach_type * at load time became required so that program could be validated properly. * Programs of types that are allowed to be loaded both w/ and w/o (for * backward compatibility) expected_attach_type, should have the default attach * type assigned to expected_attach_type for the latter case, so that it can be * validated later at attach time. * * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if * prog type requires it but has some attach types that have to be backward * compatible. */ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) { switch (attr->prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't * exist so checking for non-zero is the way to go here. */ if (!attr->expected_attach_type) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; case BPF_PROG_TYPE_SK_REUSEPORT: if (!attr->expected_attach_type) attr->expected_attach_type = BPF_SK_REUSEPORT_SELECT; break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, struct btf *attach_btf, u32 btf_id, struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; if (!attach_btf && !dst_prog) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; default: return -EINVAL; } } if (attach_btf && (!btf_id || dst_prog)) return -EINVAL; if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: switch (expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SKB: switch (expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCKOPT: switch (expected_attach_type) { case BPF_CGROUP_SETSOCKOPT: case BPF_CGROUP_GETSOCKOPT: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_SK_LOOKUP: if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; case BPF_PROG_TYPE_SK_REUSEPORT: switch (expected_attach_type) { case BPF_SK_REUSEPORT_SELECT: case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_NETFILTER: if (expected_attach_type == BPF_NETFILTER) return 0; return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; fallthrough; default: return 0; } } static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_EXT: /* extends any prog */ case BPF_PROG_TYPE_NETFILTER: return true; case BPF_PROG_TYPE_CGROUP_SKB: /* always unpriv */ case BPF_PROG_TYPE_SK_REUSEPORT: /* equivalent to SOCKET_FILTER. need CAP_BPF only */ default: return false; } } static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ case BPF_PROG_TYPE_EXT: /* extends any prog */ return true; default: return false; } } static int bpf_prog_verify_signature(struct bpf_prog *prog, union bpf_attr *attr, bool is_kernel) { bpfptr_t usig = make_bpfptr(attr->signature, is_kernel); struct bpf_dynptr_kern sig_ptr, insns_ptr; struct bpf_key *key = NULL; void *sig; int err = 0; /* * Don't attempt to use kmalloc_large or vmalloc for signatures. * Practical signature for BPF program should be below this limit. */ if (attr->signature_size > KMALLOC_MAX_CACHE_SIZE) return -EINVAL; if (system_keyring_id_check(attr->keyring_id) == 0) key = bpf_lookup_system_key(attr->keyring_id); else key = bpf_lookup_user_key(attr->keyring_id, 0); if (!key) return -EINVAL; sig = kvmemdup_bpfptr(usig, attr->signature_size); if (IS_ERR(sig)) { bpf_key_put(key); return -ENOMEM; } bpf_dynptr_init(&sig_ptr, sig, BPF_DYNPTR_TYPE_LOCAL, 0, attr->signature_size); bpf_dynptr_init(&insns_ptr, prog->insnsi, BPF_DYNPTR_TYPE_LOCAL, 0, prog->len * sizeof(struct bpf_insn)); err = bpf_verify_pkcs7_signature((struct bpf_dynptr *)&insns_ptr, (struct bpf_dynptr *)&sig_ptr, key); bpf_key_put(key); kvfree(sig); return err; } static int bpf_prog_mark_insn_arrays_ready(struct bpf_prog *prog) { int err; int i; for (i = 0; i < prog->aux->used_map_cnt; i++) { if (prog->aux->used_maps[i]->map_type != BPF_MAP_TYPE_INSN_ARRAY) continue; err = bpf_insn_array_ready(prog->aux->used_maps[i]); if (err) return err; } return 0; } /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD keyring_id static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; struct bpf_token *token = NULL; bool bpf_cap; int err; char license[128]; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_TEST_REG_INVARIANTS | BPF_F_TOKEN_FD)) return -EINVAL; bpf_prog_load_fixup_attach_type(attr); if (attr->prog_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->prog_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant prog loading permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || !bpf_token_allow_prog_type(token, attr->prog_type, attr->expected_attach_type)) { bpf_token_put(token); token = NULL; } } bpf_cap = bpf_token_capable(token, CAP_BPF); err = -EPERM; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && !bpf_cap) goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out for these * and other operations. */ if (sysctl_unprivileged_bpf_disabled && !bpf_cap) goto put_token; if (attr->insn_cnt == 0 || attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { err = -E2BIG; goto put_token; } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !bpf_cap) goto put_token; if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is */ if (attr->attach_prog_fd) { dst_prog = bpf_prog_get(attr->attach_prog_fd); if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); if (IS_ERR(attach_btf)) { err = -EINVAL; goto put_token; } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); err = -ENOTSUPP; goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); if (IS_ERR(attach_btf)) { err = PTR_ERR(attach_btf); goto put_token; } if (!attach_btf) { err = -EINVAL; goto put_token; } btf_get(attach_btf); } if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } prog->expected_attach_type = attr->expected_attach_type; prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; /* move token into prog->aux, reuse taken refcnt */ prog->aux->token = token; token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ prog->gpl_compatible = license_is_gpl_compatible(license) ? 1 : 0; if (attr->signature) { err = bpf_prog_verify_signature(prog, attr, uattr.is_kernel); if (err) goto free_prog; } prog->orig_prog = NULL; prog->jited = 0; atomic64_set(&prog->aux->refcnt, 1); if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) goto free_prog; } /* * Bookkeeping for managing the program attachment chain. * * It might be tempting to set attach_tracing_prog flag at the attachment * time, but this will not prevent from loading bunch of tracing prog * first, then attach them one to another. * * The flag attach_tracing_prog is set for the whole program lifecycle, and * doesn't have to be cleared in bpf_tracing_link_release, since tracing * programs cannot change attachment target. */ if (type == BPF_PROG_TYPE_TRACING && dst_prog && dst_prog->type == BPF_PROG_TYPE_TRACING) { prog->aux->attach_tracing_prog = true; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) goto free_prog; err = security_bpf_prog_load(prog, attr, token, uattr.is_kernel); if (err) goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr, uattr_size); if (err < 0) goto free_used_maps; prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; err = bpf_prog_mark_insn_arrays_ready(prog); if (err < 0) goto free_used_maps; err = bpf_prog_alloc_id(prog); if (err) goto free_used_maps; /* Upon success of bpf_prog_alloc_id(), the BPF prog is * effectively publicly exposed. However, retrieving via * bpf_prog_get_fd_by_id() will take another reference, * therefore it cannot be gone underneath us. * * Only for the time /after/ successful bpf_prog_new_fd() * and before returning to userspace, we might just hold * one reference and any parallel close on that fd could * rip everything out. Hence, below notifications must * happen before bpf_prog_new_fd(). * * Also, any failure handling from this point onwards must * be using bpf_prog_put() given the program is exposed. */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) bpf_prog_put(prog); return err; free_used_maps: /* In case we have subprogs, we need to wait for a grace * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; free_prog_sec: security_bpf_prog_free(prog); free_prog: free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); put_token: bpf_token_put(token); return err; } #define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_pin_user(attr->bpf_fd, path_fd, u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } /* bpf_link_init_sleepable() allows to specify whether BPF link itself has * "sleepable" semantics, which normally would mean that BPF link's attach * hook can dereference link or link's underlying program for some time after * detachment due to RCU Tasks Trace-based lifetime protection scheme. * BPF program itself can be non-sleepable, yet, because it's transitively * reachable through BPF link, its freeing has to be delayed until after RCU * Tasks Trace GP. */ void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type, bool sleepable) { WARN_ON(ops->dealloc && ops->dealloc_deferred); atomic64_set(&link->refcnt, 1); link->type = type; link->sleepable = sleepable; link->id = 0; link->ops = ops; link->prog = prog; link->attach_type = attach_type; } void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, enum bpf_attach_type attach_type) { bpf_link_init_sleepable(link, type, ops, prog, attach_type, false); } static void bpf_link_free_id(int id) { if (!id) return; spin_lock_bh(&link_idr_lock); idr_remove(&link_idr, id); spin_unlock_bh(&link_idr_lock); } /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred * anon_inode's release() call. This helper marks bpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. * This helper eventually calls link's dealloc callback, but does not call * link's release callback. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { primer->link->prog = NULL; bpf_link_free_id(primer->id); fput(primer->file); put_unused_fd(primer->fd); } void bpf_link_inc(struct bpf_link *link) { atomic64_inc(&link->refcnt); } static void bpf_link_dealloc(struct bpf_link *link) { /* now that we know that bpf_link itself can't be reached, put underlying BPF program */ if (link->prog) bpf_prog_put(link->prog); /* free bpf_link and its containing memory */ if (link->ops->dealloc_deferred) link->ops->dealloc_deferred(link); else link->ops->dealloc(link); } static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) { struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); bpf_link_dealloc(link); } static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_link_defer_dealloc_rcu_gp(rcu); else call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); } /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { const struct bpf_link_ops *ops = link->ops; bpf_link_free_id(link->id); /* detach BPF program, clean up used resources */ if (link->prog) ops->release(link); if (ops->dealloc_deferred) { /* Schedule BPF link deallocation, which will only then * trigger putting BPF program refcount. * If underlying BPF program is sleepable or BPF link's target * attach hookpoint is sleepable or otherwise requires RCU GPs * to ensure link and its underlying BPF program is not * reachable anymore, we need to first wait for RCU tasks * trace sync, and then go through "classic" RCU grace period */ if (link->sleepable || (link->prog && link->prog->sleepable)) call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); else call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); } else if (ops->dealloc) { bpf_link_dealloc(link); } } static void bpf_link_put_deferred(struct work_struct *work) { struct bpf_link *link = container_of(work, struct bpf_link, work); bpf_link_free(link); } /* bpf_link_put might be called from atomic context. It needs to be called * from sleepable context in order to acquire sleeping locks during the process. */ void bpf_link_put(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; INIT_WORK(&link->work, bpf_link_put_deferred); schedule_work(&link->work); } EXPORT_SYMBOL(bpf_link_put); static void bpf_link_put_direct(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; bpf_link_free(link); } static int bpf_link_release(struct inode *inode, struct file *filp) { struct bpf_link *link = filp->private_data; bpf_link_put_direct(link); return 0; } #ifdef CONFIG_PROC_FS #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) [_id] = #_name, static const char *bpf_link_type_strs[] = { [BPF_LINK_TYPE_UNSPEC] = "<invalid>", #include <linux/bpf_types.h> }; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; enum bpf_link_type type = link->type; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) { if (link->type == BPF_LINK_TYPE_KPROBE_MULTI) seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_KPROBE_MULTI_RETURN ? "kretprobe_multi" : "kprobe_multi"); else if (link->type == BPF_LINK_TYPE_UPROBE_MULTI) seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_UPROBE_MULTI_RETURN ? "uretprobe_multi" : "uprobe_multi"); else seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); } else { WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type); seq_printf(m, "link_type:\t<%u>\n", type); } seq_printf(m, "link_id:\t%u\n", link->id); if (prog) { bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_tag:\t%s\n" "prog_id:\t%u\n", prog_tag, prog->aux->id); } if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } #endif static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts) { struct bpf_link *link = file->private_data; return link->ops->poll(file, pts); } static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; static const struct file_operations bpf_link_fops_poll = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .poll = bpf_link_poll, }; static int bpf_link_alloc_id(struct bpf_link *link) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&link_idr_lock); id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); spin_unlock_bh(&link_idr_lock); idr_preload_end(); return id; } /* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, * reserving unused FD and allocating ID from link_idr. This is to be paired * with bpf_link_settle() to install FD and ID and expose bpf_link to * user-space, if bpf_link is successfully attached. If not, bpf_link and * pre-allocated resources are to be freed with bpf_cleanup() call. All the * transient state is passed around in struct bpf_link_primer. * This is preferred way to create and initialize bpf_link, especially when * there are complicated and expensive operations in between creating bpf_link * itself and attaching it to BPF hook. By using bpf_link_prime() and * bpf_link_settle() kernel code using bpf_link doesn't have to perform * expensive (and potentially failing) roll back operations in a rare case * that file, FD, or ID can't be allocated. */ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { struct file *file; int fd, id; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; id = bpf_link_alloc_id(link); if (id < 0) { put_unused_fd(fd); return id; } file = anon_inode_getfile("bpf_link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); if (IS_ERR(file)) { bpf_link_free_id(id); put_unused_fd(fd); return PTR_ERR(file); } primer->link = link; primer->file = file; primer->fd = fd; primer->id = id; return 0; } int bpf_link_settle(struct bpf_link_primer *primer) { /* make bpf_link fetchable by ID */ spin_lock_bh(&link_idr_lock); primer->link->id = primer->id; spin_unlock_bh(&link_idr_lock); /* make bpf_link fetchable by FD */ fd_install(primer->fd, primer->file); /* pass through installed FD */ return primer->fd; } int bpf_link_new_fd(struct bpf_link *link) { return anon_inode_getfd("bpf-link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_link *link; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll) return ERR_PTR(-EINVAL); link = fd_file(f)->private_data; bpf_link_inc(link); return link; } EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL"); static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, tr_link->trampoline, tr_link->tgt_prog)); bpf_trampoline_put(tr_link->trampoline); /* tgt_prog is NULL if target is a kernel function */ if (tr_link->tgt_prog) bpf_prog_put(tr_link->tgt_prog); } static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); kfree(tr_link); } static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); u32 target_btf_id, target_obj_id; bpf_trampoline_unpack_key(tr_link->trampoline->key, &target_obj_id, &target_btf_id); seq_printf(seq, "attach_type:\t%d\n" "target_obj_id:\t%u\n" "target_btf_id:\t%u\n" "cookie:\t%llu\n", link->attach_type, target_obj_id, target_btf_id, tr_link->link.cookie); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); info->tracing.attach_type = link->attach_type; info->tracing.cookie = tr_link->link.cookie; bpf_trampoline_unpack_key(tr_link->trampoline->key, &info->tracing.target_obj_id, &info->tracing.target_btf_id); return 0; } static const struct bpf_link_ops bpf_tracing_link_lops = { .release = bpf_tracing_link_release, .dealloc = bpf_tracing_link_dealloc, .show_fdinfo = bpf_tracing_link_show_fdinfo, .fill_link_info = bpf_tracing_link_fill_link_info, }; static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, u32 btf_id, u64 bpf_cookie, enum bpf_attach_type attach_type) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; struct bpf_trampoline *tr = NULL; struct bpf_tracing_link *link; u64 key = 0; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && prog->expected_attach_type != BPF_TRACE_FSESSION && prog->expected_attach_type != BPF_MODIFY_RETURN) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_EXT: if (prog->expected_attach_type != 0) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type != BPF_LSM_MAC) { err = -EINVAL; goto out_put_prog; } break; default: err = -EINVAL; goto out_put_prog; } if (!!tgt_prog_fd != !!btf_id) { err = -EINVAL; goto out_put_prog; } if (tgt_prog_fd) { /* * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this * part would be changed to implement the same for * BPF_PROG_TYPE_TRACING, do not forget to update the way how * attach_tracing_prog flag is set. */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } tgt_prog = bpf_prog_get(tgt_prog_fd); if (IS_ERR(tgt_prog)) { err = PTR_ERR(tgt_prog); tgt_prog = NULL; goto out_put_prog; } key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } if (prog->expected_attach_type == BPF_TRACE_FSESSION) { struct bpf_fsession_link *fslink; fslink = kzalloc_obj(*fslink, GFP_USER); if (fslink) { bpf_link_init(&fslink->fexit.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog, attach_type); fslink->fexit.cookie = bpf_cookie; link = &fslink->link; } else { link = NULL; } } else { link = kzalloc_obj(*link, GFP_USER); } if (!link) { err = -ENOMEM; goto out_put_prog; } bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog, attach_type); link->link.cookie = bpf_cookie; mutex_lock(&prog->aux->dst_mutex); /* There are a few possible cases here: * * - if prog->aux->dst_trampoline is set, the program was just loaded * and not yet attached to anything, so we can use the values stored * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. * * - if tgt_prog == NULL when this function was called using the old * raw_tracepoint_open API, and we need a target from prog->aux * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. * * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf * are NULL, then program was already attached and user did not provide * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* * Allow re-attach for TRACING and LSM programs. If it's * currently linked, bpf_trampoline_link_prog will fail. * EXT programs need to specify tgt_prog_fd, so they * re-attach in separate code path. */ if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { err = -EINVAL; goto out_unlock; } /* We can allow re-attach only if we have valid attach_btf. */ if (!prog->aux->attach_btf) { err = -EINVAL; goto out_unlock; } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } if (!prog->aux->dst_trampoline || (key && key != prog->aux->dst_trampoline->key)) { /* If there is no saved target, or the specified target is * different from the destination specified at load time, we * need a new trampoline and a check for compatibility */ struct bpf_attach_target_info tgt_info = {}; err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, &tgt_info); if (err) goto out_unlock; if (tgt_info.tgt_mod) { module_put(prog->aux->mod); prog->aux->mod = tgt_info.tgt_mod; } tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; goto out_unlock; } } else { /* The caller didn't specify a target, or the target was the * same as the destination supplied during program load. This * means we can reuse the trampoline and reference from program * load time, and there is no need to allocate a new one. This * can only happen once for any program, as the saved values in * prog->aux are cleared below. */ tr = prog->aux->dst_trampoline; tgt_prog = prog->aux->dst_prog; } err = bpf_link_prime(&link->link.link, &link_primer); if (err) goto out_unlock; err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); link = NULL; goto out_unlock; } link->tgt_prog = tgt_prog; link->trampoline = tr; /* Always clear the trampoline and target prog from prog->aux to make * sure the original attach destination is not kept alive after a * program is (re-)attached to another target. */ if (prog->aux->dst_prog && (tgt_prog_fd || tr != prog->aux->dst_trampoline)) /* got extra prog ref from syscall, or attaching to different prog */ bpf_prog_put(prog->aux->dst_prog); if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) /* we allocated a new trampoline, so free the old one */ bpf_trampoline_put(prog->aux->dst_trampoline); prog->aux->dst_prog = NULL; prog->aux->dst_trampoline = NULL; mutex_unlock(&prog->aux->dst_mutex); return bpf_link_settle(&link_primer); out_unlock: if (tr && tr != prog->aux->dst_trampoline) bpf_trampoline_put(tr); mutex_unlock(&prog->aux->dst_mutex); kfree(link); out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); return err; } static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } static void bpf_raw_tp_link_dealloc(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); kfree(raw_tp); } static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); seq_printf(seq, "tp_name:\t%s\n" "cookie:\t%llu\n", raw_tp_link->btp->tp->name, raw_tp_link->cookie); } static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen, u32 len) { if (ulen >= len + 1) { if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, buf, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } return 0; } static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); const char *tp_name = raw_tp_link->btp->tp->name; u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; info->raw_tracepoint.cookie = raw_tp_link->cookie; if (!ubuf) return 0; return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len); } static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #ifdef CONFIG_PERF_EVENTS struct bpf_perf_link { struct bpf_link link; struct file *perf_file; }; static void bpf_perf_link_release(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); struct perf_event *event = perf_link->perf_file->private_data; perf_event_free_bpf_prog(event); fput(perf_link->perf_file); } static void bpf_perf_link_dealloc(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); kfree(perf_link); } static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 *ulenp, u64 *probe_offset, u64 *probe_addr, u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id, ulen; size_t len; int err; ulen = *ulenp; if (!ulen ^ !uname) return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, probe_offset, probe_addr, missed); if (err) return err; if (buf) { len = strlen(buf); *ulenp = len + 1; } else { *ulenp = 1; } if (!uname) return 0; if (buf) { err = bpf_copy_to_user(uname, buf, ulen, len); if (err) return err; } else { char zero = '\0'; if (put_user(zero, uname)) return -EFAULT; } return 0; } #ifdef CONFIG_KPROBE_EVENTS static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; else info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.name_len = ulen; info->perf_event.kprobe.offset = offset; info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } static void bpf_perf_link_fdinfo_kprobe(const struct perf_event *event, struct seq_file *seq) { const char *name; int err; u32 prog_id, type; u64 offset, addr; unsigned long missed; err = bpf_get_perf_event_info(event, &prog_id, &type, &name, &offset, &addr, &missed); if (err) return; seq_printf(seq, "name:\t%s\n" "offset:\t%#llx\n" "missed:\t%lu\n" "addr:\t%#llx\n" "event_type:\t%s\n" "cookie:\t%llu\n", name, offset, missed, addr, type == BPF_FD_TYPE_KRETPROBE ? "kretprobe" : "kprobe", event->bpf_cookie); } #endif #ifdef CONFIG_UPROBE_EVENTS static int bpf_perf_link_fill_uprobe(const struct perf_event *event, struct bpf_link_info *info) { u64 ref_ctr_offset, offset; char __user *uname; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &ref_ctr_offset, &type, NULL); if (err) return err; if (type == BPF_FD_TYPE_URETPROBE) info->perf_event.type = BPF_PERF_EVENT_URETPROBE; else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; info->perf_event.uprobe.cookie = event->bpf_cookie; info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset; return 0; } static void bpf_perf_link_fdinfo_uprobe(const struct perf_event *event, struct seq_file *seq) { const char *name; int err; u32 prog_id, type; u64 offset, ref_ctr_offset; unsigned long missed; err = bpf_get_perf_event_info(event, &prog_id, &type, &name, &offset, &ref_ctr_offset, &missed); if (err) return; seq_printf(seq, "name:\t%s\n" "offset:\t%#llx\n" "ref_ctr_offset:\t%#llx\n" "event_type:\t%s\n" "cookie:\t%llu\n", name, offset, ref_ctr_offset, type == BPF_FD_TYPE_URETPROBE ? "uretprobe" : "uprobe", event->bpf_cookie); } #endif static int bpf_perf_link_fill_probe(const struct perf_event *event, struct bpf_link_info *info) { #ifdef CONFIG_KPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) return bpf_perf_link_fill_kprobe(event, info); #endif #ifdef CONFIG_UPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) return bpf_perf_link_fill_uprobe(event, info); #endif return -EOPNOTSUPP; } static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, struct bpf_link_info *info) { char __user *uname; u32 ulen; int err; uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); if (err) return err; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; info->perf_event.tracepoint.name_len = ulen; info->perf_event.tracepoint.cookie = event->bpf_cookie; return 0; } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, struct bpf_link_info *info) { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } static int bpf_perf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_perf_link *perf_link; const struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = perf_get_event(perf_link->perf_file); if (IS_ERR(event)) return PTR_ERR(event); switch (event->prog->type) { case BPF_PROG_TYPE_PERF_EVENT: return bpf_perf_link_fill_perf_event(event, info); case BPF_PROG_TYPE_TRACEPOINT: return bpf_perf_link_fill_tracepoint(event, info); case BPF_PROG_TYPE_KPROBE: return bpf_perf_link_fill_probe(event, info); default: return -EOPNOTSUPP; } } static void bpf_perf_event_link_show_fdinfo(const struct perf_event *event, struct seq_file *seq) { seq_printf(seq, "type:\t%u\n" "config:\t%llu\n" "event_type:\t%s\n" "cookie:\t%llu\n", event->attr.type, event->attr.config, "event", event->bpf_cookie); } static void bpf_tracepoint_link_show_fdinfo(const struct perf_event *event, struct seq_file *seq) { int err; const char *name; u32 prog_id; err = bpf_get_perf_event_info(event, &prog_id, NULL, &name, NULL, NULL, NULL); if (err) return; seq_printf(seq, "tp_name:\t%s\n" "event_type:\t%s\n" "cookie:\t%llu\n", name, "tracepoint", event->bpf_cookie); } static void bpf_probe_link_show_fdinfo(const struct perf_event *event, struct seq_file *seq) { #ifdef CONFIG_KPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) return bpf_perf_link_fdinfo_kprobe(event, seq); #endif #ifdef CONFIG_UPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) return bpf_perf_link_fdinfo_uprobe(event, seq); #endif } static void bpf_perf_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_perf_link *perf_link; const struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = perf_get_event(perf_link->perf_file); if (IS_ERR(event)) return; switch (event->prog->type) { case BPF_PROG_TYPE_PERF_EVENT: return bpf_perf_event_link_show_fdinfo(event, seq); case BPF_PROG_TYPE_TRACEPOINT: return bpf_tracepoint_link_show_fdinfo(event, seq); case BPF_PROG_TYPE_KPROBE: return bpf_probe_link_show_fdinfo(event, seq); default: return; } } static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, .fill_link_info = bpf_perf_link_fill_link_info, .show_fdinfo = bpf_perf_link_show_fdinfo, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_perf_link *link; struct perf_event *event; struct file *perf_file; int err; if (attr->link_create.flags) return -EINVAL; perf_file = perf_event_get(attr->link_create.target_fd); if (IS_ERR(perf_file)) return PTR_ERR(perf_file); link = kzalloc_obj(*link, GFP_USER); if (!link) { err = -ENOMEM; goto out_put_file; } bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog, attr->link_create.attach_type); link->perf_file = perf_file; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_file; } event = perf_file->private_data; err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); if (err) { bpf_link_cleanup(&link_primer); goto out_put_file; } /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ bpf_prog_inc(prog); return bpf_link_settle(&link_primer); out_put_file: fput(perf_file); return err; } #else static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, const char __user *user_tp_name, u64 cookie, enum bpf_attach_type attach_type) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; const char *tp_name; char buf[128]; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ return -EINVAL; if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } return bpf_tracing_prog_attach(prog, 0, 0, 0, attach_type); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); if (!btp) return -ENOENT; link = kzalloc_obj(*link, GFP_USER); if (!link) { err = -ENOMEM; goto out_put_btp; } bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog, attach_type, tracepoint_is_faultable(btp->tp)); link->btp = btp; link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_btp; } err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; } return bpf_link_settle(&link_primer); out_put_btp: bpf_put_raw_tracepoint(btp); return err; } #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; void __user *tp_name; __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); cookie = attr->raw_tracepoint.cookie; fd = bpf_raw_tp_link_attach(prog, tp_name, cookie, prog->expected_attach_type); if (fd < 0) bpf_prog_put(prog); return fd; } static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return BPF_PROG_TYPE_CGROUP_SKB; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; case BPF_LSM_MAC: return BPF_PROG_TYPE_LSM; case BPF_SK_LOOKUP: return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: return BPF_PROG_TYPE_XDP; case BPF_LSM_CGROUP: return BPF_PROG_TYPE_LSM; case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; } } static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { enum bpf_prog_type ptype; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ return -EPERM; ptype = attach_type_to_prog_type(attach_type); if (prog->type != ptype) return -EINVAL; return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; case BPF_PROG_TYPE_EXT: return 0; case BPF_PROG_TYPE_NETFILTER: if (attach_type != BPF_NETFILTER) return -EINVAL; return 0; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: if (attach_type != BPF_PERF_EVENT) return -EINVAL; return 0; case BPF_PROG_TYPE_KPROBE: if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_KPROBE_SESSION) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; return 0; case BPF_PROG_TYPE_SCHED_CLS: if (attach_type != BPF_TCX_INGRESS && attach_type != BPF_TCX_EGRESS && attach_type != BPF_NETKIT_PRIMARY && attach_type != BPF_NETKIT_PEER) return -EINVAL; return 0; default: ptype = attach_type_to_prog_type(attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) return -EINVAL; return 0; } } static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype, bool check_atype) { switch (ptype) { case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: return true; case BPF_PROG_TYPE_LSM: return check_atype ? atype == BPF_LSM_CGROUP : true; default: return false; } } #define BPF_PROG_ATTACH_LAST_FIELD expected_revision #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ BPF_F_REPLACE | \ BPF_F_PREORDER) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ BPF_F_BEFORE | \ BPF_F_AFTER | \ BPF_F_ID | \ BPF_F_LINK) static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (bpf_mprog_supported(ptype)) { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; } else if (is_cgroup_prog_type(ptype, 0, false)) { if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG)) return -EINVAL; } else { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE) return -EINVAL; if (attr->relative_fd || attr->expected_revision) return -EINVAL; } prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) { bpf_prog_put(prog); return -EINVAL; } if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) { ret = cgroup_bpf_prog_attach(attr, ptype, prog); goto out; } switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_attach(attr, prog); else ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; } out: if (ret) bpf_prog_put(prog); return ret; } #define BPF_PROG_DETACH_LAST_FIELD expected_revision static int bpf_prog_detach(const union bpf_attr *attr) { struct bpf_prog *prog = NULL; enum bpf_prog_type ptype; int ret; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (bpf_mprog_supported(ptype)) { if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; if (attr->attach_bpf_fd) { prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); } else if (!bpf_mprog_detach_empty(ptype)) { return -EPERM; } } else if (is_cgroup_prog_type(ptype, 0, false)) { if (attr->attach_flags || attr->relative_fd) return -EINVAL; } else if (attr->attach_flags || attr->relative_fd || attr->expected_revision) { return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_detach(attr); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: ret = cgroup_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_detach(attr, prog); else ret = netkit_prog_detach(attr, prog); break; default: ret = -EINVAL; } if (prog) bpf_prog_put(prog); return ret; } #define BPF_PROG_QUERY_LAST_FIELD query.revision static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) return -EINVAL; switch (attr->query.attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: case BPF_LSM_CGROUP: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_MSG_VERDICT: case BPF_SK_SKB_VERDICT: return sock_map_bpf_prog_query(attr, uattr); case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: return tcx_prog_query(attr, uattr); case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return netkit_prog_query(attr, uattr); default: return -EINVAL; } } #define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog *prog; int ret = -ENOTSUPP; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; if ((attr->test.ctx_size_in && !attr->test.ctx_in) || (!attr->test.ctx_size_in && attr->test.ctx_in)) return -EINVAL; if ((attr->test.ctx_size_out && !attr->test.ctx_out) || (!attr->test.ctx_size_out && attr->test.ctx_out)) return -EINVAL; prog = bpf_prog_get(attr->test.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->aux->ops->test_run) ret = prog->aux->ops->test_run(prog, attr, uattr); bpf_prog_put(prog); return ret; } #define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id static int bpf_obj_get_next_id(const union bpf_attr *attr, union bpf_attr __user *uattr, struct idr *idr, spinlock_t *lock) { u32 next_id = attr->start_id; int err = 0; if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; next_id++; spin_lock_bh(lock); if (!idr_get_next(idr, &next_id)) err = -ENOENT; spin_unlock_bh(lock); if (!err) err = put_user(next_id, &uattr->next_id); return err; } struct bpf_map *bpf_map_get_curr_or_next(u32 *id) { struct bpf_map *map; spin_lock_bh(&map_idr_lock); again: map = idr_get_next(&map_idr, id); if (map) { map = __bpf_map_inc_not_zero(map, false); if (IS_ERR(map)) { (*id)++; goto again; } } spin_unlock_bh(&map_idr_lock); return map; } struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) { struct bpf_prog *prog; spin_lock_bh(&prog_idr_lock); again: prog = idr_get_next(&prog_idr, id); if (prog) { prog = bpf_prog_inc_not_zero(prog); if (IS_ERR(prog)) { (*id)++; goto again; } } spin_unlock_bh(&prog_idr_lock); return prog; } #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); if (prog) prog = bpf_prog_inc_not_zero(prog); else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); return prog; } static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) { struct bpf_prog *prog; u32 id = attr->prog_id; int fd; if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); fd = bpf_prog_new_fd(prog); if (fd < 0) bpf_prog_put(prog); return fd; } #define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; int f_flags; int fd; if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; f_flags = bpf_get_file_flag(attr->open_flags); if (f_flags < 0) return f_flags; spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); if (IS_ERR(map)) return PTR_ERR(map); fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put_with_uref(map); return fd; } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, unsigned long addr, u32 *off, u32 *type) { const struct bpf_map *map; int i; mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; goto out; } } map = NULL; out: mutex_unlock(&prog->aux->used_maps_mutex); return map; } static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; u32 off, type; u64 imm; u8 code; int i; insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), GFP_USER); if (!insns) return insns; for (i = 0; i < prog->len; i++) { code = insns[i].code; if (code == (BPF_JMP | BPF_TAIL_CALL)) { insns[i].code = BPF_JMP | BPF_CALL; insns[i].imm = BPF_FUNC_tail_call; /* fall-through */ } if (code == (BPF_JMP | BPF_CALL) || code == (BPF_JMP | BPF_CALL_ARGS)) { if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) { insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM; continue; } if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; continue; } if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { insns[i].src_reg = type; insns[i].imm = map->id; insns[i + 1].imm = off; continue; } } return insns; } static int set_info_rec_size(struct bpf_prog_info *info) { /* * Ensure info.*_rec_size is the same as kernel expected size * * or * * Only allow zero *_rec_size if both _rec_size and _cnt are * zero. In this case, the kernel will set the expected * _rec_size back to the info. */ if ((info->nr_func_info || info->func_info_rec_size) && info->func_info_rec_size != sizeof(struct bpf_func_info)) return -EINVAL; if ((info->nr_line_info || info->line_info_rec_size) && info->line_info_rec_size != sizeof(struct bpf_line_info)) return -EINVAL; if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && info->jited_line_info_rec_size != sizeof(__u64)) return -EINVAL; info->func_info_rec_size = sizeof(struct bpf_func_info); info->line_info_rec_size = sizeof(struct bpf_line_info); info->jited_line_info_rec_size = sizeof(__u64); return 0; } static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct btf *attach_btf = bpf_prog_get_target_btf(prog); struct bpf_prog_info info; u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = prog->type; info.id = prog->aux->id; info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, &user_map_ids[i])) { mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; } } mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) return err; bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; if (prog->aux->btf) info.btf_id = btf_obj_id(prog->aux->btf); if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; info.nr_jited_func_lens = 0; info.nr_func_info = 0; info.nr_line_info = 0; info.nr_jited_line_info = 0; goto done; } ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { struct bpf_insn *insns_sanitized; bool fault; if (!prog->blinded || bpf_dump_raw_ok(file->f_cred)) { insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); ulen = min_t(u32, info.xlated_prog_len, ulen); fault = copy_to_user(uinsns, insns_sanitized, ulen); kfree(insns_sanitized); if (fault) return -EFAULT; } else { info.xlated_prog_insns = 0; } } if (bpf_prog_is_offloaded(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; goto done; } /* NOTE: the following code is supposed to be skipped for offload. * bpf_prog_offload_info_fill() is the place to fill similar fields * for offload. */ ulen = info.jited_prog_len; if (prog->aux->func_cnt) { u32 i; info.jited_prog_len = 0; for (i = 0; i < prog->aux->func_cnt; i++) info.jited_prog_len += prog->aux->func[i]->jited_len; } else { info.jited_prog_len = prog->jited_len; } if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); /* for multi-function programs, copy the JITed * instructions for all the functions */ if (prog->aux->func_cnt) { u32 len, free, i; u8 *img; free = ulen; for (i = 0; i < prog->aux->func_cnt; i++) { len = prog->aux->func[i]->jited_len; len = min_t(u32, len, free); img = (u8 *) prog->aux->func[i]->bpf_func; if (copy_to_user(uinsns, img, len)) return -EFAULT; uinsns += len; free -= len; if (!free) break; } } else { if (copy_to_user(uinsns, prog->bpf_func, ulen)) return -EFAULT; } } else { info.jited_prog_insns = 0; } } ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; /* copy the address of the kernel symbol * corresponding to each function */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { ksym_addr = (unsigned long) prog->aux->func[i]->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[i])) return -EFAULT; } } else { ksym_addr = (unsigned long) prog->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { info.jited_ksyms = 0; } } ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { func_len = prog->aux->func[i]->jited_len; if (put_user(func_len, &user_lens[i])) return -EFAULT; } } else { func_len = prog->jited_len; if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { info.jited_func_lens = 0; } } info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; if (info.nr_func_info && ulen) { char __user *user_finfo; user_finfo = u64_to_user_ptr(info.func_info); ulen = min_t(u32, info.nr_func_info, ulen); if (copy_to_user(user_finfo, prog->aux->func_info, info.func_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_line_info; info.nr_line_info = prog->aux->nr_linfo; if (info.nr_line_info && ulen) { __u8 __user *user_linfo; user_linfo = u64_to_user_ptr(info.line_info); ulen = min_t(u32, info.nr_line_info, ulen); if (copy_to_user(user_linfo, prog->aux->linfo, info.line_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_jited_line_info; if (prog->aux->jited_linfo) info.nr_jited_line_info = prog->aux->nr_linfo; else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long line_addr; __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { line_addr = (unsigned long)prog->aux->jited_linfo[i]; if (put_user((__u64)line_addr, &user_linfo[i])) return -EFAULT; } } else { info.jited_line_info = 0; } } ulen = info.nr_prog_tags; info.nr_prog_tags = prog->aux->func_cnt ? : 1; if (ulen) { __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; u32 i; user_prog_tags = u64_to_user_ptr(info.prog_tags); ulen = min_t(u32, info.nr_prog_tags, ulen); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { if (copy_to_user(user_prog_tags[i], prog->aux->func[i]->tag, BPF_TAG_SIZE)) return -EFAULT; } } else { if (copy_to_user(user_prog_tags[0], prog->tag, BPF_TAG_SIZE)) return -EFAULT; } } done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_map_get_info_by_fd(struct file *file, struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; } if (info.hash) { char __user *uhash = u64_to_user_ptr(info.hash); if (!map->ops->map_get_hash) return -EINVAL; if (info.hash_size != SHA256_DIGEST_SIZE) return -EINVAL; if (!READ_ONCE(map->frozen)) return -EPERM; err = map->ops->map_get_hash(map, SHA256_DIGEST_SIZE, map->sha); if (err != 0) return err; if (copy_to_user(uhash, map->sha, SHA256_DIGEST_SIZE) != 0) return -EFAULT; } else if (info.hash_size) { return -EINVAL; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_btf_get_info_by_fd(struct file *file, struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return btf_get_info_by_fd(btf, attr, uattr); } static int bpf_link_get_info_by_fd(struct file *file, struct bpf_link *link, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_link_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = link->type; info.id = link->id; if (link->prog) info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int token_get_info_by_fd(struct file *file, struct bpf_token *token, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return bpf_token_get_info_by_fd(token, attr, uattr); } #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) return -EINVAL; CLASS(fd, f)(attr->info.bpf_fd); if (fd_empty(f)) return -EBADFD; if (fd_file(f)->f_op == &bpf_prog_fops) return bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_map_fops) return bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &btf_fops) return bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll) return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_token_fops) return token_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); return -EINVAL; } #define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { struct bpf_token *token = NULL; if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; if (attr->btf_flags & ~BPF_F_TOKEN_FD) return -EINVAL; if (attr->btf_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->btf_token_fd); if (IS_ERR(token)) return PTR_ERR(token); if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { bpf_token_put(token); token = NULL; } } if (!bpf_token_capable(token, CAP_BPF)) { bpf_token_put(token); return -EPERM; } bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD fd_by_id_token_fd static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { struct bpf_token *token = NULL; if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; if (attr->open_flags & ~BPF_F_TOKEN_FD) return -EINVAL; if (attr->open_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->fd_by_id_token_fd); if (IS_ERR(token)) return PTR_ERR(token); if (!bpf_token_allow_cmd(token, BPF_BTF_GET_FD_BY_ID)) { bpf_token_put(token); token = NULL; } } if (!bpf_token_capable(token, CAP_SYS_ADMIN)) { bpf_token_put(token); return -EPERM; } bpf_token_put(token); return btf_get_fd_by_id(attr->btf_id); } static int bpf_task_fd_query_copy(const union bpf_attr *attr, union bpf_attr __user *uattr, u32 prog_id, u32 fd_type, const char *buf, u64 probe_offset, u64 probe_addr) { char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); u32 len = buf ? strlen(buf) : 0, input_len; int err = 0; if (put_user(len, &uattr->task_fd_query.buf_len)) return -EFAULT; input_len = attr->task_fd_query.buf_len; if (input_len && ubuf) { if (!len) { /* nothing to copy, just make ubuf NULL terminated */ char zero = '\0'; if (put_user(zero, ubuf)) return -EFAULT; } else { err = bpf_copy_to_user(ubuf, buf, input_len, len); if (err == -EFAULT) return err; } } if (put_user(prog_id, &uattr->task_fd_query.prog_id) || put_user(fd_type, &uattr->task_fd_query.fd_type) || put_user(probe_offset, &uattr->task_fd_query.probe_offset) || put_user(probe_addr, &uattr->task_fd_query.probe_addr)) return -EFAULT; return err; } #define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr static int bpf_task_fd_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; struct task_struct *task; struct file *file; int err; if (CHECK_ATTR(BPF_TASK_FD_QUERY)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (attr->task_fd_query.flags != 0) return -EINVAL; rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); rcu_read_unlock(); if (!task) return -ENOENT; err = 0; file = fget_task(task, fd); put_task_struct(task); if (!file) return -EBADF; if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) { struct bpf_link *link = file->private_data; if (link->ops == &bpf_raw_tp_link_lops) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); struct bpf_raw_event_map *btp = raw_tp->btp; err = bpf_task_fd_query_copy(attr, uattr, raw_tp->link.prog->aux->id, BPF_FD_TYPE_RAW_TRACEPOINT, btp->tp->name, 0, 0); goto put_file; } goto out_not_supp; } event = perf_get_event(file); if (!IS_ERR(event)) { u64 probe_offset, probe_addr; u32 prog_id, fd_type; const char *buf; err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, probe_offset, probe_addr); goto put_file; } out_not_supp: err = -ENOTSUPP; put_file: fput(file); return err; } #define BPF_MAP_BATCH_LAST_FIELD batch.flags #define BPF_DO_BATCH(fn, ...) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ err = fn(__VA_ARGS__); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; CLASS(fd, f)(attr->batch.map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (has_write) bpf_map_write_active_inc(map); if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch, map, attr, uattr); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: if (has_write) { maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); } return err; } #define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; if (attr->link_create.attach_type == BPF_STRUCT_OPS) return bpf_struct_ops_link_create(attr); prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_attach_check_attach_type(prog, attr->link_create.attach_type); if (ret) goto out; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_EXT: ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie, attr->link_create.attach_type); break; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: if (attr->link_create.attach_type != prog->expected_attach_type) { ret = -EINVAL; goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie, attr->link_create.attach_type); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) ret = cgroup_bpf_link_attach(attr, prog); else ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie, attr->link_create.attach_type); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_link_create(attr, prog); break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->link_create.attach_type == BPF_TCX_INGRESS || attr->link_create.attach_type == BPF_TCX_EGRESS) ret = tcx_link_attach(attr, prog); else ret = netkit_link_attach(attr, prog); break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); break; #endif case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: ret = bpf_perf_link_attach(attr, prog); break; case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION) ret = bpf_uprobe_multi_link_attach(attr, prog); break; default: ret = -EINVAL; } out: if (ret < 0) bpf_prog_put(prog); return ret; } static int link_update_map(struct bpf_link *link, union bpf_attr *attr) { struct bpf_map *new_map, *old_map = NULL; int ret; new_map = bpf_map_get(attr->link_update.new_map_fd); if (IS_ERR(new_map)) return PTR_ERR(new_map); if (attr->link_update.flags & BPF_F_REPLACE) { old_map = bpf_map_get(attr->link_update.old_map_fd); if (IS_ERR(old_map)) { ret = PTR_ERR(old_map); goto out_put; } } else if (attr->link_update.old_map_fd) { ret = -EINVAL; goto out_put; } ret = link->ops->update_map(link, new_map, old_map); if (old_map) bpf_map_put(old_map); out_put: bpf_map_put(new_map); return ret; } #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) { struct bpf_prog *old_prog = NULL, *new_prog; struct bpf_link *link; u32 flags; int ret; if (CHECK_ATTR(BPF_LINK_UPDATE)) return -EINVAL; flags = attr->link_update.flags; if (flags & ~BPF_F_REPLACE) return -EINVAL; link = bpf_link_get_from_fd(attr->link_update.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->update_map) { ret = link_update_map(link, attr); goto out_put_link; } new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); goto out_put_link; } if (flags & BPF_F_REPLACE) { old_prog = bpf_prog_get(attr->link_update.old_prog_fd); if (IS_ERR(old_prog)) { ret = PTR_ERR(old_prog); old_prog = NULL; goto out_put_progs; } } else if (attr->link_update.old_prog_fd) { ret = -EINVAL; goto out_put_progs; } if (link->ops->update_prog) ret = link->ops->update_prog(link, new_prog, old_prog); else ret = -EINVAL; out_put_progs: if (old_prog) bpf_prog_put(old_prog); if (ret) bpf_prog_put(new_prog); out_put_link: bpf_link_put_direct(link); return ret; } #define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd static int link_detach(union bpf_attr *attr) { struct bpf_link *link; int ret; if (CHECK_ATTR(BPF_LINK_DETACH)) return -EINVAL; link = bpf_link_get_from_fd(attr->link_detach.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->detach) ret = link->ops->detach(link); else ret = -EOPNOTSUPP; bpf_link_put_direct(link); return ret; } struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } EXPORT_SYMBOL(bpf_link_inc_not_zero); struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ link = idr_find(&link_idr, id); if (link) { if (link->id) link = bpf_link_inc_not_zero(link); else link = ERR_PTR(-EAGAIN); } else { link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); return link; } struct bpf_link *bpf_link_get_curr_or_next(u32 *id) { struct bpf_link *link; spin_lock_bh(&link_idr_lock); again: link = idr_get_next(&link_idr, id); if (link) { link = bpf_link_inc_not_zero(link); if (IS_ERR(link)) { (*id)++; goto again; } } spin_unlock_bh(&link_idr_lock); return link; } #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id static int bpf_link_get_fd_by_id(const union bpf_attr *attr) { struct bpf_link *link; u32 id = attr->link_id; int fd; if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; link = bpf_link_by_id(id); if (IS_ERR(link)) return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) bpf_link_put_direct(link); return fd; } DEFINE_MUTEX(bpf_stats_enabled_mutex); static int bpf_stats_release(struct inode *inode, struct file *file) { mutex_lock(&bpf_stats_enabled_mutex); static_key_slow_dec(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return 0; } static const struct file_operations bpf_stats_fops = { .release = bpf_stats_release, }; static int bpf_enable_runtime_stats(void) { int fd; mutex_lock(&bpf_stats_enabled_mutex); /* Set a very high limit to avoid overflow */ if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { mutex_unlock(&bpf_stats_enabled_mutex); return -EBUSY; } fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); if (fd >= 0) static_key_slow_inc(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return fd; } #define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type static int bpf_enable_stats(union bpf_attr *attr) { if (CHECK_ATTR(BPF_ENABLE_STATS)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; switch (attr->enable_stats.type) { case BPF_STATS_RUN_TIME: return bpf_enable_runtime_stats(); default: break; } return -EINVAL; } #define BPF_ITER_CREATE_LAST_FIELD iter_create.flags static int bpf_iter_create(union bpf_attr *attr) { struct bpf_link *link; int err; if (CHECK_ATTR(BPF_ITER_CREATE)) return -EINVAL; if (attr->iter_create.flags) return -EINVAL; link = bpf_link_get_from_fd(attr->iter_create.link_fd); if (IS_ERR(link)) return PTR_ERR(link); err = bpf_iter_new_fd(link); bpf_link_put_direct(link); return err; } #define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags static int bpf_prog_bind_map(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; struct bpf_map **used_maps_old, **used_maps_new; int i, ret = 0; if (CHECK_ATTR(BPF_PROG_BIND_MAP)) return -EINVAL; if (attr->prog_bind_map.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_bind_map.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); map = bpf_map_get(attr->prog_bind_map.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto out_prog_put; } mutex_lock(&prog->aux->used_maps_mutex); used_maps_old = prog->aux->used_maps; for (i = 0; i < prog->aux->used_map_cnt; i++) if (used_maps_old[i] == map) { bpf_map_put(map); goto out_unlock; } used_maps_new = kmalloc_objs(used_maps_new[0], prog->aux->used_map_cnt + 1); if (!used_maps_new) { ret = -ENOMEM; goto out_unlock; } /* The bpf program will not access the bpf map, but for the sake of * simplicity, increase sleepable_refcnt for sleepable program as well. */ if (prog->sleepable) atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; prog->aux->used_map_cnt++; prog->aux->used_maps = used_maps_new; kfree(used_maps_old); out_unlock: mutex_unlock(&prog->aux->used_maps_mutex); if (ret) bpf_map_put(map); out_prog_put: bpf_prog_put(prog); return ret; } #define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd static int token_create(union bpf_attr *attr) { if (CHECK_ATTR(BPF_TOKEN_CREATE)) return -EINVAL; /* no flags are supported yet */ if (attr->token_create.flags) return -EINVAL; return bpf_token_create(attr); } #define BPF_PROG_STREAM_READ_BY_FD_LAST_FIELD prog_stream_read.prog_fd static int prog_stream_read(union bpf_attr *attr) { char __user *buf = u64_to_user_ptr(attr->prog_stream_read.stream_buf); u32 len = attr->prog_stream_read.stream_buf_len; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_STREAM_READ_BY_FD)) return -EINVAL; prog = bpf_prog_get(attr->prog_stream_read.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_stream_read(prog, attr->prog_stream_read.stream_id, buf, len); bpf_prog_put(prog); return ret; } #define BPF_PROG_ASSOC_STRUCT_OPS_LAST_FIELD prog_assoc_struct_ops.prog_fd static int prog_assoc_struct_ops(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; int ret; if (CHECK_ATTR(BPF_PROG_ASSOC_STRUCT_OPS)) return -EINVAL; if (attr->prog_assoc_struct_ops.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_assoc_struct_ops.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) { ret = -EINVAL; goto put_prog; } map = bpf_map_get(attr->prog_assoc_struct_ops.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto put_prog; } if (map->map_type != BPF_MAP_TYPE_STRUCT_OPS) { ret = -EINVAL; goto put_map; } ret = bpf_prog_assoc_struct_ops(prog, map); put_map: bpf_map_put(map); put_prog: bpf_prog_put(prog); return ret; } static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size, uattr.is_kernel); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr, uattr); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr, uattr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; case BPF_MAP_FREEZE: err = map_freeze(&attr); break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr, size); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); break; case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; case BPF_MAP_GET_FD_BY_ID: err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); break; case BPF_LINK_GET_FD_BY_ID: err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; case BPF_ITER_CREATE: err = bpf_iter_create(&attr); break; case BPF_LINK_DETACH: err = link_detach(&attr); break; case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; case BPF_TOKEN_CREATE: err = token_create(&attr); break; case BPF_PROG_STREAM_READ_BY_FD: err = prog_stream_read(&attr); break; case BPF_PROG_ASSOC_STRUCT_OPS: err = prog_assoc_struct_ops(&attr); break; default: err = -EINVAL; break; } return err; } SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { return __sys_bpf(cmd, USER_BPFPTR(uattr), size); } static bool syscall_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= U16_MAX) return false; if (off % size != 0) return false; return true; } BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) { switch (cmd) { case BPF_MAP_CREATE: case BPF_MAP_DELETE_ELEM: case BPF_MAP_UPDATE_ELEM: case BPF_MAP_FREEZE: case BPF_MAP_GET_FD_BY_ID: case BPF_PROG_LOAD: case BPF_BTF_LOAD: case BPF_LINK_CREATE: case BPF_RAW_TRACEPOINT_OPEN: break; default: return -EINVAL; } return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); } /* To shut up -Wmissing-prototypes. * This function is used by the kernel light skeleton * to load bpf programs when modules are loaded or during kernel boot. * See tools/lib/bpf/skel_internal.h */ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) { struct bpf_prog * __maybe_unused prog; struct bpf_tramp_run_ctx __maybe_unused run_ctx; switch (cmd) { #ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */ case BPF_PROG_TEST_RUN: if (attr->test.data_in || attr->test.data_out || attr->test.ctx_out || attr->test.duration || attr->test.repeat || attr->test.flags) return -EINVAL; prog = bpf_prog_get_type(attr->test.prog_fd, BPF_PROG_TYPE_SYSCALL); if (IS_ERR(prog)) return PTR_ERR(prog); if (attr->test.ctx_size_in < prog->aux->max_ctx_offset || attr->test.ctx_size_in > U16_MAX) { bpf_prog_put(prog); return -EINVAL; } run_ctx.bpf_cookie = 0; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); bpf_prog_put(prog); return 0; #endif default: return ____bpf_sys_bpf(cmd, attr, size); } } EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL"); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) { /* When bpf program calls this helper there should not be * an fdget() without matching completed fdput(). * This helper is allowed in the following callchain only: * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close */ return close_fd(fd); } static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) { *res = 0; if (flags) return -EINVAL; if (name_sz <= 1 || name[name_sz - 1]) return -EINVAL; if (!bpf_dump_raw_ok(current_cred())) return -EPERM; *res = kallsyms_lookup_name(name); return *res ? 0 : -ENOENT; } static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .func = bpf_kallsyms_lookup_name, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: return !bpf_token_capable(prog->aux->token, CAP_PERFMON) ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; case BPF_FUNC_kallsyms_lookup_name: return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } } const struct bpf_verifier_ops bpf_syscall_verifier_ops = { .get_func_proto = syscall_prog_func_proto, .is_valid_access = syscall_prog_is_valid_access, }; const struct bpf_prog_ops bpf_syscall_prog_ops = { .test_run = bpf_prog_test_run_syscall, }; #ifdef CONFIG_SYSCTL static int bpf_stats_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; static int saved_val; int val, ret; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(val), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&bpf_stats_enabled_mutex); val = saved_val; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret && val != saved_val) { if (val) static_key_slow_inc(key); else static_key_slow_dec(key); saved_val = val; } mutex_unlock(&bpf_stats_enabled_mutex); return ret; } void __weak unpriv_ebpf_notify(int new_state) { } static int bpf_unpriv_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, unpriv_enable = *(int *)table->data; bool locked_state = unpriv_enable == 1; struct ctl_table tmp = *table; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; tmp.data = &unpriv_enable; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (locked_state && unpriv_enable != 1) return -EPERM; *(int *)table->data = unpriv_enable; } if (write) unpriv_ebpf_notify(unpriv_enable); return ret; } static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", .data = &bpf_stats_enabled_key.key, .mode = 0644, .proc_handler = bpf_stats_handler, }, }; static int __init bpf_syscall_sysctl_init(void) { register_sysctl_init("kernel", bpf_syscall_table); return 0; } late_initcall(bpf_syscall_sysctl_init); #endif /* CONFIG_SYSCTL */ |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux IPv6 multicast routing support for BSD pim6sd * Based on net/ipv4/ipmr.c. * * (c) 2004 Mickael Hoerdt, <hoerdt@clarinet.u-strasbg.fr> * LSIIT Laboratory, Strasbourg, France * (c) 2004 Jean-Philippe Andriot, <jean-philippe.andriot@6WIND.com> * 6WIND, Paris, France * Copyright (C)2007,2008 USAGI/WIDE Project * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/rhashtable.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <linux/mroute6.h> #include <linux/pim.h> #include <net/addrconf.h> #include <linux/netfilter_ipv6.h> #include <linux/export.h> #include <net/ip6_checksum.h> #include <linux/netconf.h> #include <net/ip_tunnels.h> #include <linux/nospec.h> struct ip6mr_rule { struct fib_rule common; }; struct ip6mr_result { struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ static DEFINE_SPINLOCK(mrt_lock); static struct net_device *vif_dev_read(const struct vif_device *vif) { return rcu_dereference(vif->dev); } /* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved entries is changed only in process context and protected with weak lock mrt_lock. Queue of unresolved entries is protected with strong spinlock mfc_unres_lock. In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ip6mr_new_table(struct net *net, u32 id); static void ip6mr_free_table(struct mr_table *mrt); static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd); static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \ lockdep_rtnl_is_held() || \ list_empty(&net->ipv6.mr6_tables)) static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { struct mr_table *ret; if (!mrt) ret = list_entry_rcu(net->ipv6.mr6_tables.next, struct mr_table, list); else ret = list_entry_rcu(mrt->list.next, struct mr_table, list); if (&ret->list == &net->ipv6.mr6_tables) return NULL; return ret; } static struct mr_table *__ip6mr_get_table(struct net *net, u32 id) { struct mr_table *mrt; ip6mr_for_each_table(mrt, net) { if (mrt->id == id) return mrt; } return NULL; } static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { struct mr_table *mrt; rcu_read_lock(); mrt = __ip6mr_get_table(net, id); rcu_read_unlock(); return mrt; } static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr_table **mrt) { int err; struct ip6mr_result res; struct fib_lookup_arg arg = { .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi6_to_flowi(flp6)); err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flowi6_to_flowi(flp6), 0, &arg); if (err < 0) return err; *mrt = res.mrt; return 0; } static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ip6mr_result *res = arg->result; struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } arg->table = fib_rule_get_table(rule, arg); mrt = __ip6mr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; } static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) { return 1; } static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { return 0; } static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { return 1; } static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { frh->dst_len = 0; frh->src_len = 0; frh->tos = 0; return 0; } static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { .family = RTNL_FAMILY_IP6MR, .rule_size = sizeof(struct ip6mr_rule), .addr_size = sizeof(struct in6_addr), .action = ip6mr_rule_action, .match = ip6mr_rule_match, .configure = ip6mr_rule_configure, .compare = ip6mr_rule_compare, .fill = ip6mr_rule_fill, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, }; static int __net_init ip6mr_rules_init(struct net *net) { struct fib_rules_ops *ops; struct mr_table *mrt; int err; ops = fib_rules_register(&ip6mr_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); INIT_LIST_HEAD(&net->ipv6.mr6_tables); mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); if (IS_ERR(mrt)) { err = PTR_ERR(mrt); goto err1; } err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT); if (err < 0) goto err2; net->ipv6.mr6_rules_ops = ops; return 0; err2: rtnl_lock(); ip6mr_free_table(mrt); rtnl_unlock(); err1: fib_rules_unregister(ops); return err; } static void __net_exit ip6mr_rules_exit(struct net *net) { struct mr_table *mrt, *next; ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) { list_del(&mrt->list); ip6mr_free_table(mrt); } fib_rules_unregister(net->ipv6.mr6_rules_ops); } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack); } static unsigned int ip6mr_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR); } bool ip6mr_rule_default(const struct fib_rule *rule) { return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL && rule->table == RT6_TABLE_DFLT && !rule->l3mdev; } EXPORT_SYMBOL(ip6mr_rule_default); #else #define ip6mr_for_each_table(mrt, net) \ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) return net->ipv6.mrt6; return NULL; } static struct mr_table *ip6mr_get_table(struct net *net, u32 id) { return net->ipv6.mrt6; } #define __ip6mr_get_table ip6mr_get_table static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, struct mr_table **mrt) { *mrt = net->ipv6.mrt6; return 0; } static int __net_init ip6mr_rules_init(struct net *net) { struct mr_table *mrt; mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); if (IS_ERR(mrt)) return PTR_ERR(mrt); net->ipv6.mrt6 = mrt; return 0; } static void __net_exit ip6mr_rules_exit(struct net *net) { ASSERT_RTNL(); ip6mr_free_table(net->ipv6.mrt6); net->ipv6.mrt6 = NULL; } static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static unsigned int ip6mr_rules_seq_read(const struct net *net) { return 0; } #endif static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct mfc6_cache_cmp_arg *cmparg = arg->key; struct mfc6_cache *c = (struct mfc6_cache *)ptr; return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) || !ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin); } static const struct rhashtable_params ip6mr_rht_params = { .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc6_cache, cmparg), .key_len = sizeof(struct mfc6_cache_cmp_arg), .nelem_hint = 3, .obj_cmpfn = ip6mr_hash_cmp, .automatic_shrinking = true, }; static void ip6mr_new_table_set(struct mr_table *mrt, struct net *net) { #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); #endif } static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = { .mf6c_origin = IN6ADDR_ANY_INIT, .mf6c_mcastgrp = IN6ADDR_ANY_INIT, }; static struct mr_table_ops ip6mr_mr_table_ops = { .rht_params = &ip6mr_rht_params, .cmparg_any = &ip6mr_mr_table_ops_cmparg_any, }; static struct mr_table *ip6mr_new_table(struct net *net, u32 id) { struct mr_table *mrt; mrt = __ip6mr_get_table(net, id); if (mrt) return mrt; return mr_table_alloc(net, id, &ip6mr_mr_table_ops, ipmr_expire_process, ip6mr_new_table_set); } static void ip6mr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); WARN_ON_ONCE(!mr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC | MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing * /proc/ip6_mr_cache /proc/ip6_mr_vif */ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; rcu_read_lock(); mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) { rcu_read_unlock(); return ERR_PTR(-ENOENT); } iter->mrt = mrt; return mr_vif_seq_start(seq, pos); } static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); } else { const struct vif_device *vif = v; const struct net_device *vif_dev; const char *name; vif_dev = vif_dev_read(vif); name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); } return 0; } static const struct seq_operations ip6mr_vif_seq_ops = { .start = ip6mr_vif_seq_start, .next = mr_vif_seq_next, .stop = ip6mr_vif_seq_stop, .show = ip6mr_vif_seq_show, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct mr_table *mrt; mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) return ERR_PTR(-ENOENT); return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Group " "Origin " "Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc6_cache *mfc = v; const struct mr_mfc_iter *it = seq->private; struct mr_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", atomic_long_read(&mfc->_c.mfc_un.res.pkt), atomic_long_read(&mfc->_c.mfc_un.res.bytes), atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain * pkt, bytes and wrong_if values */ seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = mr_mfc_seq_next, .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; #endif #ifdef CONFIG_IPV6_PIMSM_V2 static int pim6_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; int reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) || (pim->flags & PIM_NULL_REGISTER) || (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, sizeof(*pim), IPPROTO_PIM, csum_partial((void *)pim, sizeof(*pim), 0)) && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; /* check if the inner packet is destined to mcast group */ encap = (struct ipv6hdr *)(skb_transport_header(skb) + sizeof(*pim)); if (!ipv6_addr_is_multicast(&encap->daddr) || encap->payload_len == 0 || ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto drop; /* Pairs with WRITE_ONCE() in mif6_add()/mif6_delete() */ reg_vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (reg_vif_num >= 0) reg_dev = vif_dev_read(&mrt->vif_table[reg_vif_num]); if (!reg_dev) goto drop; skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = CHECKSUM_NONE; skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); return 0; drop: kfree_skb(skb); return 0; } static const struct inet6_protocol pim6_protocol = { .handler = pim6_rcv, }; /* Service routines creating virtual interfaces: PIMREG */ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; if (!pskb_inet_may_pull(skb)) goto tx_err; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto tx_err; DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), MRT6MSG_WHOLEPKT); rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) { return 0; } static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8; dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; dev->netns_immutable = true; } static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; if (mrt->id == RT6_TABLE_DFLT) sprintf(name, "pim6reg"); else sprintf(name, "pim6reg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (!dev) return NULL; dev_net_set(dev, net); if (register_netdevice(dev)) { free_netdev(dev); return NULL; } if (dev_open(dev, NULL)) goto failure; dev_hold(dev); return dev; failure: unregister_netdevice(dev); return NULL; } #endif static int call_ip6mr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, mifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type, vif, vif_dev, vif_index, tb_id, &net->ipv6.ipmr_seq); } static int call_ip6mr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc6_cache *mfc, u32 tb_id) { return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type, &mfc->_c, tb_id, &net->ipv6.ipmr_seq); } /* Delete a VIF entry */ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct vif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; v = &mrt->vif_table[vifi]; dev = rtnl_dereference(v->dev); if (!dev) return -EADDRNOTAVAIL; call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_VIF_DEL, v, dev, vifi, mrt->id); spin_lock(&mrt_lock); RCU_INIT_POINTER(v->dev, NULL); #ifdef CONFIG_IPV6_PIMSM_V2 if (vifi == mrt->mroute_reg_vif_num) { /* Pairs with READ_ONCE() in ip6mr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, -1); } #endif if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } WRITE_ONCE(mrt->maxvif, tmp + 1); } spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); in6_dev = __in6_dev_get(dev); if (in6_dev) { atomic_dec(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); netdev_put(dev, &v->dev_tracker); return 0; } static inline void ip6mr_cache_free_rcu(struct rcu_head *head) { struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c); } static inline void ip6mr_cache_free(struct mfc6_cache *c) { call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs and reporting error to netlink readers. */ static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)nlmsg_data(nlh))->error = -ETIMEDOUT; rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else kfree_skb(skb); } ip6mr_cache_free(c); } /* Timer process for all the unresolved queue. */ static void ipmr_do_expire_process(struct mr_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; struct mr_mfc *c, *next; list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; continue; } list_del(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = timer_container_of(mrt, t, ipmr_expire_timer); if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } if (!list_empty(&mrt->mfc_unres_queue)) ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under locked mrt_lock. */ static void ip6mr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; cache->mfc_un.res.minvif = MAXMIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; if (cache->mfc_un.res.maxvif <= vifi) cache->mfc_un.res.maxvif = vifi + 1; } } WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int mif6_add(struct net *net, struct mr_table *mrt, struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { #ifdef CONFIG_IPV6_PIMSM_V2 case MIFF_REGISTER: /* * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ip6mr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); if (err) { unregister_netdevice(dev); dev_put(dev); return err; } break; #endif case 0: dev = dev_get_by_index(net, vifc->mif6c_pifi); if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); if (err) { dev_put(dev); return err; } break; default: return -EINVAL; } in6_dev = __in6_dev_get(dev); if (in6_dev) { atomic_inc(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); } /* Fill in the VIF structures */ vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0), MIFF_REGISTER); /* And finish update writing critical data */ spin_lock(&mrt_lock); rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); #endif if (vifi + 1 > mrt->maxvif) WRITE_ONCE(mrt->maxvif, vifi + 1); spin_unlock(&mrt_lock); call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, dev, vifi, mrt->id); return 0; } static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = *origin, .mf6c_mcastgrp = *mcastgrp, }; return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt, struct in6_addr *mcastgrp, mifi_t mifi) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = in6addr_any, .mf6c_mcastgrp = *mcastgrp, }; if (ipv6_addr_any(mcastgrp)) return mr_mfc_find_any_parent(mrt, mifi); return mr_mfc_find_any(mrt, mifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ static struct mfc6_cache * ip6mr_cache_find_parent(struct mr_table *mrt, const struct in6_addr *origin, const struct in6_addr *mcastgrp, int parent) { struct mfc6_cache_cmp_arg arg = { .mf6c_origin = *origin, .mf6c_mcastgrp = *mcastgrp, }; return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ static struct mfc6_cache *ip6mr_cache_alloc(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (!c) return NULL; c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXMIFS; c->_c.free = ip6mr_cache_free_rcu; refcount_set(&c->_c.mfc_un.res.refcount, 1); return c; } static struct mfc6_cache *ip6mr_cache_alloc_unres(void) { struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (!c) return NULL; skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; return c; } /* * A cache entry has gone into a resolved state from queued */ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; /* * Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ipv6_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct ipv6hdr)); if (mr_fill_mroute(mrt, skb, &c->_c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE; } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { rcu_read_lock(); ip6_mr_forward(net, mrt, skb->dev, skb, c); rcu_read_unlock(); } } } /* * Bounce a cache query up to pim6sd and netlink. * * Called under rcu_read_lock() */ static int ip6mr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert) { struct sock *mroute6_sk; struct sk_buff *skb; struct mrt6msg *msg; int ret; #ifdef CONFIG_IPV6_PIMSM_V2 if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt) +sizeof(*msg)); else #endif skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC); if (!skb) return -ENOBUFS; /* I suppose that internal messages * do not require checksums */ skb->ip_summed = CHECKSUM_UNNECESSARY; #ifdef CONFIG_IPV6_PIMSM_V2 if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) { /* Ugly, but we have no choice with this interface. Duplicate old header, fix length etc. And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = assert; if (assert == MRT6MSG_WRMIFWHOLE) msg->im6_mif = mifi; else msg->im6_mif = READ_ONCE(mrt->mroute_reg_vif_num); msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; skb->ip_summed = CHECKSUM_UNNECESSARY; } else #endif { /* * Copy the IP header */ skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr)); /* * Add our header */ skb_put(skb, sizeof(*msg)); skb_reset_transport_header(skb); msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = assert; msg->im6_mif = mifi; msg->im6_pad = 0; msg->im6_src = ipv6_hdr(pkt)->saddr; msg->im6_dst = ipv6_hdr(pkt)->daddr; skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; } mroute6_sk = rcu_dereference(mrt->mroute_sk); if (!mroute6_sk) { kfree_skb(skb); return -EINVAL; } mrt6msg_netlink_event(mrt, skb); /* Deliver to user space multicast routing algorithms */ ret = sock_queue_rcv_skb(mroute6_sk, skb); if (ret < 0) { net_warn_ratelimited("mroute6: pending queue full, dropping entries\n"); kfree_skb(skb); } return ret; } /* Queue a packet for resolution. It gets locked cache entry! */ static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi, struct sk_buff *skb, struct net_device *dev) { struct mfc6_cache *c; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { found = true; break; } } if (!found) { /* * Create a new entry if allowable */ c = ip6mr_cache_alloc_unres(); if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); return -ENOBUFS; } /* Fill in the new cache entry */ c->_c.mfc_parent = -1; c->mf6c_origin = ipv6_hdr(skb)->saddr; c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; /* * Reflect first query at pim6sd */ err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); ip6mr_cache_free(c); kfree_skb(skb); return err; } atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); mr6_netlink_event(mrt, c, RTM_NEWROUTE); ipmr_do_expire_process(mrt); } /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { if (dev) { skb->dev = dev; skb->skb_iif = dev->ifindex; } skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } spin_unlock_bh(&mfc_unres_lock); return err; } /* * MFC6 cache manipulation by user space */ static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc, int parent) { struct mfc6_cache *c; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (!c) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params); list_del_rcu(&c->_c.list); call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_ENTRY_DEL, c, mrt->id); mr6_netlink_event(mrt, c, RTM_DELROUTE); mr_cache_put(&c->_c); return 0; } static int ip6mr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ip6mr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (rcu_access_pointer(v->dev) == dev) mif6_delete(mrt, ct, 1, NULL); } } return NOTIFY_DONE; } static unsigned int ip6mr_seq_read(const struct net *net) { return READ_ONCE(net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net); } static int ip6mr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, ip6mr_mr_table_iter, extack); } static struct notifier_block ip6_mr_notifier = { .notifier_call = ip6mr_device_event }; static const struct fib_notifier_ops ip6mr_notifier_ops_template = { .family = RTNL_FAMILY_IP6MR, .fib_seq_read = ip6mr_seq_read, .fib_dump = ip6mr_dump, .owner = THIS_MODULE, }; static int __net_init ip6mr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv6.ipmr_seq = 0; ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv6.ip6mr_notifier_ops = ops; return 0; } static void __net_exit ip6mr_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops); net->ipv6.ip6mr_notifier_ops = NULL; } /* Setup for IP multicast routing */ static int __net_init ip6mr_net_init(struct net *net) { int err; err = ip6mr_notifier_init(net); if (err) return err; err = ip6mr_rules_init(net); if (err < 0) goto ip6mr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; if (!proc_create_net("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_seq_ops, sizeof(struct mr_vif_iter))) goto proc_vif_fail; if (!proc_create_net("ip6_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: remove_proc_entry("ip6_mr_vif", net->proc_net); proc_vif_fail: rtnl_lock(); ip6mr_rules_exit(net); rtnl_unlock(); #endif ip6mr_rules_fail: ip6mr_notifier_exit(net); return err; } static void __net_exit ip6mr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ip6_mr_cache", net->proc_net); remove_proc_entry("ip6_mr_vif", net->proc_net); #endif ip6mr_notifier_exit(net); } static void __net_exit ip6mr_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ip6mr_rules_exit(net); rtnl_unlock(); } static struct pernet_operations ip6mr_net_ops = { .init = ip6mr_net_init, .exit = ip6mr_net_exit, .exit_batch = ip6mr_net_exit_batch, }; static const struct rtnl_msg_handler ip6mr_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = RTNL_FAMILY_IP6MR, .msgtype = RTM_GETROUTE, .doit = ip6mr_rtm_getroute, .dumpit = ip6mr_rtm_dumproute}, }; int __init ip6_mr_init(void) { int err; mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); if (!mrt_cachep) return -ENOMEM; err = register_pernet_subsys(&ip6mr_net_ops); if (err) goto reg_pernet_fail; err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; #ifdef CONFIG_IPV6_PIMSM_V2 if (inet6_add_protocol(&pim6_protocol, IPPROTO_PIM) < 0) { pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } #endif err = rtnl_register_many(ip6mr_rtnl_msg_handlers); if (!err) return 0; #ifdef CONFIG_IPV6_PIMSM_V2 inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); add_proto_fail: unregister_netdevice_notifier(&ip6_mr_notifier); #endif reg_notif_fail: unregister_pernet_subsys(&ip6mr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } void __init ip6_mr_cleanup(void) { rtnl_unregister_many(ip6mr_rtnl_msg_handlers); #ifdef CONFIG_IPV6_PIMSM_V2 inet6_del_protocol(&pim6_protocol, IPPROTO_PIM); #endif unregister_netdevice_notifier(&ip6_mr_notifier); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt, struct mf6cctl *mfc, int mrtsock, int parent) { unsigned char ttls[MAXMIFS]; struct mfc6_cache *uc, *c; struct mr_mfc *_uc; bool found; int i, err; if (mfc->mf6cc_parent >= MAXMIFS) return -ENFILE; memset(ttls, 255, MAXMIFS); for (i = 0; i < MAXMIFS; i++) { if (IF_ISSET(i, &mfc->mf6cc_ifset)) ttls[i] = 1; } /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr, &mfc->mf6cc_mcastgrp.sin6_addr, parent); rcu_read_unlock(); if (c) { spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; spin_unlock(&mrt_lock); call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; c = ip6mr_cache_alloc(); if (!c) return -ENOMEM; c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; c->_c.mfc_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(mrt, &c->_c, ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ip6mr_rht_params); if (err) { pr_err("ip6mr: rhtable insert error %d\n", err); ip6mr_cache_free(c); return err; } list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { uc = (struct mfc6_cache *)_uc; if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } if (list_empty(&mrt->mfc_unres_queue)) timer_delete(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mr6_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } /* * Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, int flags) { struct mr_mfc *c, *tmp; LIST_HEAD(list); int i; /* Shut down all active vif entries */ if (flags & (MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC)) { for (i = 0; i < mrt->maxvif; i++) { if (((mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS_STATIC)) || (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS))) continue; mif6_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); } /* Wipe the cache */ if (flags & (MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC)) { list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC_STATIC)) || (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC))) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), FIB_EVENT_ENTRY_DEL, (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } } if (flags & MRT6_FLUSH_MFC) { if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); } spin_unlock_bh(&mfc_unres_lock); } } } static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); spin_lock(&mrt_lock); if (rtnl_dereference(mrt->mroute_sk)) { err = -EADDRINUSE; } else { rcu_assign_pointer(mrt->mroute_sk, sk); sock_set_flag(sk, SOCK_RCU_FREE); atomic_inc(&net->ipv6.devconf_all->mc_forwarding); } spin_unlock(&mrt_lock); if (!err) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); rtnl_unlock(); return err; } int ip6mr_sk_done(struct sock *sk) { struct net *net = sock_net(sk); struct ipv6_devconf *devconf; struct mr_table *mrt; int err = -EACCES; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return err; devconf = net->ipv6.devconf_all; if (!devconf || !atomic_read(&devconf->mc_forwarding)) return err; rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { spin_lock(&mrt_lock); RCU_INIT_POINTER(mrt->mroute_sk, NULL); /* Note that mroute_sk had SOCK_RCU_FREE set, * so the RCU grace period before sk freeing * is guaranteed by sk_destruct() */ atomic_dec(&devconf->mc_forwarding); spin_unlock(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MFC); err = 0; break; } } rtnl_unlock(); return err; } bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_oif = skb->dev->ifindex, .flowi6_mark = skb->mark, }; if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) return NULL; return rcu_access_pointer(mrt->mroute_sk); } EXPORT_SYMBOL(mroute6_is_socket); /* * Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately * that's how BSD mrouted happens to think. Maybe one day with a proper * MOSPF/PIM router set up we can clean this up. */ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { int ret, parent = 0; struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; if (optname != MRT6_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EACCES; } switch (optname) { case MRT6_INIT: if (optlen < sizeof(int)) return -EINVAL; return ip6mr_sk_init(mrt, sk); case MRT6_DONE: return ip6mr_sk_done(sk); case MRT6_ADD_MIF: if (optlen < sizeof(vif)) return -EINVAL; if (copy_from_sockptr(&vif, optval, sizeof(vif))) return -EFAULT; if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); ret = mif6_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; case MRT6_DEL_MIF: if (optlen < sizeof(mifi_t)) return -EINVAL; if (copy_from_sockptr(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); ret = mif6_delete(mrt, mifi, 0, NULL); rtnl_unlock(); return ret; /* * Manipulate the forwarding caches. These live * in a sort of kernel/user symbiosis. */ case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; fallthrough; case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) return -EFAULT; if (parent == 0) parent = mfc.mf6cc_parent; rtnl_lock(); if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) ret = ip6mr_mfc_delete(mrt, &mfc, parent); else ret = ip6mr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); rtnl_unlock(); return ret; case MRT6_FLUSH: { int flags; if (optlen != sizeof(flags)) return -EINVAL; if (copy_from_sockptr(&flags, optval, sizeof(flags))) return -EFAULT; rtnl_lock(); mroute_clean_tables(mrt, flags); rtnl_unlock(); return 0; } /* * Control PIM assert (to activate pim will activate assert) */ case MRT6_ASSERT: { int v; if (optlen != sizeof(v)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; mrt->mroute_do_assert = v; return 0; } #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { bool do_wrmifwhole; int v; if (optlen != sizeof(v)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; do_wrmifwhole = (v == MRT6MSG_WRMIFWHOLE); v = !!v; rtnl_lock(); ret = 0; if (v != mrt->mroute_do_pim) { mrt->mroute_do_pim = v; mrt->mroute_do_assert = v; mrt->mroute_do_wrvifwhole = do_wrmifwhole; } rtnl_unlock(); return ret; } #endif #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES case MRT6_TABLE: { u32 v; if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&v, optval, sizeof(v))) return -EFAULT; /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (v != RT_TABLE_DEFAULT && v >= 100000000) return -EINVAL; if (sk == rcu_access_pointer(mrt->mroute_sk)) return -EBUSY; rtnl_lock(); ret = 0; mrt = ip6mr_new_table(net, v); if (IS_ERR(mrt)) ret = PTR_ERR(mrt); else raw6_sk(sk)->ip6mr_table = v; rtnl_unlock(); return ret; } #endif /* * Spurious command, or MRT6_VERSION which you cannot * set. */ default: return -ENOPROTOOPT; } } /* * Getsock opt support for the multicast routing system. */ int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) { int olr; int val; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (optname) { case MRT6_VERSION: val = 0x0305; break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: val = mrt->mroute_do_pim; break; #endif case MRT6_ASSERT: val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; } if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; olr = min_t(int, olr, sizeof(int)); if (olr < 0) return -EINVAL; if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } /* * The IP multicast ioctl support routines. */ int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) { struct sioc_sg_req6 *sr; struct sioc_mif_req6 *vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: vr = (struct sioc_mif_req6 *)arg; if (vr->mifi >= mrt->maxvif) return -EINVAL; vr->mifi = array_index_nospec(vr->mifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr->mifi]; if (VIF_EXISTS(mrt, vr->mifi)) { vr->icount = READ_ONCE(vif->pkt_in); vr->ocount = READ_ONCE(vif->pkt_out); vr->ibytes = READ_ONCE(vif->bytes_in); vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: sr = (struct sioc_sg_req6 *)arg; rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr->src.sin6_addr, &sr->grp.sin6_addr); if (c) { sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT struct compat_sioc_sg_req6 { struct sockaddr_in6 src; struct sockaddr_in6 grp; compat_ulong_t pktcnt; compat_ulong_t bytecnt; compat_ulong_t wrong_if; }; struct compat_sioc_mif_req6 { mifi_t mifi; compat_ulong_t icount; compat_ulong_t ocount; compat_ulong_t ibytes; compat_ulong_t obytes; }; int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req6 sr; struct compat_sioc_mif_req6 vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; if (vr.mifi >= mrt->maxvif) return -EINVAL; vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr.mifi]; if (VIF_EXISTS(mrt, vr.mifi)) { vr.icount = READ_ONCE(vif->pkt_in); vr.ocount = READ_ONCE(vif->pkt_out); vr.ibytes = READ_ONCE(vif->bytes_in); vr.obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #endif static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); return dst_output(net, sk, skb); } /* * Processing handlers for ip6mr_forward */ static int ip6mr_prepare_xmit(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; struct ipv6hdr *ipv6h; struct dst_entry *dst; struct flowi6 fl6; vif_dev = vif_dev_read(vif); if (!vif_dev) return -1; #ifdef CONFIG_IPV6_PIMSM_V2 if (vif->flags & MIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); return -1; } #endif ipv6h = ipv6_hdr(skb); fl6 = (struct flowi6) { .flowi6_oif = vif->link, .daddr = ipv6h->daddr, }; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); return -1; } skb_dst_drop(skb); skb_dst_set(skb, dst); /* * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface * program is joined. * If we will not make it, the program will have to join on all * interfaces. On the other hand, multihoming host (or router, but * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ skb->dev = vif_dev; WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); /* We are about to write */ /* XXX: extension headers? */ if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(vif_dev))) return -1; ipv6h = ipv6_hdr(skb); ipv6h->hop_limit--; return 0; } static void ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { struct net_device *indev = skb->dev; if (ip6mr_prepare_xmit(net, mrt, skb, vifi)) goto out_free; IP6CB(skb)->flags |= IP6SKB_FORWARDED; NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, indev, skb->dev, ip6mr_forward2_finish); return; out_free: kfree_skb(skb); } static void ip6mr_output2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { if (ip6mr_prepare_xmit(net, mrt, skb, vifi)) goto out_free; ip6_output(net, NULL, skb); return; out_free: kfree_skb(skb); } /* Called with rcu_read_lock() */ static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev) { int ct; /* Pairs with WRITE_ONCE() in mif6_delete()/mif6_add() */ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } /* Called under rcu_read_lock() */ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *c) { int psend = -1; int vif, ct; int true_vifi = ip6mr_find_vif(mrt, dev); vif = c->_c.mfc_parent; atomic_long_inc(&c->_c.mfc_un.res.pkt); atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, c->_c.mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); if (mrt->mroute_do_wrvifwhole) ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRMIFWHOLE); } goto dont_forward; } forward: WRITE_ONCE(mrt->vif_table[vif].pkt_in, mrt->vif_table[vif].pkt_in + 1); WRITE_ONCE(mrt->vif_table[vif].bytes_in, mrt->vif_table[vif].bytes_in + skb->len); /* * Forward the frame */ if (ipv6_addr_any(&c->mf6c_origin) && ipv6_addr_any(&c->mf6c_mcastgrp)) { if (true_vifi >= 0 && true_vifi != c->_c.mfc_parent && ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ if ((!ipv6_addr_any(&c->mf6c_origin) || ct != true_vifi) && ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ip6mr_forward2(net, mrt, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, psend); return; } dont_forward: kfree_skb(skb); } /* Called under rcu_read_lock() */ static void ip6_mr_output_finish(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc6_cache *c) { int psend = -1; int ct; WARN_ON_ONCE(!rcu_read_lock_held()); atomic_long_inc(&c->_c.mfc_un.res.pkt); atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); /* Forward the frame */ if (ipv6_addr_any(&c->mf6c_origin) && ipv6_addr_any(&c->mf6c_mcastgrp)) { if (ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { if (ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2; skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ip6mr_output2(net, mrt, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { ip6mr_output2(net, mrt, skb, psend); return; } dont_forward: kfree_skb(skb); } /* * Multicast packets for forwarding arrive here */ int ip6_mr_input(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct net *net = dev_net_rcu(dev); struct mfc6_cache *cache; struct mr_table *mrt; struct flowi6 fl6 = { .flowi6_iif = dev->ifindex, .flowi6_mark = skb->mark, }; int err; /* skb->dev passed in is the master dev for vrfs. * Get the proper interface that does have a vif associated with it. */ if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); return -ENODEV; } } err = ip6mr_fib_lookup(net, &fl6, &mrt); if (err < 0) { kfree_skb(skb); return err; } cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); if (!cache) { int vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &ipv6_hdr(skb)->daddr, vif); } /* * No usable cache entry */ if (!cache) { int vif; vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) { int err = ip6mr_cache_unresolved(mrt, vif, skb, dev); return err; } kfree_skb(skb); return -ENODEV; } ip6_mr_forward(net, mrt, dev, skb, cache); return 0; } int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct flowi6 fl6 = (struct flowi6) { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; struct mfc6_cache *cache; struct mr_table *mrt; int err; int vif; guard(rcu)(); if (IP6CB(skb)->flags & IP6SKB_FORWARDED) goto ip6_output; if (!(IP6CB(skb)->flags & IP6SKB_MCROUTE)) goto ip6_output; err = ip6mr_fib_lookup(net, &fl6, &mrt); if (err < 0) { kfree_skb(skb); return err; } cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); if (!cache) { vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &ipv6_hdr(skb)->daddr, vif); } /* No usable cache entry */ if (!cache) { vif = ip6mr_find_vif(mrt, dev); if (vif >= 0) return ip6mr_cache_unresolved(mrt, vif, skb, dev); goto ip6_output; } /* Wrong interface */ vif = cache->_c.mfc_parent; if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) goto ip6_output; ip6_mr_output_finish(net, mrt, dev, skb, cache); return 0; ip6_output: return ip6_output(net, sk, skb); } int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, u32 portid) { int err; struct mr_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); rcu_read_lock(); mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT); if (!mrt) { rcu_read_unlock(); return -ENOENT; } cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache && skb->dev) { int vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, vif); } if (!cache) { struct sk_buff *skb2; struct ipv6hdr *iph; struct net_device *dev; int vif; dev = skb->dev; if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) { rcu_read_unlock(); return -ENODEV; } /* really correct? */ skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb2) { rcu_read_unlock(); return -ENOMEM; } NETLINK_CB(skb2).portid = portid; skb_reset_transport_header(skb2); skb_put(skb2, sizeof(struct ipv6hdr)); skb_reset_network_header(skb2); iph = ipv6_hdr(skb2); iph->version = 0; iph->priority = 0; iph->flow_lbl[0] = 0; iph->flow_lbl[1] = 0; iph->flow_lbl[2] = 0; iph->payload_len = 0; iph->nexthdr = IPPROTO_NONE; iph->hop_limit = 0; iph->saddr = rt->rt6i_src.addr; iph->daddr = rt->rt6i_dst.addr; err = ip6mr_cache_unresolved(mrt, vif, skb2, dev); rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); rcu_read_unlock(); return err; } static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc6_cache *c, int cmd, int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = RTNL_FAMILY_IP6MR; rtm->rtm_dst_len = 128; rtm->rtm_src_len = 128; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) || nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp)) goto nla_put_failure; err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int _ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags) { return ip6mr_fill_mroute(mrt, skb, portid, seq, (struct mfc6_cache *)c, cmd, flags); } static int mr6_msgsize(bool unresolved, int maxvif) { size_t len = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(sizeof(struct in6_addr)) /* RTA_SRC */ + nla_total_size(sizeof(struct in6_addr)) /* RTA_DST */ ; if (!unresolved) len = len + nla_total_size(4) /* RTA_IIF */ + nla_total_size(0) /* RTA_MULTIPATH */ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) /* RTA_MFC_STATS */ + nla_total_size_64bit(sizeof(struct rta_mfc_stats)) ; return len; } static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mr6_msgsize(mfc->_c.mfc_parent >= MAXMIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE, NULL, GFP_ATOMIC); return; errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } static size_t mrt6msg_netlink_msgsize(size_t payloadlen) { size_t len = NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(1) /* IP6MRA_CREPORT_MSGTYPE */ + nla_total_size(4) /* IP6MRA_CREPORT_MIF_ID */ /* IP6MRA_CREPORT_SRC_ADDR */ + nla_total_size(sizeof(struct in6_addr)) /* IP6MRA_CREPORT_DST_ADDR */ + nla_total_size(sizeof(struct in6_addr)) /* IP6MRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; return len; } static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; struct rtgenmsg *rtgenm; struct mrt6msg *msg; struct sk_buff *skb; struct nlattr *nla; int payloadlen; payloadlen = pkt->len - sizeof(struct mrt6msg); msg = (struct mrt6msg *)skb_transport_header(pkt); skb = nlmsg_new(mrt6msg_netlink_msgsize(payloadlen), GFP_ATOMIC); if (!skb) goto errout; nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, sizeof(struct rtgenmsg), 0); if (!nlh) goto errout; rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IP6MR; if (nla_put_u8(skb, IP6MRA_CREPORT_MSGTYPE, msg->im6_msgtype) || nla_put_u32(skb, IP6MRA_CREPORT_MIF_ID, msg->im6_mif) || nla_put_in6_addr(skb, IP6MRA_CREPORT_SRC_ADDR, &msg->im6_src) || nla_put_in6_addr(skb, IP6MRA_CREPORT_DST_ADDR, &msg->im6_dst)) goto nla_put_failure; nla = nla_reserve(skb, IP6MRA_CREPORT_PKT, payloadlen); if (!nla || skb_copy_bits(pkt, sizeof(struct mrt6msg), nla_data(nla), payloadlen)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE_R, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_cancel(skb, nlh); errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS); } static const struct nla_policy ip6mr_getroute_policy[RTA_MAX + 1] = { [RTA_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [RTA_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [RTA_TABLE] = { .type = NLA_U32 }, }; static int ip6mr_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int err; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, ip6mr_getroute_policy, extack); if (err) return err; rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for multicast route get request"); return -EINVAL; } if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } return 0; } static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct in6_addr src = {}, grp = {}; struct nlattr *tb[RTA_MAX + 1]; struct mfc6_cache *cache; struct mr_table *mrt; struct sk_buff *skb; u32 tableid; int err; err = ip6mr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (tb[RTA_SRC]) src = nla_get_in6_addr(tb[RTA_SRC]); if (tb[RTA_DST]) grp = nla_get_in6_addr(tb[RTA_DST]); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = __ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT); if (!mrt) { NL_SET_ERR_MSG_MOD(extack, "MR table does not exist"); return -ENOENT; } /* entries are added/deleted only under RTNL */ rcu_read_lock(); cache = ip6mr_cache_find(mrt, &src, &grp); rcu_read_unlock(); if (!cache) { NL_SET_ERR_MSG_MOD(extack, "MR cache entry not found"); return -ENOENT; } skb = nlmsg_new(mr6_msgsize(false, mrt->maxvif), GFP_KERNEL); if (!skb) return -ENOBUFS; err = ip6mr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); if (err < 0) { kfree_skb(skb); return err; } return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct fib_dump_filter filter = { .rtnl_held = true, }; int err; if (cb->strict_check) { err = ip_valid_fib_dump_req(sock_net(skb->sk), nlh, &filter, cb); if (err < 0) return err; } if (filter.table_id) { struct mr_table *mrt; mrt = __ip6mr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR) return skb->len; NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist"); return -ENOENT; } err = mr_table_dump(mrt, skb, cb, _ip6mr_fill_mroute, &mfc_unres_lock, &filter); return skb->len ? : err; } return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter, _ip6mr_fill_mroute, &mfc_unres_lock, &filter); } |
| 5 5 | 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * * Copyright (c) 2002-2017 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/hrtimer.h> #include <linux/list.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/can.h> #include <net/sock.h> #include <net/net_namespace.h> /* * To send multiple CAN frame content within TX_SETUP or to filter * CAN messages with multiplex index within RX_SETUP, the number of * different filters is limited to 256 due to the one byte index value. */ #define MAX_NFRAMES 256 /* limit timers to 400 days for sending/timeouts */ #define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60) /* use of last_frames[index].flags */ #define RX_LOCAL 0x10 /* frame was created on the local host */ #define RX_OWN 0x20 /* frame was sent via the socket it was received on */ #define RX_RECV 0x40 /* received data for this element */ #define RX_THR 0x80 /* element not been sent due to throttle feature */ #define BCM_CAN_FLAGS_MASK 0x0F /* to clean private flags after usage */ /* get best masking value for can_rx_register() for a given single can_id */ #define REGMASK(id) ((id & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS("can-proto-2"); #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) /* * easy access to the first 64 bit of can(fd)_frame payload. cp->data is * 64 bit aligned so the offset has to be multiples of 8 which is ensured * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler(). */ static inline u64 get_u64(const struct canfd_frame *cp, int offset) { return *(u64 *)(cp->data + offset); } struct bcm_op { struct list_head list; struct rcu_head rcu; int ifindex; canid_t can_id; u32 flags; unsigned long frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; int cfsiz; u32 count; u32 nframes; u32 currframe; /* void pointers to arrays of struct can[fd]_frame */ void *frames; void *last_frames; struct canfd_frame sframe; struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ }; struct bcm_sock { struct sock sk; int bound; int ifindex; struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; struct proc_dir_entry *bcm_proc_read; char procname [32]; /* inode number in decimal with \0 */ }; static LIST_HEAD(bcm_notifier_list); static DEFINE_SPINLOCK(bcm_notifier_lock); static struct bcm_sock *bcm_busy_notifier; /* Return pointer to store the extra msg flags for bcm_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ static inline unsigned int *bcm_flags(struct sk_buff *skb) { /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); } static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; } static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv) { return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); } /* check limitations for timeval provided by user */ static bool bcm_is_invalid_tv(struct bcm_msg_head *msg_head) { if ((msg_head->ival1.tv_sec < 0) || (msg_head->ival1.tv_sec > BCM_TIMER_SEC_MAX) || (msg_head->ival1.tv_usec < 0) || (msg_head->ival1.tv_usec >= USEC_PER_SEC) || (msg_head->ival2.tv_sec < 0) || (msg_head->ival2.tv_sec > BCM_TIMER_SEC_MAX) || (msg_head->ival2.tv_usec < 0) || (msg_head->ival2.tv_usec >= USEC_PER_SEC)) return true; return false; } #define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU) #define OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) /* * procfs functions */ #if IS_ENABLED(CONFIG_PROC_FS) static char *bcm_proc_getifname(struct net *net, char *result, int ifindex) { struct net_device *dev; if (!ifindex) return "any"; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) strcpy(result, dev->name); else strcpy(result, "???"); rcu_read_unlock(); return result; } static int bcm_proc_show(struct seq_file *m, void *v) { char ifname[IFNAMSIZ]; struct net *net = m->private; struct sock *sk = (struct sock *)pde_data(m->file->f_inode); struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; seq_printf(m, ">>> socket %pK", sk->sk_socket); seq_printf(m, " / sk %pK", sk); seq_printf(m, " / bo %pK", bo); seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs); seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); rcu_read_lock(); list_for_each_entry_rcu(op, &bo->rx_ops, list) { unsigned long reduction; /* print only active entries & prevent division by zero */ if (!op->frames_abs) continue; seq_printf(m, "rx_op: %03X %-5s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); if (op->flags & CAN_FD_FRAME) seq_printf(m, "(%u)", op->nframes); else seq_printf(m, "[%u]", op->nframes); seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' '); if (op->kt_ival1) seq_printf(m, "timeo=%lld ", (long long)ktime_to_us(op->kt_ival1)); if (op->kt_ival2) seq_printf(m, "thr=%lld ", (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# recv %ld (%ld) => reduction: ", op->frames_filtered, op->frames_abs); reduction = 100 - (op->frames_filtered * 100) / op->frames_abs; seq_printf(m, "%s%ld%%\n", (reduction == 100) ? "near " : "", reduction); } list_for_each_entry(op, &bo->tx_ops, list) { seq_printf(m, "tx_op: %03X %s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); if (op->flags & CAN_FD_FRAME) seq_printf(m, "(%u) ", op->nframes); else seq_printf(m, "[%u] ", op->nframes); if (op->kt_ival1) seq_printf(m, "t1=%lld ", (long long)ktime_to_us(op->kt_ival1)); if (op->kt_ival2) seq_printf(m, "t2=%lld ", (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); rcu_read_unlock(); return 0; } #endif /* CONFIG_PROC_FS */ /* * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface * of the given bcm tx op */ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct can_skb_ext *csx; struct net_device *dev; struct canfd_frame *cf; int err; /* no target device? => exit */ if (!op->ifindex) return; /* read currframe under lock protection */ spin_lock_bh(&op->bcm_tx_lock); cf = op->frames + op->cfsiz * op->currframe; spin_unlock_bh(&op->bcm_tx_lock); dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ return; } skb = alloc_skb(op->cfsiz, gfp_any()); if (!skb) goto out; csx = can_skb_ext_add(skb); if (!csx) { kfree_skb(skb); goto out; } csx->can_iif = dev->ifindex; skb_put_data(skb, cf, op->cfsiz); /* send with loopback */ skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); /* update currframe and count under lock protection */ spin_lock_bh(&op->bcm_tx_lock); if (!err) op->frames_abs++; op->currframe++; /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; if (op->count > 0) op->count--; spin_unlock_bh(&op->bcm_tx_lock); out: dev_put(dev); } /* * bcm_send_to_user - send a BCM message to the userspace * (consisting of bcm_msg_head + x CAN frames) */ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, struct canfd_frame *frames, int has_timestamp) { struct sk_buff *skb; struct canfd_frame *firstframe; struct sockaddr_can *addr; struct sock *sk = op->sk; unsigned int datalen = head->nframes * op->cfsiz; int err; unsigned int *pflags; enum skb_drop_reason reason; skb = alloc_skb(sizeof(*head) + datalen, gfp_any()); if (!skb) return; skb_put_data(skb, head, sizeof(*head)); /* ensure space for sockaddr_can and msg flags */ sock_skb_cb_check_size(sizeof(struct sockaddr_can) + sizeof(unsigned int)); /* initialize msg flags */ pflags = bcm_flags(skb); *pflags = 0; if (head->nframes) { /* CAN frames starting here */ firstframe = (struct canfd_frame *)skb_tail_pointer(skb); skb_put_data(skb, frames, datalen); /* * the BCM uses the flags-element of the canfd_frame * structure for internal purposes. This is only * relevant for updates that are generated by the * BCM, where nframes is 1 */ if (head->nframes == 1) { if (firstframe->flags & RX_LOCAL) *pflags |= MSG_DONTROUTE; if (firstframe->flags & RX_OWN) *pflags |= MSG_CONFIRM; firstframe->flags &= BCM_CAN_FLAGS_MASK; } } if (has_timestamp) { /* restore rx timestamp */ skb->tstamp = op->rx_stamp; } /* * Put the datagram to the queue so that bcm_recvmsg() can * get it from there. We need to pass the interface index to * bcm_recvmsg(). We pass a whole struct sockaddr_can in skb->cb * containing the interface index. */ addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = op->rx_ifindex; err = sock_queue_rcv_skb_reason(sk, skb, &reason); if (err < 0) { struct bcm_sock *bo = bcm_sk(sk); sk_skb_reason_drop(sk, skb, reason); /* don't care about overflows in this statistic */ bo->dropped_usr_msgs++; } } static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { ktime_t ival; if (op->kt_ival1 && op->count) ival = op->kt_ival1; else if (op->kt_ival2) ival = op->kt_ival2; else return false; hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); return true; } static void bcm_tx_start_timer(struct bcm_op *op) { if (bcm_tx_set_expiry(op, &op->timer)) hrtimer_start_expires(&op->timer, HRTIMER_MODE_ABS_SOFT); } /* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { bcm_can_tx(op); if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; msg_head.ival1 = op->ival1; msg_head.ival2 = op->ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); } } else if (op->kt_ival2) { bcm_can_tx(op); } return bcm_tx_set_expiry(op, &op->timer) ? HRTIMER_RESTART : HRTIMER_NORESTART; } /* * bcm_rx_changed - create a RX_CHANGED notification due to changed content */ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) { struct bcm_msg_head head; /* update statistics */ op->frames_filtered++; /* prevent statistics overflow */ if (op->frames_filtered > ULONG_MAX/100) op->frames_filtered = op->frames_abs = 0; /* this element is not throttled anymore */ data->flags &= ~RX_THR; memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; head.ival1 = op->ival1; head.ival2 = op->ival2; head.can_id = op->can_id; head.nframes = 1; bcm_send_to_user(op, &head, data, 1); } /* * bcm_rx_update_and_send - process a detected relevant receive content change * 1. update the last received data * 2. send a notification to the user (if possible) */ static void bcm_rx_update_and_send(struct bcm_op *op, struct canfd_frame *lastdata, const struct canfd_frame *rxdata, unsigned char traffic_flags) { memcpy(lastdata, rxdata, op->cfsiz); /* mark as used and throttled by default */ lastdata->flags |= (RX_RECV|RX_THR); /* add own/local/remote traffic flags */ lastdata->flags |= traffic_flags; /* throttling mode inactive ? */ if (!op->kt_ival2) { /* send RX_CHANGED to the user immediately */ bcm_rx_changed(op, lastdata); return; } /* with active throttling timer we are just done here */ if (hrtimer_active(&op->thrtimer)) return; /* first reception with enabled throttling mode */ if (!op->kt_lastmsg) goto rx_changed_settime; /* got a second frame inside a potential throttle period? */ if (ktime_us_delta(ktime_get(), op->kt_lastmsg) < ktime_to_us(op->kt_ival2)) { /* do not send the saved data - only start throttle timer */ hrtimer_start(&op->thrtimer, ktime_add(op->kt_lastmsg, op->kt_ival2), HRTIMER_MODE_ABS_SOFT); return; } /* the gap was that big, that throttling was not needed here */ rx_changed_settime: bcm_rx_changed(op, lastdata); op->kt_lastmsg = ktime_get(); } /* * bcm_rx_cmp_to_index - (bit)compares the currently received data to formerly * received data stored in op->last_frames[] */ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, const struct canfd_frame *rxdata, unsigned char traffic_flags) { struct canfd_frame *cf = op->frames + op->cfsiz * index; struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; int i; /* * no one uses the MSBs of flags for comparison, * so we use it here to detect the first time of reception */ if (!(lcf->flags & RX_RECV)) { /* received data for the first time => send update to user */ bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } /* do a real check in CAN frame data section */ for (i = 0; i < rxdata->len; i += 8) { if ((get_u64(cf, i) & get_u64(rxdata, i)) != (get_u64(cf, i) & get_u64(lcf, i))) { bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } if (op->flags & RX_CHECK_DLC) { /* do a real check in CAN frame length */ if (rxdata->len != lcf->len) { bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } } /* * bcm_rx_starttimer - enable timeout monitoring for CAN frame reception */ static void bcm_rx_starttimer(struct bcm_op *op) { if (op->flags & RX_NO_AUTOTIMER) return; if (op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } /* bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out */ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; /* if user wants to be informed, when cyclic CAN-Messages come back */ if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { /* clear received CAN frames to indicate 'nothing received' */ memset(op->last_frames, 0, op->nframes * op->cfsiz); } /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; msg_head.ival1 = op->ival1; msg_head.ival2 = op->ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); return HRTIMER_NORESTART; } /* * bcm_rx_do_flush - helper for bcm_rx_thr_flush */ static inline int bcm_rx_do_flush(struct bcm_op *op, unsigned int index) { struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; if ((op->last_frames) && (lcf->flags & RX_THR)) { bcm_rx_changed(op, lcf); return 1; } return 0; } /* * bcm_rx_thr_flush - Check for throttled data and send it to the userspace */ static int bcm_rx_thr_flush(struct bcm_op *op) { int updated = 0; if (op->nframes > 1) { unsigned int i; /* for MUX filter we start at index 1 */ for (i = 1; i < op->nframes; i++) updated += bcm_rx_do_flush(op, i); } else { /* for RX_FILTER_ID and simple filter */ updated += bcm_rx_do_flush(op, 0); } return updated; } /* * bcm_rx_thr_handler - the time for blocked content updates is over now: * Check for throttled data and send it to the userspace */ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); if (bcm_rx_thr_flush(op)) { hrtimer_forward_now(hrtimer, op->kt_ival2); return HRTIMER_RESTART; } else { /* rearm throttle handling */ op->kt_lastmsg = 0; return HRTIMER_NORESTART; } } /* * bcm_rx_handler - handle a CAN frame reception */ static void bcm_rx_handler(struct sk_buff *skb, void *data) { struct bcm_op *op = (struct bcm_op *)data; const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data; unsigned int i; unsigned char traffic_flags; if (op->can_id != rxframe->can_id) return; /* make sure to handle the correct frame type (CAN / CAN FD) */ if (op->flags & CAN_FD_FRAME) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } /* disable timeout */ hrtimer_cancel(&op->timer); /* save rx timestamp */ op->rx_stamp = skb->tstamp; /* save originator for recvfrom() */ op->rx_ifindex = skb->dev->ifindex; /* update statistics */ op->frames_abs++; if (op->flags & RX_RTR_FRAME) { /* send reply for RTR-request (placed in op->frames[0]) */ bcm_can_tx(op); return; } /* compute flags to distinguish between own/local/remote CAN traffic */ traffic_flags = 0; if (skb->sk) { traffic_flags |= RX_LOCAL; if (skb->sk == op->sk) traffic_flags |= RX_OWN; } if (op->flags & RX_FILTER_ID) { /* the easiest case */ bcm_rx_update_and_send(op, op->last_frames, rxframe, traffic_flags); goto rx_starttimer; } if (op->nframes == 1) { /* simple compare with index 0 */ bcm_rx_cmp_to_index(op, 0, rxframe, traffic_flags); goto rx_starttimer; } if (op->nframes > 1) { /* * multiplex compare * * find the first multiplex mask that fits. * Remark: The MUX-mask is stored in index 0 - but only the * first 64 bits of the frame data[] are relevant (CAN FD) */ for (i = 1; i < op->nframes; i++) { if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) == (get_u64(op->frames, 0) & get_u64(op->frames + op->cfsiz * i, 0))) { bcm_rx_cmp_to_index(op, i, rxframe, traffic_flags); break; } } } rx_starttimer: bcm_rx_starttimer(op); } /* * helpers for bcm_op handling: find & delete bcm [rx|tx] op elements */ static struct bcm_op *bcm_find_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op; list_for_each_entry(op, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) return op; } return NULL; } static void bcm_free_op_rcu(struct rcu_head *rcu_head) { struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); if ((op->last_frames) && (op->last_frames != &op->last_sframe)) kfree(op->last_frames); kfree(op); } static void bcm_remove_op(struct bcm_op *op) { hrtimer_cancel(&op->timer); hrtimer_cancel(&op->thrtimer); call_rcu(&op->rcu, bcm_free_op_rcu); } static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) { if (op->rx_reg_dev == dev) { can_rx_unregister(dev_net(dev), dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); /* mark as removed subscription */ op->rx_reg_dev = NULL; } else printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device " "mismatch %p %p\n", op->rx_reg_dev, dev); } /* * bcm_delete_rx_op - find and remove a rx op (returns number of removed ops) */ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op, *n; list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { /* disable automatic timer on frame reception */ op->flags |= RX_NO_AUTOTIMER; /* * Don't care if we're bound or not (due to netdev * problems) can_rx_unregister() is always a save * thing to do here. */ if (op->ifindex) { /* * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() */ if (op->rx_reg_dev) { struct net_device *dev; dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (dev) { bcm_rx_unreg(dev, op); dev_put(dev); } } } else can_rx_unregister(sock_net(op->sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } } return 0; /* not found */ } /* * bcm_delete_tx_op - find and remove a tx op (returns number of removed ops) */ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op, *n; list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } } return 0; /* not found */ } /* * bcm_read_op - read out a bcm_op and send it to the user (for bcm_sendmsg) */ static int bcm_read_op(struct list_head *ops, struct bcm_msg_head *msg_head, int ifindex) { struct bcm_op *op = bcm_find_op(ops, msg_head, ifindex); if (!op) return -EINVAL; /* put current values into msg_head */ msg_head->flags = op->flags; msg_head->count = op->count; msg_head->ival1 = op->ival1; msg_head->ival2 = op->ival2; msg_head->nframes = op->nframes; bcm_send_to_user(op, msg_head, op->frames, 0); return MHSIZ; } /* * bcm_tx_setup - create or update a bcm tx op (for bcm_sendmsg) */ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, int ifindex, struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; struct canfd_frame *cf; unsigned int i; int err; /* we need a real device to send frames */ if (!ifindex) return -ENODEV; /* check nframes boundaries - we need at least one CAN frame */ if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES) return -EINVAL; /* check timeval limitations */ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) return -EINVAL; /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { /* update existing BCM operation */ /* * Do we need more space for the CAN frames than currently * allocated? -> This is a _really_ unusual use-case and * therefore (complexity / locking) it is not supported. */ if (msg_head->nframes > op->nframes) return -E2BIG; /* update CAN frames content */ for (i = 0; i < msg_head->nframes; i++) { cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) err = -EINVAL; } else { if (cf->len > 8) err = -EINVAL; } if (err < 0) return err; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } op->flags = msg_head->flags; /* only lock for unlikely count/nframes/currframe changes */ if (op->nframes != msg_head->nframes || op->flags & TX_RESET_MULTI_IDX || op->flags & SETTIMER) { spin_lock_bh(&op->bcm_tx_lock); if (op->nframes != msg_head->nframes || op->flags & TX_RESET_MULTI_IDX) { /* potentially update changed nframes */ op->nframes = msg_head->nframes; /* restart multiple frame transmission */ op->currframe = 0; } if (op->flags & SETTIMER) op->count = msg_head->count; spin_unlock_bh(&op->bcm_tx_lock); } } else { /* insert new BCM operation for the given can_id */ op = kzalloc(OPSIZ, GFP_KERNEL); if (!op) return -ENOMEM; spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; op->nframes = msg_head->nframes; if (op->flags & SETTIMER) op->count = msg_head->count; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { op->frames = kmalloc_array(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->frames) { kfree(op); return -ENOMEM; } } else op->frames = &op->sframe; for (i = 0; i < msg_head->nframes; i++) { cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); if (err < 0) goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) err = -EINVAL; } else { if (cf->len > 8) err = -EINVAL; } if (err < 0) goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } /* tx_ops never compare with previous received messages */ op->last_frames = NULL; /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ hrtimer_setup(&op->timer, bcm_tx_timeout_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); /* currently unused in tx_ops */ hrtimer_setup(&op->thrtimer, hrtimer_dummy_timeout, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); /* add this bcm_op to the list of the tx_ops */ list_add(&op->list, &bo->tx_ops); } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ if (op->flags & SETTIMER) { /* set timer values */ op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero values? */ if (!op->kt_ival1 && !op->kt_ival2) hrtimer_cancel(&op->timer); } if (op->flags & STARTTIMER) { hrtimer_cancel(&op->timer); /* spec: send CAN frame when starting timer */ op->flags |= TX_ANNOUNCE; } if (op->flags & TX_ANNOUNCE) bcm_can_tx(op); if (op->flags & STARTTIMER) bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; free_op: if (op->frames != &op->sframe) kfree(op->frames); kfree(op); return err; } /* * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg) */ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, int ifindex, struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; int do_rx_register; int err = 0; if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) { /* be robust against wrong usage ... */ msg_head->flags |= RX_FILTER_ID; /* ignore trailing garbage */ msg_head->nframes = 0; } /* the first element contains the mux-mask => MAX_NFRAMES + 1 */ if (msg_head->nframes > MAX_NFRAMES + 1) return -EINVAL; if ((msg_head->flags & RX_RTR_FRAME) && ((msg_head->nframes != 1) || (!(msg_head->can_id & CAN_RTR_FLAG)))) return -EINVAL; /* check timeval limitations */ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) return -EINVAL; /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { /* update existing BCM operation */ /* * Do we need more space for the CAN frames than currently * allocated? -> This is a _really_ unusual use-case and * therefore (complexity / locking) it is not supported. */ if (msg_head->nframes > op->nframes) return -E2BIG; if (msg_head->nframes) { /* update CAN frames content */ err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) return err; /* clear last_frames to indicate 'nothing received' */ memset(op->last_frames, 0, msg_head->nframes * op->cfsiz); } op->nframes = msg_head->nframes; op->flags = msg_head->flags; /* Only an update -> do not call can_rx_register() */ do_rx_register = 0; } else { /* insert new BCM operation for the given can_id */ op = kzalloc(OPSIZ, GFP_KERNEL); if (!op) return -ENOMEM; spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; if (msg_head->nframes > 1) { /* create array for CAN frames and copy the data */ op->frames = kmalloc_array(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->frames) { kfree(op); return -ENOMEM; } /* create and init array for received CAN frames */ op->last_frames = kcalloc(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->last_frames) { kfree(op->frames); kfree(op); return -ENOMEM; } } else { op->frames = &op->sframe; op->last_frames = &op->last_sframe; } if (msg_head->nframes) { err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) { if (op->frames != &op->sframe) kfree(op->frames); if (op->last_frames != &op->last_sframe) kfree(op->last_frames); kfree(op); return err; } } /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; op->ifindex = ifindex; /* ifindex for timeout events w/o previous frame reception */ op->rx_ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ hrtimer_setup(&op->timer, bcm_rx_timeout_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); hrtimer_setup(&op->thrtimer, bcm_rx_thr_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); /* add this bcm_op to the list of the rx_ops */ list_add(&op->list, &bo->rx_ops); /* call can_rx_register() */ do_rx_register = 1; } /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */ /* check flags */ if (op->flags & RX_RTR_FRAME) { struct canfd_frame *frame0 = op->frames; /* no timers in RTR-mode */ hrtimer_cancel(&op->thrtimer); hrtimer_cancel(&op->timer); /* * funny feature in RX(!)_SETUP only for RTR-mode: * copy can_id into frame BUT without RTR-flag to * prevent a full-load-loopback-test ... ;-] */ if ((op->flags & TX_CP_CAN_ID) || (frame0->can_id == op->can_id)) frame0->can_id = op->can_id & ~CAN_RTR_FLAG; } else { if (op->flags & SETTIMER) { /* set timer value */ op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero value? */ if (!op->kt_ival1) hrtimer_cancel(&op->timer); /* * In any case cancel the throttle timer, flush * potentially blocked msgs and reset throttle handling */ op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); bcm_rx_thr_flush(op); } if ((op->flags & STARTTIMER) && op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } /* now we can register for can_ids, if we added a new bcm_op */ if (do_rx_register) { if (ifindex) { struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); if (dev) { err = can_rx_register(sock_net(sk), dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); op->rx_reg_dev = dev; dev_put(dev); } } else err = can_rx_register(sock_net(sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ list_del_rcu(&op->list); bcm_remove_op(op); return err; } } return msg_head->nframes * op->cfsiz + MHSIZ; } /* * bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg) */ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk, int cfsiz) { struct sk_buff *skb; struct can_skb_ext *csx; struct net_device *dev; int err; /* we need a real device to send frames */ if (!ifindex) return -ENODEV; skb = alloc_skb(cfsiz, GFP_KERNEL); if (!skb) return -ENOMEM; csx = can_skb_ext_add(skb); if (!csx) { kfree_skb(skb); return -ENOMEM; } err = memcpy_from_msg(skb_put(skb, cfsiz), msg, cfsiz); if (err < 0) { kfree_skb(skb); return err; } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) { kfree_skb(skb); return -ENODEV; } csx->can_iif = dev->ifindex; skb->dev = dev; can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ dev_put(dev); if (err) return err; return cfsiz + MHSIZ; } /* * bcm_sendmsg - process BCM commands (opcodes) from the userspace */ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); int ifindex = bo->ifindex; /* default ifindex for this bcm_op */ struct bcm_msg_head msg_head; int cfsiz; int ret; /* read bytes or error codes as return value */ if (!bo->bound) return -ENOTCONN; /* check for valid message length from userspace */ if (size < MHSIZ) return -EINVAL; /* read message head information */ ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ); if (ret < 0) return ret; cfsiz = CFSIZ(msg_head.flags); if ((size - MHSIZ) % cfsiz) return -EINVAL; /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < BCM_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; /* ifindex from sendto() */ ifindex = addr->can_ifindex; if (ifindex) { struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENODEV; if (dev->type != ARPHRD_CAN) { dev_put(dev); return -ENODEV; } dev_put(dev); } } lock_sock(sk); switch (msg_head.opcode) { case TX_SETUP: ret = bcm_tx_setup(&msg_head, msg, ifindex, sk); break; case RX_SETUP: ret = bcm_rx_setup(&msg_head, msg, ifindex, sk); break; case TX_DELETE: if (bcm_delete_tx_op(&bo->tx_ops, &msg_head, ifindex)) ret = MHSIZ; else ret = -EINVAL; break; case RX_DELETE: if (bcm_delete_rx_op(&bo->rx_ops, &msg_head, ifindex)) ret = MHSIZ; else ret = -EINVAL; break; case TX_READ: /* reuse msg_head for the reply to TX_READ */ msg_head.opcode = TX_STATUS; ret = bcm_read_op(&bo->tx_ops, &msg_head, ifindex); break; case RX_READ: /* reuse msg_head for the reply to RX_READ */ msg_head.opcode = RX_STATUS; ret = bcm_read_op(&bo->rx_ops, &msg_head, ifindex); break; case TX_SEND: /* we need exactly one CAN frame behind the msg head */ if ((msg_head.nframes != 1) || (size != cfsiz + MHSIZ)) ret = -EINVAL; else ret = bcm_tx_send(msg, ifindex, sk, cfsiz); break; default: ret = -EINVAL; break; } release_sock(sk); return ret; } /* * notification handler for netdevice status changes */ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, struct net_device *dev) { struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove device specific receive entries */ list_for_each_entry(op, &bo->rx_ops, list) if (op->rx_reg_dev == dev) bcm_rx_unreg(dev, op); /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { #if IS_ENABLED(CONFIG_PROC_FS) if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) { remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir); bo->bcm_proc_read = NULL; } #endif bo->bound = 0; bo->ifindex = 0; notify_enodev = 1; } release_sock(sk); if (notify_enodev) { sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } break; case NETDEV_DOWN: if (bo->bound && bo->ifindex == dev->ifindex) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } } } static int bcm_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&bcm_notifier_lock); list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { spin_unlock(&bcm_notifier_lock); bcm_notify(bcm_busy_notifier, msg, dev); spin_lock(&bcm_notifier_lock); } bcm_busy_notifier = NULL; spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } /* * initial settings for all BCM sockets to be set at socket creation time */ static int bcm_init(struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); bo->bound = 0; bo->ifindex = 0; bo->dropped_usr_msgs = 0; bo->bcm_proc_read = NULL; INIT_LIST_HEAD(&bo->tx_ops); INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ spin_lock(&bcm_notifier_lock); list_add_tail(&bo->notifier, &bcm_notifier_list); spin_unlock(&bcm_notifier_lock); return 0; } /* * standard socket functions */ static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; struct net *net; struct bcm_sock *bo; struct bcm_op *op, *next; if (!sk) return 0; net = sock_net(sk); bo = bcm_sk(sk); /* remove bcm_ops, timer, rx_unregister(), etc. */ spin_lock(&bcm_notifier_lock); while (bcm_busy_notifier == bo) { spin_unlock(&bcm_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&bcm_notifier_lock); } list_del(&bo->notifier); spin_unlock(&bcm_notifier_lock); lock_sock(sk); #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) remove_proc_entry(bo->procname, net->can.bcmproc_dir); #endif /* CONFIG_PROC_FS */ list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); list_for_each_entry_safe(op, next, &bo->rx_ops, list) { /* * Don't care if we're bound or not (due to netdev problems) * can_rx_unregister() is always a save thing to do here. */ if (op->ifindex) { /* * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() */ if (op->rx_reg_dev) { struct net_device *dev; dev = dev_get_by_index(net, op->ifindex); if (dev) { bcm_rx_unreg(dev, op); dev_put(dev); } } } else can_rx_unregister(net, NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); } synchronize_rcu(); list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); /* remove device reference */ if (bo->bound) { bo->bound = 0; bo->ifindex = 0; } sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_prot_inuse_add(net, sk->sk_prot, -1); sock_put(sk); return 0; } static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int len, int flags) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); struct net *net = sock_net(sk); int ret = 0; if (len < BCM_MIN_NAMELEN) return -EINVAL; lock_sock(sk); if (bo->bound) { ret = -EISCONN; goto fail; } /* bind a device to this socket */ if (addr->can_ifindex) { struct net_device *dev; dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { ret = -ENODEV; goto fail; } if (dev->type != ARPHRD_CAN) { dev_put(dev); ret = -ENODEV; goto fail; } bo->ifindex = dev->ifindex; dev_put(dev); } else { /* no interface reference for ifindex = 0 ('any' CAN device) */ bo->ifindex = 0; } #if IS_ENABLED(CONFIG_PROC_FS) if (net->can.bcmproc_dir) { /* unique socket address as filename */ sprintf(bo->procname, "%lu", sock_i_ino(sk)); bo->bcm_proc_read = proc_create_net_single(bo->procname, 0644, net->can.bcmproc_dir, bcm_proc_show, sk); if (!bo->bcm_proc_read) { ret = -ENOMEM; goto fail; } } #endif /* CONFIG_PROC_FS */ bo->bound = 1; fail: release_sock(sk); return ret; } static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int error = 0; int err; skb = skb_recv_datagram(sk, flags, &error); if (!skb) return error; if (skb->len < size) size = skb->len; err = memcpy_to_msg(msg, skb->data, size); if (err < 0) { skb_free_datagram(sk, skb); return err; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(BCM_MIN_NAMELEN); msg->msg_namelen = BCM_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* assign the flags that have been recorded in bcm_send_to_user() */ msg->msg_flags |= *(bcm_flags(skb)); skb_free_datagram(sk, skb); return size; } static int bcm_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops bcm_ops = { .family = PF_CAN, .release = bcm_release, .bind = sock_no_bind, .connect = bcm_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = bcm_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = bcm_sendmsg, .recvmsg = bcm_recvmsg, .mmap = sock_no_mmap, }; static struct proto bcm_proto __read_mostly = { .name = "CAN_BCM", .owner = THIS_MODULE, .obj_size = sizeof(struct bcm_sock), .init = bcm_init, }; static const struct can_proto bcm_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_BCM, .ops = &bcm_ops, .prot = &bcm_proto, }; static int canbcm_pernet_init(struct net *net) { #if IS_ENABLED(CONFIG_PROC_FS) /* create /proc/net/can-bcm directory */ net->can.bcmproc_dir = proc_net_mkdir(net, "can-bcm", net->proc_net); #endif /* CONFIG_PROC_FS */ return 0; } static void canbcm_pernet_exit(struct net *net) { #if IS_ENABLED(CONFIG_PROC_FS) /* remove /proc/net/can-bcm directory */ if (net->can.bcmproc_dir) remove_proc_entry("can-bcm", net->proc_net); #endif /* CONFIG_PROC_FS */ } static struct pernet_operations canbcm_pernet_ops __read_mostly = { .init = canbcm_pernet_init, .exit = canbcm_pernet_exit, }; static struct notifier_block canbcm_notifier = { .notifier_call = bcm_notifier }; static int __init bcm_module_init(void) { int err; pr_info("can: broadcast manager protocol\n"); err = register_pernet_subsys(&canbcm_pernet_ops); if (err) return err; err = register_netdevice_notifier(&canbcm_notifier); if (err) goto register_notifier_failed; err = can_proto_register(&bcm_can_proto); if (err < 0) { printk(KERN_ERR "can: registration of bcm protocol failed\n"); goto register_proto_failed; } return 0; register_proto_failed: unregister_netdevice_notifier(&canbcm_notifier); register_notifier_failed: unregister_pernet_subsys(&canbcm_pernet_ops); return err; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } module_init(bcm_module_init); module_exit(bcm_module_exit); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLER__ static inline void cpu_relax(void) { asm volatile("yield" ::: "memory"); } #endif /* __ASSEMBLER__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 1272 | 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 | // 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); return PTR_ERR_OR_ZERO(dir); } 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); |
| 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Event handling for HSR and PRP devices. */ #include <linux/netdevice.h> #include <net/rtnetlink.h> #include <linux/rculist.h> #include <linux/timer.h> #include <linux/etherdevice.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_netlink.h" #include "hsr_framereg.h" #include "hsr_slave.h" static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port; hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; } static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, void *ptr) { struct hsr_port *port, *master; struct net_device *dev; struct hsr_priv *hsr; LIST_HEAD(list_kill); int mtu_max; int res; dev = netdev_notifier_info_to_dev(ptr); port = hsr_port_get_rtnl(dev); if (!port) { if (!is_hsr_master(dev)) return NOTIFY_DONE; /* Not an HSR device */ hsr = netdev_priv(dev); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (!port) { /* Resend of notification concerning removed device? */ return NOTIFY_DONE; } } else { hsr = port->hsr; } switch (event) { case NETDEV_UP: /* Administrative state DOWN */ case NETDEV_DOWN: /* Administrative state UP */ case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; case NETDEV_CHANGENAME: if (is_hsr_master(dev)) hsr_debugfs_rename(dev); break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no * ndo_set_mac_address() for HSR devices - i.e. not * supported. */ break; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port->type == HSR_PT_SLAVE_A) { eth_hw_addr_set(master->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, master->dev); if (hsr->prot_version == PRP_V1) { port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) { eth_hw_addr_set(port->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, port->dev); } } } /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : master->dev->dev_addr); if (res) netdev_warn(master->dev, "Could not update HSR node address.\n"); break; case NETDEV_CHANGEMTU: if (port->type == HSR_PT_MASTER) break; /* Handled in ndo_change_mtu() */ mtu_max = hsr_get_max_mtu(port->hsr); master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); WRITE_ONCE(master->dev->mtu, mtu_max); break; case NETDEV_UNREGISTER: if (!is_hsr_master(dev)) { master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); hsr_del_port(port); if (hsr_slave_empty(master->hsr)) { const struct rtnl_link_ops *ops; ops = master->dev->rtnl_link_ops; ops->dellink(master->dev, &list_kill); unregister_netdevice_many(&list_kill); } } break; case NETDEV_PRE_TYPE_CHANGE: /* HSR works only on Ethernet devices. Refuse slave to change * its type. */ return NOTIFY_BAD; } return NOTIFY_DONE; } struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port; hsr_for_each_port_rtnl(hsr, port) if (port->type == pt) return port; return NULL; } int hsr_get_version(struct net_device *dev, enum hsr_version *ver) { struct hsr_priv *hsr; hsr = netdev_priv(dev); *ver = hsr->prot_version; return 0; } EXPORT_SYMBOL(hsr_get_version); static struct notifier_block hsr_nb = { .notifier_call = hsr_netdev_notify, /* Slave event notifications */ }; static int __init hsr_init(void) { int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); err = register_netdevice_notifier(&hsr_nb); if (err) return err; err = hsr_netlink_init(); if (err) { unregister_netdevice_notifier(&hsr_nb); return err; } return 0; } static void __exit hsr_exit(void) { hsr_netlink_exit(); hsr_debugfs_remove_root(); unregister_netdevice_notifier(&hsr_nb); } module_init(hsr_init); module_exit(hsr_exit); MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver"); MODULE_LICENSE("GPL"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> extern struct file_system_type nullfs_fs_type; extern struct list_head notify_list; struct mnt_namespace { struct ns_common ns; struct mount * root; struct { struct rb_root mounts; /* Protected by namespace_sem */ struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ }; struct user_namespace *user_ns; struct ucounts *ucounts; wait_queue_head_t poll; u64 seq_origin; /* Sequence number of origin mount namespace */ u64 event; #ifdef CONFIG_FSNOTIFY __u32 n_fsnotify_mask; struct fsnotify_mark_connector __rcu *n_fsnotify_marks; #endif unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; refcount_t passive; /* number references not pinning @mounts */ bool is_anon; } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct mount *mnt_next_for_sb; /* the next two fields are hlist_node, */ struct mount * __aligned(1) *mnt_pprev_for_sb; /* except that LSB of pprev is stolen */ #define WRITE_HOLD 1 /* ... for use by mnt_hold_writers() */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct hlist_head mnt_slave_list;/* list of slave mounts */ struct hlist_node mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; struct list_head to_notify; /* need to queue notification */ struct mnt_namespace *prev_ns; /* previous namespace (NULL if none) */ #endif int mnt_t_flags; /* namespace_sem-protected flags */ int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; struct mount *overmount; /* mounted on ->mnt_root */ } __randomize_layout; enum { T_SHARED = 1, /* mount is shared */ T_UNBINDABLE = 2, /* mount is unbindable */ T_MARKED = 4, /* internal mark for propagate_... */ T_UMOUNT_CANDIDATE = 8, /* for propagate_umount */ /* * T_SHARED_MASK is the set of flags that should be cleared when a * mount becomes shared. Currently, this is only the flag that says a * mount cannot be bind mounted, since this is how we create a mount * that shares events with another mount. If you add a new T_* * flag, consider how it interacts with shared mounts. */ T_SHARED_MASK = T_UNBINDABLE, }; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(const struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { ns_ref_inc(ns); } extern seqlock_t mount_lock; DEFINE_LOCK_GUARD_0(mount_writer, write_seqlock(&mount_lock), write_sequnlock(&mount_lock)) DEFINE_LOCK_GUARD_0(mount_locked_reader, read_seqlock_excl(&mount_lock), read_sequnlock_excl(&mount_lock)) struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(const struct dentry *dentry); static inline bool is_local_mountpoint(const struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->is_anon; } static inline bool anon_ns_root(const struct mount *m) { struct mnt_namespace *ns = READ_ONCE(m->mnt_ns); return !IS_ERR_OR_NULL(ns) && is_anon_ns(ns) && m == ns->root; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline bool mnt_ns_empty(const struct mnt_namespace *ns) { return RB_EMPTY_ROOT(&ns->mounts); } static inline void move_from_ns(struct mount *mnt) { struct mnt_namespace *ns = mnt->mnt_ns; WARN_ON(!mnt_ns_attached(mnt)); if (ns->mnt_last_node == &mnt->mnt_node) ns->mnt_last_node = rb_prev(&mnt->mnt_node); if (ns->mnt_first_node == &mnt->mnt_node) ns->mnt_first_node = rb_next(&mnt->mnt_node); rb_erase(&mnt->mnt_node, &ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } #ifdef CONFIG_FSNOTIFY static inline void mnt_notify_add(struct mount *m) { /* Optimize the case where there are no watches */ if ((m->mnt_ns && m->mnt_ns->n_fsnotify_marks) || (m->prev_ns && m->prev_ns->n_fsnotify_marks)) list_add_tail(&m->to_notify, ¬ify_list); else m->prev_ns = m->mnt_ns; } #else static inline void mnt_notify_add(struct mount *m) { } #endif static inline struct mount *topmost_overmount(struct mount *m) { while (m->overmount) m = m->overmount; return m; } static inline bool __test_write_hold(struct mount * __aligned(1) *val) { return (unsigned long)val & WRITE_HOLD; } static inline bool test_write_hold(const struct mount *m) { return __test_write_hold(m->mnt_pprev_for_sb); } static inline void set_write_hold(struct mount *m) { m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb | WRITE_HOLD); } static inline void clear_write_hold(struct mount *m) { m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb & ~WRITE_HOLD); } struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry); |
| 12 12 12 12 12 12 12 12 12 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <linux/poison.h> #include <net/ipv6.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); void *ip6t_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ip6t, IP6T); } EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip6_packet_match(const struct sk_buff *skb, const char *indev, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); if (NF_INVF(ip6info, IP6T_INV_SRCIP, ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, &ip6info->src)) || NF_INVF(ip6info, IP6T_INV_DSTIP, ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, &ip6info->dst))) return false; ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0)) return false; /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ if (ip6info->flags & IP6T_F_PROTO) { int protohdr; unsigned short _frag_off; protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); if (protohdr < 0) { if (_frag_off == 0) *hotdrop = true; return false; } *fragoff = _frag_off; if (ip6info->proto == protohdr) { if (ip6info->invflags & IP6T_INV_PROTO) return false; return true; } /* We need match for the '-p all', too! */ if ((ip6info->proto != 0) && !(ip6info->invflags & IP6T_INV_PROTO)) return false; } return true; } /* should be ip6 safe */ static bool ip6_checkentry(const struct ip6t_ip6 *ipv6) { if (ipv6->flags & ~IP6T_F_MASK) return false; if (ipv6->invflags & ~IP6T_INV_MASK) return false; return true; } static unsigned int ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline struct ip6t_entry * get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; return e->target_offset == sizeof(struct ip6t_entry) && memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP6_TRACE_COMMENT_RULE, NF_IP6_TRACE_COMMENT_RETURN, NF_IP6_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP6_TRACE_COMMENT_RULE] = "rule", [NF_IP6_TRACE_COMMENT_RETURN] = "return", [NF_IP6_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = LOGLEVEL_WARNING, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] : comments[NF_IP6_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ip6t_entry *e) { const struct ip6t_entry *root; const char *hookname, *chainname, *comment; const struct ip6t_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP6_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * current->in_nf_duplicate; e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: e = ip6t_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ip6t_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ break; } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ip6t_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV6, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); } static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ip6t_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ip6t_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ip6t_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ip6t_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ip6t_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET6, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET6, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ip6t_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ip6t_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET6, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ip6t_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET6); #endif t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET6); #endif return ret; } static int get_entries(struct net *net, struct ip6t_get_entries __user *uptr, const int *len) { int ret; struct ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ip6t_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET6, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ip6t_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET6, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ip6t_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[]; }; static int compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ip6t_entry); *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ip6t_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ip6t_ip6 *ipv6, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ip6t_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ip6t_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ip6t_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ip6t_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ip6t_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ip6t_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ip6t_entry *iter0; struct ip6t_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET6); ret = xt_compat_init_offsets(AF_INET6, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. */ xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ip6t_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ip6t_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, int *len) { int ret; struct compat_ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET6); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET6); return ret; } #endif static int do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IP6T_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IP6T_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IP6T_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET6, rev.name, rev.revision, target, &ret), "ip6t_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ip6t_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ip6t_unregister_table(net, new_table); return ret; } void ip6t_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ip6t_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; static struct nf_sockopt_ops ip6t_sockopts = { .pf = PF_INET6, .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, .owner = THIS_MODULE, }; static int __net_init ip6_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV6); } static void __net_exit ip6_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV6); } static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, }; static int __init ip6_tables_init(void) { int ret; ret = register_pernet_subsys(&ip6_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); if (ret < 0) goto err4; return 0; err4: xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); err2: unregister_pernet_subsys(&ip6_tables_net_ops); err1: return ret; } static void __exit ip6_tables_fini(void) { nf_unregister_sockopt(&ip6t_sockopts); xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); unregister_pernet_subsys(&ip6_tables_net_ops); } EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); module_exit(ip6_tables_fini); |
| 1114 392 1252 1258 1259 1254 393 392 395 1114 1112 1114 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(rstat_base_lock); static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); /* * Determines whether a given css can participate in rstat. * css's that are cgroup::self use rstat for base stats. * Other css's associated with a subsystem use rstat only when * they define the ss->css_rstat_flush callback. */ static inline bool css_uses_rstat(struct cgroup_subsys_state *css) { return css_is_self(css) || css->ss->css_rstat_flush != NULL; } static struct css_rstat_cpu *css_rstat_cpu( struct cgroup_subsys_state *css, int cpu) { return per_cpu_ptr(css->rstat_cpu, cpu); } static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu( struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_base_cpu, cpu); } static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss) { if (ss) return &ss->rstat_ss_lock; return &rstat_base_lock; } static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) { if (ss) return per_cpu_ptr(ss->lhead, cpu); return per_cpu_ptr(&rstat_backlog_list, cpu); } /** * css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * * Atomically inserts the css in the ss's llist for the given cpu. This is * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist * will be processed at the flush time to create the update tree. * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a * memory barrier is needed before the call to css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling * css_rstat_updated(). */ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct llist_node *self; /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; lockdep_assert_preemption_disabled(); /* * For archs withnot nmi safe cmpxchg or percpu ops support, ignore * the requests from nmi context. */ if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) || !IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi()) return; rstatc = css_rstat_cpu(css, cpu); /* * If already on list return. This check is racy and smp_mb() is needed * to pair it with the smp_mb() in css_process_update_tree() if the * guarantee that the updated stats are visible to concurrent flusher is * needed. */ if (llist_on_list(&rstatc->lnode)) return; /* * This function can be renentered by irqs and nmis for the same cgroup * and may try to insert the same per-cpu lnode into the llist. Note * that llist_add() does not protect against such scenarios. In addition * this same per-cpu lnode can be modified through init_llist_node() * from css_rstat_flush() running on a different CPU. * * To protect against such stacked contexts of irqs/nmis, we use the * fact that lnode points to itself when not on a list and then use * try_cmpxchg() to atomically set to NULL to select the winner * which will call llist_add(). The losers can assume the insertion is * successful and the winner will eventually add the per-cpu lnode to * the llist. * * Please note that we can not use this_cpu_cmpxchg() here as on some * archs it is not safe against modifications from multiple CPUs. */ self = &rstatc->lnode; if (!try_cmpxchg(&rstatc->lnode.next, &self, NULL)) return; lhead = ss_lhead_cpu(css->ss, cpu); llist_add(&rstatc->lnode, lhead); } static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu) { /* put @css and all ancestors on the corresponding updated lists */ while (true) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); struct cgroup_subsys_state *parent = css->parent; struct css_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = css; break; } prstatc = css_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = css; css = parent; } } static void css_process_update_tree(struct cgroup_subsys *ss, int cpu) { struct llist_head *lhead = ss_lhead_cpu(ss, cpu); struct llist_node *lnode; while ((lnode = llist_del_first_init(lhead))) { struct css_rstat_cpu *rstatc; /* * smp_mb() is needed here (more specifically in between * init_llist_node() and per-cpu stats flushing) if the * guarantee is required by a rstat user where etiher the * updater should add itself on the lockless list or the * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before * css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add * smp_mb() here. */ rstatc = container_of(lnode, struct css_rstat_cpu, lnode); __css_process_update_tree(rstatc->owner, cpu); } } /** * css_rstat_push_children - push children css's into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of css's to be flushed * * Iteratively traverse down the css_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list via the rstat_flush_next pointer built from the * tail backward like "pushing" css's into a stack. The root is pushed by * the caller. */ static struct cgroup_subsys_state *css_rstat_push_children( struct cgroup_subsys_state *head, struct cgroup_subsys_state *child, int cpu) { struct cgroup_subsys_state *cnext = child; /* Next head of child css level */ struct cgroup_subsys_state *ghead = NULL; /* Head of grandchild css level */ struct cgroup_subsys_state *parent, *grandchild; struct css_rstat_cpu *crstatc; child->rstat_flush_next = NULL; /* * The subsystem rstat lock must be held for the whole duration from * here as the rstat_flush_next list is being constructed to when * it is consumed later in css_rstat_flush(). */ lockdep_assert_held(ss_rstat_lock(head->ss)); /* * Notation: -> updated_next pointer * => rstat_flush_next pointer * * Assuming the following sample updated_children lists: * P: C1 -> C2 -> P * C1: G11 -> G12 -> C1 * C2: G21 -> G22 -> C2 * * After 1st iteration: * head => C2 => C1 => NULL * ghead => G21 => G11 => NULL * * After 2nd iteration: * head => G12 => G11 => G22 => G21 => C2 => C1 => NULL */ next_level: while (cnext) { child = cnext; cnext = child->rstat_flush_next; parent = child->parent; /* updated_next is parent cgroup terminated if !NULL */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = css_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { cnext = ghead; ghead = NULL; goto next_level; } return head; } /** * css_rstat_updated_list - build a list of updated css's to be flushed * @root: root of the css subtree to traverse * @cpu: target cpu * Return: A singly linked list of css's to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned css is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child css's if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent css. An exception * here is the css root whose updated_next can be self terminated. */ static struct cgroup_subsys_state *css_rstat_updated_list( struct cgroup_subsys_state *root, int cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu); struct cgroup_subsys_state *head = NULL, *parent, *child; css_process_update_tree(root->ss, cpu); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) return NULL; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = root->parent; if (parent) { struct css_rstat_cpu *prstatc; struct cgroup_subsys_state **nextp; prstatc = css_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct css_rstat_cpu *nrstatc; nrstatc = css_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = css_rstat_push_children(head, child, cpu); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for css_rstat_updated() and * css_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __css_rstat_lock(struct cgroup_subsys_state *css, int cpu_in_loop) __acquires(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; bool contended; lock = ss_rstat_lock(css->ss); contended = !spin_trylock_irq(lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __css_rstat_unlock(struct cgroup_subsys_state *css, int cpu_in_loop) __releases(ss_rstat_lock(css->ss)) { struct cgroup *cgrp = css->cgroup; spinlock_t *lock; lock = ss_rstat_lock(css->ss); trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(lock); } /** * css_rstat_flush - flush stats in @css's rstat subtree * @css: target cgroup subsystem state * * Collect all per-cpu stats in @css's subtree into the global counters * and propagate them upwards. After this function returns, all rstat * nodes in the subtree have up-to-date ->stat. * * This also gets all rstat nodes in the subtree including @css off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css) { int cpu; bool is_self = css_is_self(css); /* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; might_sleep(); for_each_possible_cpu(cpu) { struct cgroup_subsys_state *pos; /* Reacquire for each CPU to avoid disabling IRQs too long */ __css_rstat_lock(css, cpu); pos = css_rstat_updated_list(css, cpu); for (; pos; pos = pos->rstat_flush_next) { if (is_self) { cgroup_base_stat_flush(pos->cgroup, cpu); bpf_rstat_flush(pos->cgroup, cgroup_parent(pos->cgroup), cpu); } else pos->ss->css_rstat_flush(pos, cpu); } __css_rstat_unlock(css, cpu); if (!cond_resched()) cpu_relax(); } } int css_rstat_init(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; int cpu; bool is_self = css_is_self(css); if (is_self) { /* the root cgrp has rstat_base_cpu preallocated */ if (!cgrp->rstat_base_cpu) { cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu); if (!cgrp->rstat_base_cpu) return -ENOMEM; } } else if (css->ss->css_rstat_flush == NULL) return 0; /* the root cgrp's self css has rstat_cpu preallocated */ if (!css->rstat_cpu) { css->rstat_cpu = alloc_percpu(struct css_rstat_cpu); if (!css->rstat_cpu) { if (is_self) free_percpu(cgrp->rstat_base_cpu); return -ENOMEM; } } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); rstatc->owner = rstatc->updated_children = css; init_llist_node(&rstatc->lnode); if (is_self) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); u64_stats_init(&rstatbc->bsync); } } return 0; } void css_rstat_exit(struct cgroup_subsys_state *css) { int cpu; if (!css_uses_rstat(css)) return; if (!css->rstat_cpu) return; css_rstat_flush(css); /* sanity check */ for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu); if (WARN_ON_ONCE(rstatc->updated_children != css) || WARN_ON_ONCE(rstatc->updated_next)) return; } if (css_is_self(css)) { struct cgroup *cgrp = css->cgroup; free_percpu(cgrp->rstat_base_cpu); cgrp->rstat_base_cpu = NULL; } free_percpu(css->rstat_cpu); css->rstat_cpu = NULL; } /** * ss_rstat_init - subsystem-specific rstat initialization * @ss: target subsystem * * If @ss is NULL, the static locks associated with the base stats * are initialized. If @ss is non-NULL, the subsystem-specific locks * are initialized. */ int __init ss_rstat_init(struct cgroup_subsys *ss) { int cpu; if (ss) { ss->lhead = alloc_percpu(struct llist_head); if (!ss->lhead) return -ENOMEM; } spin_lock_init(ss_rstat_lock(ss)); for_each_possible_cpu(cpu) init_llist_head(ss_lhead_cpu(ss, cpu)); return 0; } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_base_cpu *rstatbc = cgroup_rstat_base_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_base_cpu *prstatbc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatbc->bsync); delta = rstatbc->bstat; } while (__u64_stats_fetch_retry(&rstatbc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatbc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatbc->last_bstat, &delta); cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatbc->subtree_bstat; prstatbc = cgroup_rstat_base_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatbc->last_subtree_bstat); cgroup_base_stat_add(&prstatbc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatbc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_base_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_base_cpu *rstatbc; rstatbc = get_cpu_ptr(cgrp->rstat_base_cpu); *flags = u64_stats_update_begin_irqsave(&rstatbc->bsync); return rstatbc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_base_cpu *rstatbc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatbc->bsync, flags); css_rstat_updated(&cgrp->self, smp_processor_id()); put_cpu_ptr(rstatbc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatbc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_base_cpu *rstatbc; unsigned long flags; rstatbc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatbc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatbc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatbc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatbc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatbc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_base_stat bstat; if (cgroup_parent(cgrp)) { css_rstat_flush(&cgrp->self); __css_rstat_lock(&cgrp->self, -1); bstat = cgrp->bstat; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &bstat.cputime.utime, &bstat.cputime.stime); __css_rstat_unlock(&cgrp->self, -1); } else { root_cgroup_cputime(&bstat); } do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC); do_div(bstat.cputime.utime, NSEC_PER_USEC); do_div(bstat.cputime.stime, NSEC_PER_USEC); do_div(bstat.ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", bstat.cputime.sum_exec_runtime, bstat.cputime.utime, bstat.cputime.stime, bstat.ntime); cgroup_force_idle_show(seq, &bstat); } /* Add bpf kfuncs for css_rstat_updated() and css_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, css_rstat_updated) BTF_ID_FLAGS(func, css_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 41 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_copy(dst, src) __nodes_copy(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_copy(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_copy(dstp->bits, srcp->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min()s could be dropped. */ #define first_node(src) __first_node(&(src)) static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min(MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min(MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); if (ret == MAX_NUMNODES) ret = __first_node(srcp); return ret; } static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min(MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static __always_inline int node_state(int node, enum node_states state) { return node == 0; } static __always_inline void node_set_state(int node, enum node_states state) { } static __always_inline void node_clear_state(int node, enum node_states state) { } static __always_inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int node = find_random_bit(maskp->bits, MAX_NUMNODES); return node < MAX_NUMNODES ? node : NUMA_NO_NODE; #else return 0; #endif } #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) #define for_each_node_with_cpus(node) for_each_node_state(node, N_CPU) /* * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 13 13 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 IBM Corporation * * Author: * Mimi Zohar <zohar@us.ibm.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/fs.h> #include <linux/xattr.h> #include <linux/magic.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsverity.h> #include <keys/system_keyring.h> #include <uapi/linux/fsverity.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM static char *ima_appraise_cmdline_default __initdata; core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0); void __init ima_appraise_parse_cmdline(void) { const char *str = ima_appraise_cmdline_default; bool sb_state = arch_ima_get_secureboot(); int appraisal_state = ima_appraise; if (!str) return; if (strncmp(str, "off", 3) == 0) appraisal_state = 0; else if (strncmp(str, "log", 3) == 0) appraisal_state = IMA_APPRAISE_LOG; else if (strncmp(str, "fix", 3) == 0) appraisal_state = IMA_APPRAISE_FIX; else if (strncmp(str, "enforce", 7) == 0) appraisal_state = IMA_APPRAISE_ENFORCE; else pr_err("invalid \"%s\" appraise option", str); /* If appraisal state was changed, but secure boot is enabled, * keep its default */ if (sb_state) { if (!(appraisal_state & IMA_APPRAISE_ENFORCE)) pr_info("Secure boot enabled: ignoring ima_appraise=%s option", str); } else { ima_appraise = appraisal_state; } } #endif /* * is_ima_appraise_enabled - return appraise status * * Only return enabled, if not in ima_appraise="fix" or "log" modes. */ bool is_ima_appraise_enabled(void) { return ima_appraise & IMA_APPRAISE_ENFORCE; } /* * ima_must_appraise - set appraise flag * * Return 1 to appraise or hash */ int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode, int mask, enum ima_hooks func) { struct lsm_prop prop; if (!ima_appraise) return 0; security_current_getlsmprop_subj(&prop); return ima_match_policy(idmap, inode, current_cred(), &prop, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); } static int ima_fix_xattr(struct dentry *dentry, struct ima_iint_cache *iint) { int rc, offset; u8 algo = iint->ima_hash->algo; if (algo <= HASH_ALGO_SHA1) { offset = 1; iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST; } else { offset = 0; iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG; iint->ima_hash->xattr.ng.algo = algo; } rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, &iint->ima_hash->xattr.data[offset], (sizeof(iint->ima_hash->xattr) - offset) + iint->ima_hash->length, 0); return rc; } /* Return specific func appraised cached result */ enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: return iint->ima_mmap_status; case BPRM_CHECK: return iint->ima_bprm_status; case CREDS_CHECK: return iint->ima_creds_status; case FILE_CHECK: case POST_SETATTR: return iint->ima_file_status; case MODULE_CHECK ... MAX_CHECK - 1: default: return iint->ima_read_status; } } static void ima_set_cache_status(struct ima_iint_cache *iint, enum ima_hooks func, enum integrity_status status) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->ima_mmap_status = status; break; case BPRM_CHECK: iint->ima_bprm_status = status; break; case CREDS_CHECK: iint->ima_creds_status = status; break; case FILE_CHECK: case POST_SETATTR: iint->ima_file_status = status; break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->ima_read_status = status; break; } } static void ima_cache_flags(struct ima_iint_cache *iint, enum ima_hooks func) { switch (func) { case MMAP_CHECK: case MMAP_CHECK_REQPROT: iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED); break; case BPRM_CHECK: iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED); break; case CREDS_CHECK: iint->flags |= (IMA_CREDS_APPRAISED | IMA_APPRAISED); break; case FILE_CHECK: case POST_SETATTR: iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED); break; case MODULE_CHECK ... MAX_CHECK - 1: default: iint->flags |= (IMA_READ_APPRAISED | IMA_APPRAISED); break; } } enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value, int xattr_len) { struct signature_v2_hdr *sig; enum hash_algo ret; if (!xattr_value || xattr_len < 2) /* return default hash algo */ return ima_hash_algo; switch (xattr_value->type) { case IMA_VERITY_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 3 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case EVM_IMA_XATTR_DIGSIG: sig = (typeof(sig))xattr_value; if (sig->version != 2 || xattr_len <= sizeof(*sig) || sig->hash_algo >= HASH_ALGO__LAST) return ima_hash_algo; return sig->hash_algo; case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ ret = xattr_value->data[0]; if (ret < HASH_ALGO__LAST) return ret; break; case IMA_XATTR_DIGEST: /* this is for backward compatibility */ if (xattr_len == 21) { unsigned int zero = 0; if (!memcmp(&xattr_value->data[16], &zero, 4)) return HASH_ALGO_MD5; else return HASH_ALGO_SHA1; } else if (xattr_len == 17) return HASH_ALGO_MD5; break; } /* return default hash algo */ return ima_hash_algo; } int ima_read_xattr(struct dentry *dentry, struct evm_ima_xattr_data **xattr_value, int xattr_len) { int ret; ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA, (char **)xattr_value, xattr_len, GFP_NOFS); if (ret == -EOPNOTSUPP) ret = 0; return ret; } /* * calc_file_id_hash - calculate the hash of the ima_file_id struct data * @type: xattr type [enum evm_ima_xattr_type] * @algo: hash algorithm [enum hash_algo] * @digest: pointer to the digest to be hashed * @hash: (out) pointer to the hash * * IMA signature version 3 disambiguates the data that is signed by * indirectly signing the hash of the ima_file_id structure data. * * Signing the ima_file_id struct is currently only supported for * IMA_VERITY_DIGSIG type xattrs. * * Return 0 on success, error code otherwise. */ static int calc_file_id_hash(enum evm_ima_xattr_type type, enum hash_algo algo, const u8 *digest, struct ima_digest_data *hash) { struct ima_file_id file_id = { .hash_type = IMA_VERITY_DIGSIG, .hash_algorithm = algo}; unsigned int unused = HASH_MAX_DIGESTSIZE - hash_digest_size[algo]; if (type != IMA_VERITY_DIGSIG) return -EINVAL; memcpy(file_id.hash, digest, hash_digest_size[algo]); hash->algo = algo; hash->length = hash_digest_size[algo]; return ima_calc_buffer_hash(&file_id, sizeof(file_id) - unused, hash); } /* * xattr_verify - verify xattr digest or signature * * Verify whether the hash or signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint, struct evm_ima_xattr_data *xattr_value, int xattr_len, enum integrity_status *status, const char **cause) { struct ima_max_digest_data hash; struct signature_v2_hdr *sig; int rc = -EINVAL, hash_start = 0; int mask; switch (xattr_value->type) { case IMA_XATTR_DIGEST_NG: /* first byte contains algorithm id */ hash_start = 1; fallthrough; case IMA_XATTR_DIGEST: if (*status != INTEGRITY_PASS_IMMUTABLE) { if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) *cause = "verity-signature-required"; else *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } clear_bit(IMA_DIGSIG, &iint->atomic_flags); } else { set_bit(IMA_DIGSIG, &iint->atomic_flags); } if (xattr_len - sizeof(xattr_value->type) - hash_start >= iint->ima_hash->length) /* * xattr length may be longer. md5 hash in previous * version occupied 20 bytes in xattr, instead of 16 */ rc = memcmp(&xattr_value->data[hash_start], iint->ima_hash->digest, iint->ima_hash->length); else rc = -EINVAL; if (rc) { *cause = "invalid-hash"; *status = INTEGRITY_FAIL; break; } *status = INTEGRITY_PASS; break; case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED; if ((iint->flags & mask) == mask) { *cause = "verity-signature-required"; *status = INTEGRITY_FAIL; break; } sig = (typeof(sig))xattr_value; if (sig->version >= 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { *status = INTEGRITY_UNKNOWN; break; } if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, (const char *)xattr_value, xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; case IMA_VERITY_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); if (iint->flags & IMA_DIGSIG_REQUIRED) { if (!(iint->flags & IMA_VERITY_REQUIRED)) { *cause = "IMA-signature-required"; *status = INTEGRITY_FAIL; break; } } sig = (typeof(sig))xattr_value; if (sig->version != 3) { *cause = "invalid-signature-version"; *status = INTEGRITY_FAIL; break; } rc = calc_file_id_hash(IMA_VERITY_DIGSIG, iint->ima_hash->algo, iint->ima_hash->digest, container_of(&hash.hdr, struct ima_digest_data, hdr)); if (rc) { *cause = "sigv3-hashing-error"; *status = INTEGRITY_FAIL; break; } rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, (const char *)xattr_value, xattr_len, hash.digest, hash.hdr.length); if (rc) { *cause = "invalid-verity-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } break; default: *status = INTEGRITY_UNKNOWN; *cause = "unknown-ima-data"; break; } return rc; } /* * modsig_verify - verify modsig signature * * Verify whether the signature matches the file contents. * * Return 0 on success, error code otherwise. */ static int modsig_verify(enum ima_hooks func, const struct modsig *modsig, enum integrity_status *status, const char **cause) { int rc; rc = integrity_modsig_verify(INTEGRITY_KEYRING_IMA, modsig); if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && func == KEXEC_KERNEL_CHECK) rc = integrity_modsig_verify(INTEGRITY_KEYRING_PLATFORM, modsig); if (rc) { *cause = "invalid-signature"; *status = INTEGRITY_FAIL; } else { *status = INTEGRITY_PASS; } return rc; } /* * ima_check_blacklist - determine if the binary is blacklisted. * * Add the hash of the blacklisted binary to the measurement list, based * on policy. * * Returns -EPERM if the hash is blacklisted. */ int ima_check_blacklist(struct ima_iint_cache *iint, const struct modsig *modsig, int pcr) { enum hash_algo hash_algo; const u8 *digest = NULL; u32 digestsize = 0; int rc = 0; if (!(iint->flags & IMA_CHECK_BLACKLIST)) return 0; if (iint->flags & IMA_MODSIG_ALLOWED && modsig) { ima_get_modsig_digest(modsig, &hash_algo, &digest, &digestsize); rc = is_binary_blacklisted(digest, digestsize); } else if (iint->flags & IMA_DIGSIG_REQUIRED && iint->ima_hash) rc = is_binary_blacklisted(iint->ima_hash->digest, iint->ima_hash->length); if ((rc == -EPERM) && (iint->flags & IMA_MEASURE)) process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize, "blacklisted-hash", NONE, pcr, NULL, false, NULL, 0); return rc; } /* * ima_appraise_measurement - appraise file measurement * * Call evm_verifyxattr() to verify the integrity of 'security.ima'. * Assuming success, compare the xattr hash with the collected measurement. * * Return 0 on success, error code otherwise */ int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint, struct file *file, const unsigned char *filename, struct evm_ima_xattr_data *xattr_value, int xattr_len, const struct modsig *modsig, bool bprm_is_check) { static const char op[] = "appraise_data"; int audit_msgno = AUDIT_INTEGRITY_DATA; const char *cause = "unknown"; struct dentry *dentry = file_dentry(file); struct inode *inode = d_backing_inode(dentry); enum integrity_status status = INTEGRITY_UNKNOWN; int rc = xattr_len; bool try_modsig = iint->flags & IMA_MODSIG_ALLOWED && modsig; /* If not appraising a modsig, we need an xattr. */ if (!(inode->i_opflags & IOP_XATTR) && !try_modsig) return INTEGRITY_UNKNOWN; /* * Unlike any of the other LSM hooks where the kernel enforces file * integrity, enforcing file integrity for the bprm_creds_for_exec() * LSM hook with the AT_EXECVE_CHECK flag is left up to the discretion * of the script interpreter(userspace). Differentiate kernel and * userspace enforced integrity audit messages. */ if (bprm_is_check) audit_msgno = AUDIT_INTEGRITY_USERSPACE; /* If reading the xattr failed and there's no modsig, error out. */ if (rc <= 0 && !try_modsig) { if (rc && rc != -ENODATA) goto out; if (iint->flags & IMA_DIGSIG_REQUIRED) { if (iint->flags & IMA_VERITY_REQUIRED) cause = "verity-signature-required"; else cause = "IMA-signature-required"; } else { cause = "missing-hash"; } status = INTEGRITY_NOLABEL; if (file->f_mode & FMODE_CREATED) iint->flags |= IMA_NEW_FILE; if ((iint->flags & IMA_NEW_FILE) && (!(iint->flags & IMA_DIGSIG_REQUIRED) || (inode->i_size == 0))) status = INTEGRITY_PASS; goto out; } status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc < 0 ? 0 : rc); switch (status) { case INTEGRITY_PASS: case INTEGRITY_PASS_IMMUTABLE: case INTEGRITY_UNKNOWN: break; case INTEGRITY_NOXATTRS: /* No EVM protected xattrs. */ /* It's fine not to have xattrs when using a modsig. */ if (try_modsig) break; fallthrough; case INTEGRITY_NOLABEL: /* No security.evm xattr. */ cause = "missing-HMAC"; goto out; case INTEGRITY_FAIL_IMMUTABLE: set_bit(IMA_DIGSIG, &iint->atomic_flags); cause = "invalid-fail-immutable"; goto out; case INTEGRITY_FAIL: /* Invalid HMAC/signature. */ cause = "invalid-HMAC"; goto out; default: WARN_ONCE(true, "Unexpected integrity status %d\n", status); } if (xattr_value) rc = xattr_verify(func, iint, xattr_value, xattr_len, &status, &cause); /* * If we have a modsig and either no imasig or the imasig's key isn't * known, then try verifying the modsig. */ if (try_modsig && (!xattr_value || xattr_value->type == IMA_XATTR_DIGEST_NG || rc == -ENOKEY)) rc = modsig_verify(func, modsig, &status, &cause); out: /* * File signatures on some filesystems can not be properly verified. * When such filesystems are mounted by an untrusted mounter or on a * system not willing to accept such a risk, fail the file signature * verification. */ if ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && ((inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) || (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) { status = INTEGRITY_FAIL; cause = "unverifiable-signature"; integrity_audit_msg(audit_msgno, inode, filename, op, cause, rc, 0); } else if (status != INTEGRITY_PASS) { /* Fix mode, but don't replace file signatures. */ if ((ima_appraise & IMA_APPRAISE_FIX) && !try_modsig && (!xattr_value || xattr_value->type != EVM_IMA_XATTR_DIGSIG)) { if (!ima_fix_xattr(dentry, iint)) status = INTEGRITY_PASS; } /* * Permit new files with file/EVM portable signatures, but * without data. */ if (inode->i_size == 0 && iint->flags & IMA_NEW_FILE && test_bit(IMA_DIGSIG, &iint->atomic_flags)) { status = INTEGRITY_PASS; } integrity_audit_msg(audit_msgno, inode, filename, op, cause, rc, 0); } else { ima_cache_flags(iint, func); } ima_set_cache_status(iint, func, status); return status; } /* * ima_update_xattr - update 'security.ima' hash value */ void ima_update_xattr(struct ima_iint_cache *iint, struct file *file) { struct dentry *dentry = file_dentry(file); int rc = 0; /* do not collect and update hash for digital signatures */ if (test_bit(IMA_DIGSIG, &iint->atomic_flags)) return; if ((iint->ima_file_status != INTEGRITY_PASS) && !(iint->flags & IMA_HASH)) return; rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) return; inode_lock(file_inode(file)); ima_fix_xattr(dentry, iint); inode_unlock(file_inode(file)); } /** * ima_inode_post_setattr - reflect file metadata changes * @idmap: idmap of the mount the inode was found from * @dentry: pointer to the affected dentry * @ia_valid: for the UID and GID status * * Changes to a dentry's metadata might result in needing to appraise. * * This function is called from notify_change(), which expects the caller * to lock the inode's i_mutex. */ static void ima_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { struct inode *inode = d_backing_inode(dentry); struct ima_iint_cache *iint; int action; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode) || !(inode->i_opflags & IOP_XATTR)) return; action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR); iint = ima_iint_find(inode); if (iint) { set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags); if (!action) clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } } /* * ima_protect_xattr - protect 'security.ima' * * Ensure that not just anyone can modify or remove 'security.ima'. */ static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len) { if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 1; } return 0; } /* * ima_reset_appraise_flags - reset ima_iint_cache flags * * @digsig: whether to clear/set IMA_DIGSIG flag, tristate values * 0: clear IMA_DIGSIG * 1: set IMA_DIGSIG * -1: don't change IMA_DIGSIG * */ static void ima_reset_appraise_flags(struct inode *inode, int digsig) { struct ima_iint_cache *iint; if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; iint->measured_pcrs = 0; set_bit(IMA_CHANGE_XATTR, &iint->atomic_flags); if (digsig == 1) set_bit(IMA_DIGSIG, &iint->atomic_flags); else if (digsig == 0) clear_bit(IMA_DIGSIG, &iint->atomic_flags); } /** * validate_hash_algo() - Block setxattr with unsupported hash algorithms * @dentry: object of the setxattr() * @xattr_value: userland supplied xattr value * @xattr_value_len: length of xattr_value * * The xattr value is mapped to its hash algorithm, and this algorithm * must be built in the kernel for the setxattr to be allowed. * * Emit an audit message when the algorithm is invalid. * * Return: 0 on success, else an error. */ static int validate_hash_algo(struct dentry *dentry, const struct evm_ima_xattr_data *xattr_value, size_t xattr_value_len) { char *path = NULL, *pathbuf = NULL; enum hash_algo xattr_hash_algo; const char *errmsg = "unavailable-hash-algorithm"; unsigned int allowed_hashes; xattr_hash_algo = ima_get_hash_algo(xattr_value, xattr_value_len); allowed_hashes = atomic_read(&ima_setxattr_allowed_hash_algorithms); if (allowed_hashes) { /* success if the algorithm is allowed in the ima policy */ if (allowed_hashes & (1U << xattr_hash_algo)) return 0; /* * We use a different audit message when the hash algorithm * is denied by a policy rule, instead of not being built * in the kernel image */ errmsg = "denied-hash-algorithm"; } else { if (likely(xattr_hash_algo == ima_hash_algo)) return 0; /* allow any xattr using an algorithm built in the kernel */ if (crypto_has_alg(hash_algo_name[xattr_hash_algo], 0, 0)) return 0; } pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) return -EACCES; path = dentry_path(dentry, pathbuf, PATH_MAX); integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path, "set_data", errmsg, -EACCES, 0); kfree(pathbuf); return -EACCES; } static int ima_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len, int flags) { const struct evm_ima_xattr_data *xvalue = xattr_value; int digsig = 0; int result; int err; result = ima_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); if (result == 1) { if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST)) return -EINVAL; err = validate_hash_algo(dentry, xvalue, xattr_value_len); if (err) return err; digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG); } else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) { digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG); } else { digsig = -1; } if (result == 1 || evm_revalidate_status(xattr_name)) { ima_reset_appraise_flags(d_backing_inode(dentry), digsig); if (result == 1) result = 0; } return result; } static int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (evm_revalidate_status(acl_name)) ima_reset_appraise_flags(d_backing_inode(dentry), -1); return 0; } static int ima_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *xattr_name) { int result, digsig = -1; result = ima_protect_xattr(dentry, xattr_name, NULL, 0); if (result == 1 || evm_revalidate_status(xattr_name)) { if (!strcmp(xattr_name, XATTR_NAME_IMA)) digsig = 0; ima_reset_appraise_flags(d_backing_inode(dentry), digsig); if (result == 1) result = 0; } return result; } static int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { return ima_inode_set_acl(idmap, dentry, acl_name, NULL); } static struct security_hook_list ima_appraise_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_post_setattr, ima_inode_post_setattr), LSM_HOOK_INIT(inode_setxattr, ima_inode_setxattr), LSM_HOOK_INIT(inode_set_acl, ima_inode_set_acl), LSM_HOOK_INIT(inode_removexattr, ima_inode_removexattr), LSM_HOOK_INIT(inode_remove_acl, ima_inode_remove_acl), }; void __init init_ima_appraise_lsm(const struct lsm_id *lsmid) { security_add_hooks(ima_appraise_hooks, ARRAY_SIZE(ima_appraise_hooks), lsmid); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_MTE_H #define __ASM_MTE_H #include <asm/compiler.h> #include <asm/mte-def.h> #ifndef __ASSEMBLER__ #include <linux/bitfield.h> #include <linux/kasan-enabled.h> #include <linux/page-flags.h> #include <linux/sched.h> #include <linux/types.h> #include <asm/pgtable-types.h> void mte_clear_page_tags(void *addr); unsigned long mte_copy_tags_from_user(void *to, const void __user *from, unsigned long n); unsigned long mte_copy_tags_to_user(void __user *to, void *from, unsigned long n); int mte_save_tags(struct page *page); void mte_save_page_tags(const void *page_addr, void *tag_storage); void mte_restore_tags(swp_entry_t entry, struct page *page); void mte_restore_page_tags(void *page_addr, const void *tag_storage); void mte_invalidate_tags(int type, pgoff_t offset); void mte_invalidate_tags_area(int type); void *mte_allocate_tag_storage(void); void mte_free_tag_storage(char *storage); #ifdef CONFIG_ARM64_MTE /* track which pages have valid allocation tags */ #define PG_mte_tagged PG_arch_2 /* simple lock to avoid multiple threads tagging the same page */ #define PG_mte_lock PG_arch_3 static inline void set_page_mte_tagged(struct page *page) { VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); /* * Ensure that the tags written prior to this function are visible * before the page flags update. */ smp_wmb(); set_bit(PG_mte_tagged, &page->flags.f); } static inline bool page_mte_tagged(struct page *page) { bool ret = test_bit(PG_mte_tagged, &page->flags.f); VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); /* * If the page is tagged, ensure ordering with a likely subsequent * read of the tags. */ if (ret) smp_rmb(); return ret; } /* * Lock the page for tagging and return 'true' if the page can be tagged, * 'false' if already tagged. PG_mte_tagged is never cleared and therefore the * locking only happens once for page initialisation. * * The page MTE lock state: * * Locked: PG_mte_lock && !PG_mte_tagged * Unlocked: !PG_mte_lock || PG_mte_tagged * * Acquire semantics only if the page is tagged (returning 'false'). */ static inline bool try_page_mte_tagging(struct page *page) { VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); if (!test_and_set_bit(PG_mte_lock, &page->flags.f)) return true; /* * The tags are either being initialised or may have been initialised * already. Check if the PG_mte_tagged flag has been set or wait * otherwise. */ smp_cond_load_acquire(&page->flags.f, VAL & (1UL << PG_mte_tagged)); return false; } void mte_zero_clear_page_tags(void *addr); void mte_sync_tags(pte_t pte, unsigned int nr_pages); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); void mte_cpu_setup(void); void mte_suspend_enter(void); void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data); size_t mte_probe_user_range(const char __user *uaddr, size_t size); #else /* CONFIG_ARM64_MTE */ /* unused if !CONFIG_ARM64_MTE, silence the compiler */ #define PG_mte_tagged 0 static inline void set_page_mte_tagged(struct page *page) { } static inline bool page_mte_tagged(struct page *page) { return false; } static inline bool try_page_mte_tagging(struct page *page) { return false; } static inline void mte_zero_clear_page_tags(void *addr) { } static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages) { } static inline void mte_copy_page_tags(void *kto, const void *kfrom) { } static inline void mte_thread_init_user(void) { } static inline void mte_thread_switch(struct task_struct *next) { } static inline void mte_suspend_enter(void) { } static inline void mte_suspend_exit(void) { } static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; } static inline long get_mte_ctrl(struct task_struct *task) { return 0; } static inline int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data) { return -EIO; } #endif /* CONFIG_ARM64_MTE */ #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_ARM64_MTE) static inline void folio_set_hugetlb_mte_tagged(struct folio *folio) { VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); /* * Ensure that the tags written prior to this function are visible * before the folio flags update. */ smp_wmb(); set_bit(PG_mte_tagged, &folio->flags.f); } static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio) { bool ret = test_bit(PG_mte_tagged, &folio->flags.f); VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); /* * If the folio is tagged, ensure ordering with a likely subsequent * read of the tags. */ if (ret) smp_rmb(); return ret; } static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio) { VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); if (!test_and_set_bit(PG_mte_lock, &folio->flags.f)) return true; /* * The tags are either being initialised or may have been initialised * already. Check if the PG_mte_tagged flag has been set or wait * otherwise. */ smp_cond_load_acquire(&folio->flags.f, VAL & (1UL << PG_mte_tagged)); return false; } #else static inline void folio_set_hugetlb_mte_tagged(struct folio *folio) { } static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio) { return false; } static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio) { return false; } #endif static inline void mte_disable_tco_entry(struct task_struct *task) { if (!system_supports_mte()) return; /* * Re-enable tag checking (TCO set on exception entry). This is only * necessary if MTE is enabled in either the kernel or the userspace * task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set * for both). With MTE disabled in the kernel and disabled or * asynchronous in userspace, tag check faults (including in uaccesses) * are not reported, therefore there is no need to re-enable checking. * This is beneficial on microarchitectures where re-enabling TCO is * expensive. */ if (kasan_hw_tags_enabled() || (task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT))) asm volatile(SET_PSTATE_TCO(0)); } #ifdef CONFIG_KASAN_HW_TAGS void mte_check_tfsr_el1(void); static inline void mte_check_tfsr_entry(void) { if (!kasan_hw_tags_enabled()) return; mte_check_tfsr_el1(); } static inline void mte_check_tfsr_exit(void) { if (!kasan_hw_tags_enabled()) return; /* * The asynchronous faults are sync'ed automatically with * TFSR_EL1 on kernel entry but for exit an explicit dsb() * is required. */ dsb(nsh); isb(); mte_check_tfsr_el1(); } #else static inline void mte_check_tfsr_el1(void) { } static inline void mte_check_tfsr_entry(void) { } static inline void mte_check_tfsr_exit(void) { } #endif /* CONFIG_KASAN_HW_TAGS */ #endif /* __ASSEMBLER__ */ #endif /* __ASM_MTE_H */ |
| 973 975 977 809 517 309 417 192 192 13 175 192 493 493 493 493 277 231 283 278 267 267 274 274 274 273 220 220 310 309 309 514 9 492 490 7 81 81 488 491 35 285 283 13 361 364 363 775 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H /* Avoid a dependency loop by declaring here. */ extern int rcuwait_wake_up(struct rcuwait *w); #include <linux/lockdep.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/rwsem.h> #include <linux/tracepoint-defs.h> #include <linux/types.h> #include <linux/cleanup.h> #include <linux/sched/mm.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), DECLARE_TRACEPOINT(mmap_lock_start_locking); DECLARE_TRACEPOINT(mmap_lock_acquire_returned); DECLARE_TRACEPOINT(mmap_lock_released); #ifdef CONFIG_TRACING void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write); void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write, bool success); void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write); static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_start_locking)) __mmap_lock_do_trace_start_locking(mm, write); } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { if (tracepoint_enabled(mmap_lock_acquire_returned)) __mmap_lock_do_trace_acquire_returned(mm, write, success); } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { if (tracepoint_enabled(mmap_lock_released)) __mmap_lock_do_trace_released(mm, write); } #else /* !CONFIG_TRACING */ static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm, bool write) { } static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm, bool write, bool success) { } static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) { } #endif /* CONFIG_TRACING */ static inline void mmap_assert_locked(const struct mm_struct *mm) { rwsem_assert_held(&mm->mmap_lock); } static inline void mmap_assert_write_locked(const struct mm_struct *mm) { rwsem_assert_held_write(&mm->mmap_lock); } #ifdef CONFIG_PER_VMA_LOCK #ifdef CONFIG_LOCKDEP #define __vma_lockdep_map(vma) (&vma->vmlock_dep_map) #else #define __vma_lockdep_map(vma) NULL #endif /* * VMA locks do not behave like most ordinary locks found in the kernel, so we * cannot quite have full lockdep tracking in the way we would ideally prefer. * * Read locks act as shared locks which exclude an exclusive lock being * taken. We therefore mark these accordingly on read lock acquire/release. * * Write locks are acquired exclusively per-VMA, but released in a shared * fashion, that is upon vma_end_write_all(), we update the mmap's seqcount such * that write lock is released. * * We therefore cannot track write locks per-VMA, nor do we try. Mitigating this * is the fact that, of course, we do lockdep-track the mmap lock rwsem which * must be held when taking a VMA write lock. * * We do, however, want to indicate that during either acquisition of a VMA * write lock or detachment of a VMA that we require the lock held be exclusive, * so we utilise lockdep to do so. */ #define __vma_lockdep_acquire_read(vma) \ lock_acquire_shared(__vma_lockdep_map(vma), 0, 1, NULL, _RET_IP_) #define __vma_lockdep_release_read(vma) \ lock_release(__vma_lockdep_map(vma), _RET_IP_) #define __vma_lockdep_acquire_exclusive(vma) \ lock_acquire_exclusive(__vma_lockdep_map(vma), 0, 0, NULL, _RET_IP_) #define __vma_lockdep_release_exclusive(vma) \ lock_release(__vma_lockdep_map(vma), _RET_IP_) /* Only meaningful if CONFIG_LOCK_STAT is defined. */ #define __vma_lockdep_stat_mark_acquired(vma) \ lock_acquired(__vma_lockdep_map(vma), _RET_IP_) static inline void mm_lock_seqcount_init(struct mm_struct *mm) { seqcount_init(&mm->mm_lock_seq); } static inline void mm_lock_seqcount_begin(struct mm_struct *mm) { do_raw_write_seqcount_begin(&mm->mm_lock_seq); } static inline void mm_lock_seqcount_end(struct mm_struct *mm) { ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq); do_raw_write_seqcount_end(&mm->mm_lock_seq); } static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { /* * Since mmap_lock is a sleeping lock, and waiting for it to become * unlocked is more or less equivalent with taking it ourselves, don't * bother with the speculative path if mmap_lock is already write-locked * and take the slow path, which takes the lock. */ return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq); } static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) { return read_seqcount_retry(&mm->mm_lock_seq, seq); } static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) { #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key lockdep_key; lockdep_init_map(__vma_lockdep_map(vma), "vm_lock", &lockdep_key, 0); #endif if (reset_refcnt) refcount_set(&vma->vm_refcnt, 0); vma->vm_lock_seq = UINT_MAX; } /* * This function determines whether the input VMA reference count describes a * VMA which has excluded all VMA read locks. * * In the case of a detached VMA, we may incorrectly indicate that readers are * excluded when one remains, because in that scenario we target a refcount of * VM_REFCNT_EXCLUDE_READERS_FLAG, rather than the attached target of * VM_REFCNT_EXCLUDE_READERS_FLAG + 1. * * However, the race window for that is very small so it is unlikely. * * Returns: true if readers are excluded, false otherwise. */ static inline bool __vma_are_readers_excluded(int refcnt) { /* * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ return (refcnt & VM_REFCNT_EXCLUDE_READERS_FLAG) && refcnt <= VM_REFCNT_EXCLUDE_READERS_FLAG + 1; } /* * Actually decrement the VMA reference count. * * The function returns the reference count as it was immediately after the * decrement took place. If it returns zero, the VMA is now detached. */ static inline __must_check unsigned int __vma_refcount_put_return(struct vm_area_struct *vma) { int oldcnt; if (__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) return 0; return oldcnt - 1; } /** * vma_refcount_put() - Drop reference count in VMA vm_refcnt field due to a * read-lock being dropped. * @vma: The VMA whose reference count we wish to decrement. * * If we were the last reader, wake up threads waiting to obtain an exclusive * lock. */ static inline void vma_refcount_put(struct vm_area_struct *vma) { /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt. */ struct mm_struct *mm = vma->vm_mm; int newcnt; __vma_lockdep_release_read(vma); newcnt = __vma_refcount_put_return(vma); /* * __vma_start_exclude_readers() may be sleeping waiting for readers to * drop their reference count, so wake it up if we were the last reader * blocking it from being acquired. * * We may be raced by other readers temporarily incrementing the * reference count, though the race window is very small, this might * cause spurious wakeups. */ if (newcnt && __vma_are_readers_excluded(newcnt)) rcuwait_wake_up(&mm->vma_writer_wait); } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) { int oldcnt; mmap_assert_locked(vma->vm_mm); if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, VM_REFCNT_LIMIT))) return false; __vma_lockdep_acquire_read(vma); return true; } /* * Use only while holding mmap read lock which guarantees that locking will not * fail (nobody can concurrently write-lock the vma). vma_start_read() should * not be used in such cases because it might fail due to mm_lock_seq overflow. * This functionality is used to obtain vma read lock and drop the mmap read lock. */ static inline bool vma_start_read_locked(struct vm_area_struct *vma) { return vma_start_read_locked_nested(vma, 0); } static inline void vma_end_read(struct vm_area_struct *vma) { vma_refcount_put(vma); } static inline unsigned int __vma_raw_mm_seqnum(struct vm_area_struct *vma) { const struct mm_struct *mm = vma->vm_mm; /* We must hold an exclusive write lock for this access to be valid. */ mmap_assert_write_locked(vma->vm_mm); return mm->mm_lock_seq.sequence; } /* * Determine whether a VMA is write-locked. Must be invoked ONLY if the mmap * write lock is held. * * Returns true if write-locked, otherwise false. */ static inline bool __is_vma_write_locked(struct vm_area_struct *vma) { /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ return vma->vm_lock_seq == __vma_raw_mm_seqnum(vma); } int __vma_start_write(struct vm_area_struct *vma, int state); /* * Begin writing to a VMA. * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. */ static inline void vma_start_write(struct vm_area_struct *vma) { if (__is_vma_write_locked(vma)) return; __vma_start_write(vma, TASK_UNINTERRUPTIBLE); } /** * vma_start_write_killable - Begin writing to a VMA. * @vma: The VMA we are going to modify. * * Exclude concurrent readers under the per-VMA lock until the currently * write-locked mmap_lock is dropped or downgraded. * * Context: May sleep while waiting for readers to drop the vma read lock. * Caller must already hold the mmap_lock for write. * * Return: 0 for a successful acquisition. -EINTR if a fatal signal was * received. */ static inline __must_check int vma_start_write_killable(struct vm_area_struct *vma) { if (__is_vma_write_locked(vma)) return 0; return __vma_start_write(vma, TASK_KILLABLE); } /** * vma_assert_write_locked() - assert that @vma holds a VMA write lock. * @vma: The VMA to assert. */ static inline void vma_assert_write_locked(struct vm_area_struct *vma) { VM_WARN_ON_ONCE_VMA(!__is_vma_write_locked(vma), vma); } /** * vma_assert_locked() - assert that @vma holds either a VMA read or a VMA write * lock and is not detached. * @vma: The VMA to assert. */ static inline void vma_assert_locked(struct vm_area_struct *vma) { unsigned int refcnt; if (IS_ENABLED(CONFIG_LOCKDEP)) { if (!lock_is_held(__vma_lockdep_map(vma))) vma_assert_write_locked(vma); return; } /* * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ refcnt = refcount_read(&vma->vm_refcnt); /* * In this case we're either read-locked, write-locked with temporary * readers, or in the midst of excluding readers, all of which means * we're locked. */ if (refcnt > 1) return; /* It is a bug for the VMA to be detached here. */ VM_WARN_ON_ONCE_VMA(!refcnt, vma); /* * OK, the VMA has a reference count of 1 which means it is either * unlocked and attached or write-locked, so assert that it is * write-locked. */ vma_assert_write_locked(vma); } /** * vma_assert_stabilised() - assert that this VMA cannot be changed from * underneath us either by having a VMA or mmap lock held. * @vma: The VMA whose stability we wish to assess. * * If lockdep is enabled we can precisely ensure stability via either an mmap * lock owned by us or a specific VMA lock. * * With lockdep disabled we may sometimes race with other threads acquiring the * mmap read lock simultaneous with our VMA read lock. */ static inline void vma_assert_stabilised(struct vm_area_struct *vma) { /* * If another thread owns an mmap lock, it may go away at any time, and * thus is no guarantee of stability. * * If lockdep is enabled we can accurately determine if an mmap lock is * held and owned by us. Otherwise we must approximate. * * It doesn't necessarily mean we are not stabilised however, as we may * hold a VMA read lock (not a write lock as this would require an owned * mmap lock). * * If (assuming lockdep is not enabled) we were to assert a VMA read * lock first we may also run into issues, as other threads can hold VMA * read locks simlutaneous to us. * * Therefore if lockdep is not enabled we risk a false negative (i.e. no * assert fired). If accurate checking is required, enable lockdep. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { if (lockdep_is_held(&vma->vm_mm->mmap_lock)) return; } else { if (rwsem_is_locked(&vma->vm_mm->mmap_lock)) return; } /* * We're not stabilised by the mmap lock, so assert that we're * stabilised by a VMA lock. */ vma_assert_locked(vma); } static inline bool vma_is_attached(struct vm_area_struct *vma) { return refcount_read(&vma->vm_refcnt); } /* * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these * assertions should be made either under mmap_write_lock or when the object * has been isolated under mmap_write_lock, ensuring no competing writers. */ static inline void vma_assert_attached(struct vm_area_struct *vma) { WARN_ON_ONCE(!vma_is_attached(vma)); } static inline void vma_assert_detached(struct vm_area_struct *vma) { WARN_ON_ONCE(vma_is_attached(vma)); } static inline void vma_mark_attached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_detached(vma); refcount_set_release(&vma->vm_refcnt, 1); } void __vma_exclude_readers_for_detach(struct vm_area_struct *vma); static inline void vma_mark_detached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_attached(vma); /* * The VMA still being attached (refcnt > 0) - is unlikely, because the * vma has been already write-locked and readers can increment vm_refcnt * only temporarily before they check vm_lock_seq, realize the vma is * locked and drop back the vm_refcnt. That is a narrow window for * observing a raised vm_refcnt. * * See the comment describing the vm_area_struct->vm_refcnt field for * details of possible refcnt values. */ if (likely(!__vma_refcount_put_return(vma))) return; __vma_exclude_readers_for_detach(vma); } struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address); /* * Locks next vma pointed by the iterator. Confirms the locked vma has not * been modified and will retry under mmap_lock protection if modification * was detected. Should be called from read RCU section. * Returns either a valid locked VMA, NULL if no more VMAs or -EINTR if the * process was interrupted. */ struct vm_area_struct *lock_next_vma(struct mm_struct *mm, struct vma_iterator *iter, unsigned long address); #else /* CONFIG_PER_VMA_LOCK */ static inline void mm_lock_seqcount_init(struct mm_struct *mm) {} static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {} static inline void mm_lock_seqcount_end(struct mm_struct *mm) {} static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq) { return false; } static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq) { return true; } static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline __must_check int vma_start_write_killable(struct vm_area_struct *vma) { return 0; } static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } static inline void vma_assert_attached(struct vm_area_struct *vma) {} static inline void vma_assert_detached(struct vm_area_struct *vma) {} static inline void vma_mark_attached(struct vm_area_struct *vma) {} static inline void vma_mark_detached(struct vm_area_struct *vma) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) { return NULL; } static inline void vma_assert_locked(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); } static inline void vma_assert_stabilised(struct vm_area_struct *vma) { /* If no VMA locks, then either mmap lock suffices to stabilise. */ mmap_assert_locked(vma->vm_mm); } #endif /* CONFIG_PER_VMA_LOCK */ static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); if (!ret) mm_lock_seqcount_begin(mm); __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } /* * Drop all currently-held per-VMA locks. * This is called from the mmap_lock implementation directly before releasing * a write-locked mmap_lock (or downgrading it to read-locked). * This should normally NOT be called manually from other places. * If you want to call this manually anyway, keep in mind that this will release * *all* VMA write locks, including ones from further up the stack. */ static inline void vma_end_write_all(struct mm_struct *mm) { mmap_assert_write_locked(mm); mm_lock_seqcount_end(mm); } static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, false); down_read(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, true); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { int ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_killable(&mm->mmap_lock); __mmap_lock_trace_acquire_returned(mm, false, ret == 0); return ret; } static inline bool mmap_read_trylock(struct mm_struct *mm) { bool ret; __mmap_lock_trace_start_locking(mm, false); ret = down_read_trylock(&mm->mmap_lock) != 0; __mmap_lock_trace_acquire_returned(mm, false, ret); return ret; } static inline void mmap_read_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read(&mm->mmap_lock); } DEFINE_GUARD(mmap_read_lock, struct mm_struct *, mmap_read_lock(_T), mmap_read_unlock(_T)) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); up_read_non_owner(&mm->mmap_lock); } static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); } #endif /* _LINUX_MMAP_LOCK_H */ |
| 1075 3 3 350 229 220 220 9 9 150 150 150 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> #include "internal.h" static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* * User space expects anonymous inodes to have no file type in st_mode. * * In particular, 'lsof' has this legacy logic: * * type = s->st_mode & S_IFMT; * switch (type) { * ... * case 0: * if (!strcmp(p, "anon_inode")) * Lf->ntype = Ntype = N_ANON_INODE; * * to detect our old anon_inode logic. * * Rather than mess with our internal sane inode data, just fix it * up here in getattr() by masking off the format bits. */ int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->mode &= ~S_IFMT; return 0; } int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EOPNOTSUPP; } static const struct inode_operations anon_inode_operations = { .getattr = anon_inode_getattr, .setattr = anon_inode_setattr, }; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; fc->s_iflags |= SB_I_NOEXEC; fc->s_iflags |= SB_I_NODEV; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; /** * anon_inode_make_secure_inode - allocate an anonymous inode with security context * @sb: [in] Superblock to allocate from * @name: [in] Name of the class of the newfile (e.g., "secretmem") * @context_inode: * [in] Optional parent inode for security inheritance * * The function ensures proper security initialization through the LSM hook * security_inode_init_security_anon(). * * Return: Pointer to new inode on success, ERR_PTR on failure. */ struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, const struct inode *context_inode) { struct inode *inode; int error; inode = alloc_anon_inode(sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; inode->i_op = &anon_inode_operations; error = security_inode_init_security_anon(inode, &QSTR(name), context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } EXPORT_SYMBOL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (make_inode) { inode = anon_inode_make_secure_inode(anon_inode_mnt->mnt_sb, name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @f_mode: [in] fmode * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Allows setting the fmode. Returns the newly created file* or an error * pointer. */ struct file *anon_inode_getfile_fmode(const char *name, const struct file_operations *fops, void *priv, int flags, fmode_t f_mode) { struct file *file; file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); if (!IS_ERR(file)) file->f_mode |= f_mode; return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); /** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns the newly created file* or an error pointer. */ struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { return FD_ADD(flags, __anon_inode_getfile(name, fops, priv, flags, context_inode, make_inode)); } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns a newly created file descriptor or an error code. */ int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); anon_inode_inode->i_op = &anon_inode_operations; return 0; } fs_initcall(anon_inode_init); |
| 223 225 34 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 194 194 193 194 194 194 194 194 194 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * device_cgroup.c - device cgroup subsystem * * Copyright 2007 IBM Corp */ #include <linux/bpf-cgroup.h> #include <linux/device_cgroup.h> #include <linux/cgroup.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #ifdef CONFIG_CGROUP_DEVICE static DEFINE_MUTEX(devcgroup_mutex); enum devcg_behavior { DEVCG_DEFAULT_NONE, DEVCG_DEFAULT_ALLOW, DEVCG_DEFAULT_DENY, }; /* * exception list locking rules: * hold devcgroup_mutex for update/read. * hold rcu_read_lock() for read. */ struct dev_exception_item { u32 major, minor; short type; short access; struct list_head list; struct rcu_head rcu; }; struct dev_cgroup { struct cgroup_subsys_state css; struct list_head exceptions; enum devcg_behavior behavior; }; static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) { return s ? container_of(s, struct dev_cgroup, css) : NULL; } static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { return css_to_devcgroup(task_css(task, devices_cgrp_id)); } /* * called under devcgroup_mutex */ static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp, *new; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry(ex, orig, list) { new = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!new) goto free_and_exit; list_add_tail(&new->list, dest); } return 0; free_and_exit: list_for_each_entry_safe(ex, tmp, dest, list) { list_del(&ex->list); kfree(ex); } return -ENOMEM; } static void dev_exceptions_move(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(ex, tmp, orig, list) { list_move_tail(&ex->list, dest); } } /* * called under devcgroup_mutex */ static int dev_exception_add(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *excopy, *walk; lockdep_assert_held(&devcgroup_mutex); excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!excopy) return -ENOMEM; list_for_each_entry(walk, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access |= ex->access; kfree(excopy); excopy = NULL; } if (excopy != NULL) list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions); return 0; } /* * called under devcgroup_mutex */ static void dev_exception_rm(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *walk, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access &= ~ex->access; if (!walk->access) { list_del_rcu(&walk->list); kfree_rcu(walk, rcu); } } } static void __dev_exception_clean(struct dev_cgroup *dev_cgroup) { struct dev_exception_item *ex, *tmp; list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) { list_del_rcu(&ex->list); kfree_rcu(ex, rcu); } } /** * dev_exception_clean - frees all entries of the exception list * @dev_cgroup: dev_cgroup with the exception list to be cleaned * * called under devcgroup_mutex */ static void dev_exception_clean(struct dev_cgroup *dev_cgroup) { lockdep_assert_held(&devcgroup_mutex); __dev_exception_clean(dev_cgroup); } static inline bool is_devcg_online(const struct dev_cgroup *devcg) { return (devcg->behavior != DEVCG_DEFAULT_NONE); } /** * devcgroup_online - initializes devcgroup's behavior and exceptions based on * parent's * @css: css getting online * returns 0 in case of success, error code otherwise */ static int devcgroup_online(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent); int ret = 0; mutex_lock(&devcgroup_mutex); if (parent_dev_cgroup == NULL) dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW; else { ret = dev_exceptions_copy(&dev_cgroup->exceptions, &parent_dev_cgroup->exceptions); if (!ret) dev_cgroup->behavior = parent_dev_cgroup->behavior; } mutex_unlock(&devcgroup_mutex); return ret; } static void devcgroup_offline(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); mutex_lock(&devcgroup_mutex); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; mutex_unlock(&devcgroup_mutex); } /* * called from kernel/cgroup/cgroup.c with cgroup_lock() held. */ static struct cgroup_subsys_state * devcgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct dev_cgroup *dev_cgroup; dev_cgroup = kzalloc_obj(*dev_cgroup); if (!dev_cgroup) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dev_cgroup->exceptions); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; return &dev_cgroup->css; } static void devcgroup_css_free(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); __dev_exception_clean(dev_cgroup); kfree(dev_cgroup); } #define DEVCG_ALLOW 1 #define DEVCG_DENY 2 #define DEVCG_LIST 3 static void seq_putaccess(struct seq_file *m, short access) { if (access & DEVCG_ACC_READ) seq_putc(m, 'r'); if (access & DEVCG_ACC_WRITE) seq_putc(m, 'w'); if (access & DEVCG_ACC_MKNOD) seq_putc(m, 'm'); } static void seq_puttype(struct seq_file *m, short type) { if (type == DEVCG_DEV_ALL) seq_putc(m, 'a'); else if (type == DEVCG_DEV_CHAR) seq_putc(m, 'c'); else if (type == DEVCG_DEV_BLOCK) seq_putc(m, 'b'); else seq_putc(m, 'X'); } static void seq_putversion(struct seq_file *m, unsigned int version) { if (version == ~0) seq_putc(m, '*'); else seq_printf(m, "%u", version); } static int devcgroup_seq_show(struct seq_file *m, void *v) { struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m)); struct dev_exception_item *ex; rcu_read_lock(); /* * To preserve the compatibility: * - Only show the "all devices" when the default policy is to allow * - List the exceptions in case the default policy is to deny * This way, the file remains as a "whitelist of devices" */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { seq_puts(m, "a *:* rwm\n"); } else { list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) { seq_puttype(m, ex->type); seq_putc(m, ' '); seq_putversion(m, ex->major); seq_putc(m, ':'); seq_putversion(m, ex->minor); seq_putc(m, ' '); seq_putaccess(m, ex->access); seq_putc(m, '\n'); } } rcu_read_unlock(); return 0; } /** * match_exception - iterates the exception list trying to find a complete match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a complete match if an exception is found that will * contain the entire range of provided parameters. * * Return: true in case it matches an exception completely */ static bool match_exception(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; if (ex->major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && ex->minor != minor) continue; /* provided access cannot have more than the exception rule */ if (access & (~ex->access)) continue; return true; } return false; } /** * match_exception_partial - iterates the exception list trying to find a partial match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a partial match if an exception's range is found to * contain *any* of the devices specified by provided parameters. This is * used to make sure no extra access is being granted that is forbidden by * any of the exception list. * * Return: true in case the provided range mat matches an exception completely */ static bool match_exception_partial(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list, lockdep_is_held(&devcgroup_mutex)) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; /* * We must be sure that both the exception and the provided * range aren't masking all devices */ if (ex->major != ~0 && major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && minor != ~0 && ex->minor != minor) continue; /* * In order to make sure the provided range isn't matching * an exception, all its access bits shouldn't match the * exception's access bits */ if (!(access & ex->access)) continue; return true; } return false; } /** * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions * @dev_cgroup: dev cgroup to be tested against * @refex: new exception * @behavior: behavior of the exception's dev_cgroup * * This is used to make sure a child cgroup won't have more privileges * than its parent */ static bool verify_new_ex(struct dev_cgroup *dev_cgroup, struct dev_exception_item *refex, enum devcg_behavior behavior) { bool match = false; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&devcgroup_mutex), "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { /* * new exception in the child doesn't matter, only * adding extra restrictions */ return true; } else { /* * new exception in the child will add more devices * that can be accessed, so it can't match any of * parent's exceptions, even slightly */ match = match_exception_partial(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) return false; return true; } } else { /* * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore * the new exception will add access to more devices and must * be contained completely in an parent's exception to be * allowed */ match = match_exception(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) /* parent has an exception that matches the proposed */ return true; else return false; } return false; } /* * parent_has_perm: * when adding a new allow rule to a device exception list, the rule * must be allowed in the parent device */ static int parent_has_perm(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return 1; return verify_new_ex(parent, ex, childcg->behavior); } /** * parent_allows_removal - verify if it's ok to remove an exception * @childcg: child cgroup from where the exception will be removed * @ex: exception being removed * * When removing an exception in cgroups with default ALLOW policy, it must * be checked if removing it will give the child cgroup more access than the * parent. * * Return: true if it's ok to remove exception, false otherwise */ static bool parent_allows_removal(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return true; /* It's always allowed to remove access to devices */ if (childcg->behavior == DEVCG_DEFAULT_DENY) return true; /* * Make sure you're not removing part or a whole exception existing in * the parent cgroup */ return !match_exception_partial(&parent->exceptions, ex->type, ex->major, ex->minor, ex->access); } /** * may_allow_all - checks if it's possible to change the behavior to * allow based on parent's rules. * @parent: device cgroup's parent * returns: != 0 in case it's allowed, 0 otherwise */ static inline int may_allow_all(struct dev_cgroup *parent) { if (!parent) return 1; return parent->behavior == DEVCG_DEFAULT_ALLOW; } /** * revalidate_active_exceptions - walks through the active exception list and * revalidates the exceptions based on parent's * behavior and exceptions. The exceptions that * are no longer valid will be removed. * Called with devcgroup_mutex held. * @devcg: cgroup which exceptions will be checked * * This is one of the three key functions for hierarchy implementation. * This function is responsible for re-evaluating all the cgroup's active * exceptions due to a parent's exception change. * Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details. */ static void revalidate_active_exceptions(struct dev_cgroup *devcg) { struct dev_exception_item *ex; struct list_head *this, *tmp; list_for_each_safe(this, tmp, &devcg->exceptions) { ex = container_of(this, struct dev_exception_item, list); if (!parent_has_perm(devcg, ex)) dev_exception_rm(devcg, ex); } } /** * propagate_exception - propagates a new exception to the children * @devcg_root: device cgroup that added a new exception * @ex: new exception to be propagated * * returns: 0 in case of success, != 0 in case of error */ static int propagate_exception(struct dev_cgroup *devcg_root, struct dev_exception_item *ex) { struct cgroup_subsys_state *pos; int rc = 0; rcu_read_lock(); css_for_each_descendant_pre(pos, &devcg_root->css) { struct dev_cgroup *devcg = css_to_devcgroup(pos); /* * Because devcgroup_mutex is held, no devcg will become * online or offline during the tree walk (see on/offline * methods), and online ones are safe to access outside RCU * read lock without bumping refcnt. */ if (pos == &devcg_root->css || !is_devcg_online(devcg)) continue; rcu_read_unlock(); /* * in case both root's behavior and devcg is allow, a new * restriction means adding to the exception list */ if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW && devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) return rc; } else { /* * in the other possible cases: * root's behavior: allow, devcg's: deny * root's behavior: deny, devcg's: deny * the exception will be removed */ dev_exception_rm(devcg, ex); } revalidate_active_exceptions(devcg); rcu_read_lock(); } rcu_read_unlock(); return rc; } /* * Modify the exception list using allow/deny rules. * CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD * so we can give a container CAP_MKNOD to let it create devices but not * modify the exception list. * It seems likely we'll want to add a CAP_CONTAINER capability to allow * us to also grant CAP_SYS_ADMIN to containers without giving away the * device exception list controls, but for now we'll stick with CAP_SYS_ADMIN * * Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting * new access is only allowed if you're in the top-level cgroup, or your * parent cgroup has the access you're asking for. */ static int devcgroup_update_access(struct dev_cgroup *devcgroup, int filetype, char *buffer) { const char *b; char temp[12]; /* 11 + 1 characters needed for a u32 */ int count, rc = 0; struct dev_exception_item ex; struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent); struct dev_cgroup tmp_devcgrp; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(&ex, 0, sizeof(ex)); memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp)); b = buffer; switch (*b) { case 'a': switch (filetype) { case DEVCG_ALLOW: if (css_has_online_children(&devcgroup->css)) return -EINVAL; if (!may_allow_all(parent)) return -EPERM; if (!parent) { devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(devcgroup); break; } INIT_LIST_HEAD(&tmp_devcgrp.exceptions); rc = dev_exceptions_copy(&tmp_devcgrp.exceptions, &devcgroup->exceptions); if (rc) return rc; dev_exception_clean(devcgroup); rc = dev_exceptions_copy(&devcgroup->exceptions, &parent->exceptions); if (rc) { dev_exceptions_move(&devcgroup->exceptions, &tmp_devcgrp.exceptions); return rc; } devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(&tmp_devcgrp); break; case DEVCG_DENY: if (css_has_online_children(&devcgroup->css)) return -EINVAL; dev_exception_clean(devcgroup); devcgroup->behavior = DEVCG_DEFAULT_DENY; break; default: return -EINVAL; } return 0; case 'b': ex.type = DEVCG_DEV_BLOCK; break; case 'c': ex.type = DEVCG_DEV_CHAR; break; default: return -EINVAL; } b++; if (!isspace(*b)) return -EINVAL; b++; if (*b == '*') { ex.major = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.major); if (rc) return -EINVAL; } else { return -EINVAL; } if (*b != ':') return -EINVAL; b++; /* read minor */ if (*b == '*') { ex.minor = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.minor); if (rc) return -EINVAL; } else { return -EINVAL; } if (!isspace(*b)) return -EINVAL; for (b++, count = 0; count < 3; count++, b++) { switch (*b) { case 'r': ex.access |= DEVCG_ACC_READ; break; case 'w': ex.access |= DEVCG_ACC_WRITE; break; case 'm': ex.access |= DEVCG_ACC_MKNOD; break; case '\n': case '\0': count = 3; break; default: return -EINVAL; } } switch (filetype) { case DEVCG_ALLOW: /* * If the default policy is to allow by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { /* Check if the parent allows removing it first */ if (!parent_allows_removal(devcgroup, &ex)) return -EPERM; dev_exception_rm(devcgroup, &ex); break; } if (!parent_has_perm(devcgroup, &ex)) return -EPERM; rc = dev_exception_add(devcgroup, &ex); break; case DEVCG_DENY: /* * If the default policy is to deny by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_DENY) dev_exception_rm(devcgroup, &ex); else rc = dev_exception_add(devcgroup, &ex); if (rc) break; /* we only propagate new restrictions */ rc = propagate_exception(devcgroup, &ex); break; default: rc = -EINVAL; } return rc; } static ssize_t devcgroup_access_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int retval; mutex_lock(&devcgroup_mutex); retval = devcgroup_update_access(css_to_devcgroup(of_css(of)), of_cft(of)->private, strstrip(buf)); mutex_unlock(&devcgroup_mutex); return retval ?: nbytes; } static struct cftype dev_cgroup_files[] = { { .name = "allow", .write = devcgroup_access_write, .private = DEVCG_ALLOW, }, { .name = "deny", .write = devcgroup_access_write, .private = DEVCG_DENY, }, { .name = "list", .seq_show = devcgroup_seq_show, .private = DEVCG_LIST, }, { } /* terminate */ }; struct cgroup_subsys devices_cgrp_subsys = { .css_alloc = devcgroup_css_alloc, .css_free = devcgroup_css_free, .css_online = devcgroup_online, .css_offline = devcgroup_offline, .legacy_cftypes = dev_cgroup_files, }; /** * devcgroup_legacy_check_permission - checks if an inode operation is permitted * @type: device type * @major: device major number * @minor: device minor number * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD * * returns 0 on success, -EPERM case the operation is not permitted */ static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; bool rc; rcu_read_lock(); dev_cgroup = task_devcgroup(current); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) /* Can't match any of the exceptions, even partially */ rc = !match_exception_partial(&dev_cgroup->exceptions, type, major, minor, access); else /* Need to match completely one exception to be allowed */ rc = match_exception(&dev_cgroup->exceptions, type, major, minor, access); rcu_read_unlock(); if (!rc) return -EPERM; return 0; } #endif /* CONFIG_CGROUP_DEVICE */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc) return rc; #ifdef CONFIG_CGROUP_DEVICE return devcgroup_legacy_check_permission(type, major, minor, access); #else /* CONFIG_CGROUP_DEVICE */ return 0; #endif /* CONFIG_CGROUP_DEVICE */ } EXPORT_SYMBOL(devcgroup_check_permission); #endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */ |
| 4 4 4 261 261 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ARM64_KVM_HYP_FAULT_H__ #define __ARM64_KVM_HYP_FAULT_H__ #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> static inline bool __fault_safe_to_translate(u64 esr) { u64 fsc = esr & ESR_ELx_FSC; if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr)) return false; return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV)); } static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) { int ret; u64 par, tmp; /* * Resolve the IPA the hard way using the guest VA. * * Stage-1 translation already validated the memory access * rights. As such, we can use the EL1 translation regime, and * don't have to distinguish between EL0 and EL1 access. * * We do need to save/restore PAR_EL1 though, as we haven't * saved the guest context yet, and we may return early... */ par = read_sysreg_par(); ret = system_supports_poe() ? __kvm_at(OP_AT_S1E1A, far) : __kvm_at(OP_AT_S1E1R, far); if (!ret) tmp = read_sysreg_par(); else tmp = SYS_PAR_EL1_F; /* back to the guest */ write_sysreg(par, par_el1); if (unlikely(tmp & SYS_PAR_EL1_F)) return false; /* Translation failed, back to guest */ /* Convert PAR to HPFAR format */ *hpfar = PAR_TO_HPFAR(tmp); return true; } /* * Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR. */ static inline bool __hpfar_valid(u64 esr) { /* * CPUs affected by ARM erratum #834220 may incorrectly report a * stage-2 translation fault when a stage-1 permission fault occurs. * * Re-walk the page tables to determine if a stage-1 fault actually * occurred. */ if (cpus_have_final_cap(ARM64_WORKAROUND_834220) && esr_fsc_is_translation_fault(esr)) return false; if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr)) return true; if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr)) return true; return esr_fsc_is_addr_sz_fault(esr); } static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) { u64 hpfar; fault->far_el2 = read_sysreg_el2(SYS_FAR); fault->hpfar_el2 = 0; if (__hpfar_valid(esr)) hpfar = read_sysreg(hpfar_el2); else if (unlikely(!__fault_safe_to_translate(esr))) return true; else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar)) return false; /* * Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid * HPFAR value. */ fault->hpfar_el2 = hpfar | HPFAR_EL2_NS; return true; } #endif |
| 27 277 273 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_ABOVE4G #define MAP_ABOVE4G 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. * * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the * kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_ABOVE4G \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline vm_flags_t calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline vm_flags_t calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | #ifdef CONFIG_TRANSPARENT_HUGEPAGE _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | #endif arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); #ifndef arch_memory_deny_write_exec_supported static inline bool arch_memory_deny_write_exec_supported(void) { return true; } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported #endif /* * Denies creating a writable executable mapping or gaining executable permissions. * * This denies the following: * * a) mmap(PROT_WRITE | PROT_EXEC) * * b) mmap(PROT_WRITE) * mprotect(PROT_EXEC) * * c) mmap(PROT_WRITE) * mprotect(PROT_READ) * mprotect(PROT_EXEC) * * But allows the following: * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) * * This is only applicable if the user has set the Memory-Deny-Write-Execute * (MDWE) protection mask for the current process. * * @old specifies the VMA flags the VMA originally possessed, and @new the ones * we propose to set. * * Return: false if proposed change is OK, true if not ok and should be denied. */ static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { /* If MDWE is disabled, we have nothing to deny. */ if (!mm_flags_test(MMF_HAS_MDWE, current->mm)) return false; /* If the new VMA is not executable, we have nothing to deny. */ if (!(new & VM_EXEC)) return false; /* Under MDWE we do not accept newly writably executable VMAs... */ if (new & VM_WRITE) return true; /* ...nor previously non-executable VMAs becoming executable. */ if (!(old & VM_EXEC)) return true; return false; } #endif /* _LINUX_MMAN_H */ |
| 3 2 1 42 58 3 3 10 2 1 2 1 3 3 54 54 7 61 42 2 62 61 1 2 12 1 1 2 2 2 38 220 29 2 1 1 1 1 2 2 2 10 1 1 2 3 1 1 1 9 3 2 25 1 10 9 1 1 4 4 2 2 1 1 1 5 1 11 1 10 | 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2019 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <kvm/arm_hypercalls.h> #include <kvm/arm_psci.h> #define KVM_ARM_SMCCC_STD_FEATURES \ GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_STD_HYP_FEATURES \ GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \ GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2 \ GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_2_BIT_COUNT - 1, 0) static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) { struct system_time_snapshot systime_snapshot; u64 cycles = ~0UL; u32 feature; /* * system time and counter value must captured at the same * time to keep consistency and precision. */ ktime_get_snapshot(&systime_snapshot); /* * This is only valid if the current clocksource is the * architected counter, as this is the only one the guest * can see. */ if (systime_snapshot.cs_id != CSID_ARM_ARCH_COUNTER) return; /* * The guest selects one of the two reference counters * (virtual or physical) with the first argument of the SMCCC * call. In case the identifier is not supported, error out. */ feature = smccc_get_arg1(vcpu); switch (feature) { case KVM_PTP_VIRT_COUNTER: cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset; break; case KVM_PTP_PHYS_COUNTER: cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.poffset; break; default: return; } /* * This relies on the top bit of val[0] never being set for * valid values of system time, because that is *really* far * in the future (about 292 years from 1970, and at that stage * nobody will give a damn about it). */ val[0] = upper_32_bits(systime_snapshot.real); val[1] = lower_32_bits(systime_snapshot.real); val[2] = upper_32_bits(cycles); val[3] = lower_32_bits(cycles); } static bool kvm_smccc_default_allowed(u32 func_id) { switch (func_id) { /* * List of function-ids that are not gated with the bitmapped * feature firmware registers, and are to be allowed for * servicing the call by default. */ case ARM_SMCCC_VERSION_FUNC_ID: case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: return true; default: /* PSCI 0.2 and up is in the 0:0x1f range */ if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD && ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f) return true; /* * KVM's PSCI 0.1 doesn't comply with SMCCC, and has * its own function-id base and range */ if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3)) return true; return false; } } static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; switch (func_id) { case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0, &smccc_feat->std_bmap); case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: return test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, &smccc_feat->std_hyp_bmap); case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT, &smccc_feat->vendor_hyp_bmap); case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP, &smccc_feat->vendor_hyp_bmap); default: return false; } } #define SMC32_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID #define SMC32_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ 0, ARM_SMCCC_FUNC_MASK) #define SMC64_ARCH_RANGE_BEGIN ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ 0, 0) #define SMC64_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ 0, ARM_SMCCC_FUNC_MASK) static int kvm_smccc_filter_insert_reserved(struct kvm *kvm) { int r; /* * Prevent userspace from handling any SMCCC calls in the architecture * range, avoiding the risk of misrepresenting Spectre mitigation status * to the guest. */ r = mtree_insert_range(&kvm->arch.smccc_filter, SMC32_ARCH_RANGE_BEGIN, SMC32_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); if (r) goto out_destroy; r = mtree_insert_range(&kvm->arch.smccc_filter, SMC64_ARCH_RANGE_BEGIN, SMC64_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); if (r) goto out_destroy; return 0; out_destroy: mtree_destroy(&kvm->arch.smccc_filter); return r; } static bool kvm_smccc_filter_configured(struct kvm *kvm) { return !mtree_empty(&kvm->arch.smccc_filter); } static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr) { const void *zero_page = page_to_virt(ZERO_PAGE(0)); struct kvm_smccc_filter filter; u32 start, end; int r; if (copy_from_user(&filter, uaddr, sizeof(filter))) return -EFAULT; if (memcmp(filter.pad, zero_page, sizeof(filter.pad))) return -EINVAL; start = filter.base; end = start + filter.nr_functions - 1; if (end < start || filter.action >= NR_SMCCC_FILTER_ACTIONS) return -EINVAL; mutex_lock(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm)) { r = -EBUSY; goto out_unlock; } if (!kvm_smccc_filter_configured(kvm)) { r = kvm_smccc_filter_insert_reserved(kvm); if (WARN_ON_ONCE(r)) goto out_unlock; } r = mtree_insert_range(&kvm->arch.smccc_filter, start, end, xa_mk_value(filter.action), GFP_KERNEL_ACCOUNT); out_unlock: mutex_unlock(&kvm->arch.config_lock); return r; } static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id) { unsigned long idx = func_id; void *val; if (!kvm_smccc_filter_configured(kvm)) return KVM_SMCCC_FILTER_HANDLE; /* * But where's the error handling, you say? * * mt_find() returns NULL if no entry was found, which just so happens * to match KVM_SMCCC_FILTER_HANDLE. */ val = mt_find(&kvm->arch.smccc_filter, &idx, idx); return xa_to_value(val); } static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id) { /* * Intervening actions in the SMCCC filter take precedence over the * pseudo-firmware register bitmaps. */ u8 action = kvm_smccc_filter_get_action(vcpu->kvm, func_id); if (action != KVM_SMCCC_FILTER_HANDLE) return action; if (kvm_smccc_test_fw_bmap(vcpu, func_id) || kvm_smccc_default_allowed(func_id)) return KVM_SMCCC_FILTER_HANDLE; return KVM_SMCCC_FILTER_DENY; } static void kvm_prepare_hypercall_exit(struct kvm_vcpu *vcpu, u32 func_id) { u8 ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); struct kvm_run *run = vcpu->run; u64 flags = 0; if (ec == ESR_ELx_EC_SMC32 || ec == ESR_ELx_EC_SMC64) flags |= KVM_HYPERCALL_EXIT_SMC; if (!kvm_vcpu_trap_il_is32bit(vcpu)) flags |= KVM_HYPERCALL_EXIT_16BIT; run->exit_reason = KVM_EXIT_HYPERCALL; run->hypercall = (typeof(run->hypercall)) { .nr = func_id, .flags = flags, }; } int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); u64 val[4] = {SMCCC_RET_NOT_SUPPORTED}; u32 feature; u8 action; gpa_t gpa; uuid_t uuid; action = kvm_smccc_get_action(vcpu, func_id); switch (action) { case KVM_SMCCC_FILTER_HANDLE: break; case KVM_SMCCC_FILTER_DENY: goto out; case KVM_SMCCC_FILTER_FWD_TO_USER: kvm_prepare_hypercall_exit(vcpu, func_id); return 0; default: WARN_RATELIMIT(1, "Unhandled SMCCC filter action: %d\n", action); goto out; } switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: val[0] = ARM_SMCCC_VERSION_1_1; break; case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: feature = smccc_get_arg1(vcpu); switch (feature) { case ARM_SMCCC_ARCH_WORKAROUND_1: switch (arm64_get_spectre_v2_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: val[0] = SMCCC_RET_SUCCESS; break; case SPECTRE_UNAFFECTED: val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; break; } break; case ARM_SMCCC_ARCH_WORKAROUND_2: switch (arm64_get_spectre_v4_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: /* * SSBS everywhere: Indicate no firmware * support, as the SSBS support will be * indicated to the guest and the default is * safe. * * Otherwise, expose a permanent mitigation * to the guest, and hide SSBS so that the * guest stays protected. */ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP)) break; fallthrough; case SPECTRE_UNAFFECTED: val[0] = SMCCC_RET_NOT_REQUIRED; break; } break; case ARM_SMCCC_ARCH_WORKAROUND_3: switch (arm64_get_spectre_bhb_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: val[0] = SMCCC_RET_SUCCESS; break; case SPECTRE_UNAFFECTED: val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; break; } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: if (test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, &smccc_feat->std_hyp_bmap)) val[0] = SMCCC_RET_SUCCESS; break; } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: val[0] = kvm_hypercall_pv_features(vcpu); break; case ARM_SMCCC_HV_PV_TIME_ST: gpa = kvm_init_stolen_time(vcpu); if (gpa != INVALID_GPA) val[0] = gpa; break; case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: uuid = ARM_SMCCC_VENDOR_HYP_UID_KVM; val[0] = smccc_uuid_to_reg(&uuid, 0); val[1] = smccc_uuid_to_reg(&uuid, 1); val[2] = smccc_uuid_to_reg(&uuid, 2); val[3] = smccc_uuid_to_reg(&uuid, 3); break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: val[0] = smccc_feat->vendor_hyp_bmap; /* Function numbers 2-63 are reserved for pKVM for now */ val[2] = smccc_feat->vendor_hyp_bmap_2; break; case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: kvm_ptp_get_time(vcpu, val); break; case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: return kvm_trng_call(vcpu); default: return kvm_psci_call(vcpu); } out: smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]); return 1; } static const u64 kvm_arm_fw_reg_ids[] = { KVM_REG_ARM_PSCI_VERSION, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, KVM_REG_ARM_STD_BMAP, KVM_REG_ARM_STD_HYP_BMAP, KVM_REG_ARM_VENDOR_HYP_BMAP, KVM_REG_ARM_VENDOR_HYP_BMAP_2, }; void kvm_arm_init_hypercalls(struct kvm *kvm) { struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES; smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; mt_init(&kvm->arch.smccc_filter); } void kvm_arm_teardown_hypercalls(struct kvm *kvm) { mtree_destroy(&kvm->arch.smccc_filter); } int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) { return ARRAY_SIZE(kvm_arm_fw_reg_ids); } int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { int i; for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) { if (put_user(kvm_arm_fw_reg_ids[i], uindices++)) return -EFAULT; } return 0; } #define KVM_REG_FEATURE_LEVEL_MASK GENMASK(3, 0) /* * Convert the workaround level into an easy-to-compare number, where higher * values mean better protection. */ static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid) { switch (regid) { case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: switch (arm64_get_spectre_v2_state()) { case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; case SPECTRE_MITIGATED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; } return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: switch (arm64_get_spectre_v4_state()) { case SPECTRE_MITIGATED: /* * As for the hypercall discovery, we pretend we * don't have any FW mitigation if SSBS is there at * all times. */ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP)) return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; fallthrough; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; } break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: switch (arm64_get_spectre_bhb_state()) { case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; case SPECTRE_MITIGATED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; } return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; } return -EINVAL; } int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; void __user *uaddr = (void __user *)(long)reg->addr; u64 val; switch (reg->id) { case KVM_REG_ARM_PSCI_VERSION: val = kvm_psci_version(vcpu); break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK; break; case KVM_REG_ARM_STD_BMAP: val = READ_ONCE(smccc_feat->std_bmap); break; case KVM_REG_ARM_STD_HYP_BMAP: val = READ_ONCE(smccc_feat->std_hyp_bmap); break; case KVM_REG_ARM_VENDOR_HYP_BMAP: val = READ_ONCE(smccc_feat->vendor_hyp_bmap); break; case KVM_REG_ARM_VENDOR_HYP_BMAP_2: val = READ_ONCE(smccc_feat->vendor_hyp_bmap_2); break; default: return -ENOENT; } if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) return -EFAULT; return 0; } static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) { int ret = 0; struct kvm *kvm = vcpu->kvm; struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; unsigned long *fw_reg_bmap, fw_reg_features; switch (reg_id) { case KVM_REG_ARM_STD_BMAP: fw_reg_bmap = &smccc_feat->std_bmap; fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES; break; case KVM_REG_ARM_STD_HYP_BMAP: fw_reg_bmap = &smccc_feat->std_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_STD_HYP_FEATURES; break; case KVM_REG_ARM_VENDOR_HYP_BMAP: fw_reg_bmap = &smccc_feat->vendor_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; break; case KVM_REG_ARM_VENDOR_HYP_BMAP_2: fw_reg_bmap = &smccc_feat->vendor_hyp_bmap_2; fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2; break; default: return -ENOENT; } /* Check for unsupported bit */ if (val & ~fw_reg_features) return -EINVAL; mutex_lock(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm) && val != *fw_reg_bmap) { ret = -EBUSY; goto out; } WRITE_ONCE(*fw_reg_bmap, val); out: mutex_unlock(&kvm->arch.config_lock); return ret; } int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; int wa_level; if (KVM_REG_SIZE(reg->id) != sizeof(val)) return -ENOENT; if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; switch (reg->id) { case KVM_REG_ARM_PSCI_VERSION: { bool wants_02; wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2); switch (val) { case KVM_ARM_PSCI_0_1: if (wants_02) return -EINVAL; vcpu->kvm->arch.psci_version = val; return 0; case KVM_ARM_PSCI_0_2: case KVM_ARM_PSCI_1_0: case KVM_ARM_PSCI_1_1: case KVM_ARM_PSCI_1_2: case KVM_ARM_PSCI_1_3: if (!wants_02) return -EINVAL; vcpu->kvm->arch.psci_version = val; return 0; } break; } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: if (val & ~KVM_REG_FEATURE_LEVEL_MASK) return -EINVAL; if (get_kernel_wa_level(vcpu, reg->id) < val) return -EINVAL; return 0; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) return -EINVAL; /* The enabled bit must not be set unless the level is AVAIL. */ if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) return -EINVAL; /* * Map all the possible incoming states to the only two we * really want to deal with. */ switch (val & KVM_REG_FEATURE_LEVEL_MASK) { case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; break; default: return -EINVAL; } /* * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the * other way around. */ if (get_kernel_wa_level(vcpu, reg->id) < wa_level) return -EINVAL; return 0; case KVM_REG_ARM_STD_BMAP: case KVM_REG_ARM_STD_HYP_BMAP: case KVM_REG_ARM_VENDOR_HYP_BMAP: case KVM_REG_ARM_VENDOR_HYP_BMAP_2: return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val); default: return -ENOENT; } return -EINVAL; } int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VM_SMCCC_FILTER: return 0; default: return -ENXIO; } } int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { void __user *uaddr = (void __user *)attr->addr; switch (attr->attr) { case KVM_ARM_VM_SMCCC_FILTER: return kvm_smccc_set_filter(kvm, uaddr); default: return -ENXIO; } } |
| 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * * Fixes from William Schumacher incorporated on 15 March 2001. * (Reported by Charles Bertsch, <CBertsch@microtest.com>). */ /* * This file contains generic functions for manipulating * POSIX 1003.1e draft standard 17 ACLs. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/mnt_idmapping.h> #include <linux/iversion.h> #include <linux/security.h> #include <linux/fsnotify.h> #include <linux/filelock.h> #include "internal.h" static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: return &inode->i_acl; case ACL_TYPE_DEFAULT: return &inode->i_default_acl; default: BUG(); } } struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *acl; for (;;) { rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); } rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); if (acl == ACL_DONT_CACHE) { struct posix_acl *ret; ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU); if (!IS_ERR(ret)) acl = ret; } return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); static void __forget_cached_acl(struct posix_acl **p) { struct posix_acl *old; old = xchg(p, ACL_NOT_CACHED); if (!is_uncached_acl(old)) posix_acl_release(old); } void forget_cached_acl(struct inode *inode, int type) { __forget_cached_acl(acl_by_type(inode, type)); } EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { __forget_cached_acl(&inode->i_acl); __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); static struct posix_acl *__get_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, int type) { struct posix_acl *sentinel; struct posix_acl **p; struct posix_acl *acl; /* * The sentinel is used to detect when another operation like * set_cached_acl() or forget_cached_acl() races with get_inode_acl(). * It is guaranteed that is_uncached_acl(sentinel) is true. */ acl = get_cached_acl(inode, type); if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; sentinel = uncached_acl_sentinel(current); p = acl_by_type(inode, type); /* * If the ACL isn't being read yet, set our sentinel. Otherwise, the * current value of the ACL will not be ACL_NOT_CACHED and so our own * sentinel will not be set; another task will update the cache. We * could wait for that other task to complete its job, but it's easier * to just call ->get_inode_acl to fetch the ACL ourself. (This is * going to be an unlikely race.) */ cmpxchg(p, ACL_NOT_CACHED, sentinel); /* * Normally, the ACL returned by ->get{_inode}_acl will be cached. * A filesystem can prevent that by calling * forget_cached_acl(inode, type) in ->get{_inode}_acl. * * If the filesystem doesn't have a get{_inode}_ acl() function at all, * we'll just create the negative cache entry. */ if (dentry && inode->i_op->get_acl) { acl = inode->i_op->get_acl(idmap, dentry, type); } else if (inode->i_op->get_inode_acl) { acl = inode->i_op->get_inode_acl(inode, type, false); } else { set_cached_acl(inode, type, NULL); return NULL; } if (IS_ERR(acl)) { /* * Remove our sentinel so that we don't block future attempts * to cache the ACL. */ cmpxchg(p, sentinel, ACL_NOT_CACHED); return acl; } /* * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); if (unlikely(!try_cmpxchg(p, &sentinel, acl))) posix_acl_release(acl); return acl; } struct posix_acl *get_inode_acl(struct inode *inode, int type) { return __get_acl(&nop_mnt_idmap, NULL, inode, type); } EXPORT_SYMBOL(get_inode_acl); /* * Init a fresh posix_acl */ void posix_acl_init(struct posix_acl *acl, int count) { refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); /* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * posix_acl_alloc(unsigned int count, gfp_t flags) { struct posix_acl *acl; acl = kmalloc_flex(*acl, a_entries, count, flags); if (acl) posix_acl_init(acl, count); return acl; } EXPORT_SYMBOL(posix_acl_alloc); /* * Clone an ACL. */ struct posix_acl * posix_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count), flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } EXPORT_SYMBOL_GPL(posix_acl_clone); /* * Check if an acl is valid. Returns 0 if it is, or -E... otherwise. */ int posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl) { const struct posix_acl_entry *pa, *pe; int state = ACL_USER_OBJ; int needs_mask = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE)) return -EINVAL; switch (pa->e_tag) { case ACL_USER_OBJ: if (state == ACL_USER_OBJ) { state = ACL_USER; break; } return -EINVAL; case ACL_USER: if (state != ACL_USER) return -EINVAL; if (!kuid_has_mapping(user_ns, pa->e_uid)) return -EINVAL; needs_mask = 1; break; case ACL_GROUP_OBJ: if (state == ACL_USER) { state = ACL_GROUP; break; } return -EINVAL; case ACL_GROUP: if (state != ACL_GROUP) return -EINVAL; if (!kgid_has_mapping(user_ns, pa->e_gid)) return -EINVAL; needs_mask = 1; break; case ACL_MASK: if (state != ACL_GROUP) return -EINVAL; state = ACL_OTHER; break; case ACL_OTHER: if (state == ACL_OTHER || (state == ACL_GROUP && !needs_mask)) { state = 0; break; } return -EINVAL; default: return -EINVAL; } } if (state == 0) return 0; return -EINVAL; } EXPORT_SYMBOL(posix_acl_valid); /* * Returns 0 if the acl can be exactly represented in the traditional * file mode permission bits, or else 1. Returns -E... on error. */ int posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; umode_t mode = 0; int not_equiv = 0; /* * A null ACL can always be presented as mode bits. */ if (!acl) return 0; FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: mode |= (pa->e_perm & S_IRWXO) << 6; break; case ACL_GROUP_OBJ: mode |= (pa->e_perm & S_IRWXO) << 3; break; case ACL_OTHER: mode |= pa->e_perm & S_IRWXO; break; case ACL_MASK: mode = (mode & ~S_IRWXG) | ((pa->e_perm & S_IRWXO) << 3); not_equiv = 1; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; default: return -EINVAL; } } if (mode_p) *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } EXPORT_SYMBOL(posix_acl_equiv_mode); /* * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) return ERR_PTR(-ENOMEM); acl->a_entries[0].e_tag = ACL_USER_OBJ; acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6; acl->a_entries[1].e_tag = ACL_GROUP_OBJ; acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3; acl->a_entries[2].e_tag = ACL_OTHER; acl->a_entries[2].e_perm = (mode & S_IRWXO); return acl; } EXPORT_SYMBOL(posix_acl_from_mode); /* * Return 0 if current is granted want access to the inode * by the acl. Returns -E... otherwise. */ int posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto check_perm; break; case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_MASK: break; case ACL_OTHER: if (found) return -EACCES; else goto check_perm; default: return -EIO; } } return -EIO; mask: for (mask_obj = pa+1; mask_obj != pe; mask_obj++) { if (mask_obj->e_tag == ACL_MASK) { if ((pa->e_perm & mask_obj->e_perm & want) == want) return 0; return -EACCES; } } check_perm: if ((pa->e_perm & want) == want) return 0; return -EACCES; } /* * Modify acl when creating a new inode. The caller must ensure the acl is * only referenced once. * * mode_p initially must contain the mode parameter to the open() / creat() * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } /* * Modify the ACL for the chmod syscall. */ static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm = (mode & S_IRWXU) >> 6; break; case ACL_USER: case ACL_GROUP: break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_MASK: mask_obj = pa; break; case ACL_OTHER: pa->e_perm = (mode & S_IRWXO); break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm = (mode & S_IRWXG) >> 3; } else { if (!group_obj) return -EIO; group_obj->e_perm = (mode & S_IRWXG) >> 3; } return 0; } int __posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = posix_acl_create_masq(clone, mode_p); if (err < 0) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_create); int __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = __posix_acl_chmod_masq(clone, mode); if (err) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * * @idmap: idmap of the mount @inode was found from * @dentry: dentry to check permissions on * @mode: the new mode of @inode * * If the dentry has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int ret = 0; if (!IS_POSIXACL(inode)) return 0; if (!inode->i_op->set_acl) return -EOPNOTSUPP; acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR_OR_NULL(acl)) { if (acl == ERR_PTR(-EOPNOTSUPP)) return 0; return PTR_ERR(acl); } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } EXPORT_SYMBOL(posix_acl_chmod); int posix_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = get_inode_acl(dir, ACL_TYPE_DEFAULT); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); ret = -ENOMEM; clone = posix_acl_clone(p, GFP_NOFS); if (!clone) goto err_release; ret = posix_acl_create_masq(clone, mode); if (ret < 0) goto err_release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; err_release_clone: posix_acl_release(clone); err_release: posix_acl_release(p); return ret; } EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl * @idmap: idmap of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new * file mode, set *@acl to NULL to indicate that no ACL should be set. * * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Called from set_acl inode operations. */ int posix_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; *mode_p = mode; return 0; } EXPORT_SYMBOL(posix_acl_update_mode); /* * Fix up the uids and gids in posix acl extended attributes in place. */ static int posix_acl_fix_xattr_common(const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; int count; if (!header) return -EINVAL; if (size < sizeof(struct posix_acl_xattr_header)) return -EINVAL; if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return -EOPNOTSUPP; count = posix_acl_xattr_count(size); if (count < 0) return -EINVAL; if (count == 0) return 0; return count; } /** * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format * @userns: the filesystem's idmapping * @value: the uapi representation of POSIX ACLs * @size: the size of @void * * Filesystems that store POSIX ACLs in the unaltered uapi format should use * posix_acl_from_xattr() when reading them from the backing store and * converting them into the struct posix_acl VFS format. The helper is * specifically intended to be called from the acl inode operation. * * The posix_acl_from_xattr() function will map the raw {g,u}id values stored * in ACL_{GROUP,USER} entries into idmapping in @userns. * * Note that posix_acl_from_xattr() does not take idmapped mounts into account. * If it did it calling it from the get acl inode operation would return POSIX * ACLs mapped according to an idmapped mount which would mean that the value * couldn't be cached for the filesystem. Idmapped mounts are taken into * account on the fly during permission checking or right at the VFS - * userspace boundary before reporting them to the user. * * Return: Allocated struct posix_acl on success, NULL for a valid header but * without actual POSIX ACL entries, or ERR_PTR() encoded error code. */ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns, const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end; int count; struct posix_acl *acl; struct posix_acl_entry *acl_e; count = posix_acl_fix_xattr_common(value, size); if (count < 0) return ERR_PTR(count); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; for (end = entry + count; entry != end; acl_e++, entry++) { acl_e->e_tag = le16_to_cpu(entry->e_tag); acl_e->e_perm = le16_to_cpu(entry->e_perm); switch(acl_e->e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: break; case ACL_USER: acl_e->e_uid = make_kuid(userns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = make_kgid(userns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; break; default: goto fail; } } return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL (posix_acl_from_xattr); /* * Convert from in-memory to extended attribute representation. */ void * posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, size_t *sizep, gfp_t gfp) { struct posix_acl_xattr_header *ext_acl; struct posix_acl_xattr_entry *ext_entry; size_t size; int n; size = posix_acl_xattr_size(acl->a_count); ext_acl = kmalloc(size, gfp); if (!ext_acl) return NULL; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } *sizep = size; return ext_acl; } EXPORT_SYMBOL (posix_acl_to_xattr); /** * vfs_posix_acl_to_xattr - convert from kernel to userspace representation * @idmap: idmap of the mount * @inode: inode the posix acls are set on * @acl: the posix acls as represented by the vfs * @buffer: the buffer into which to convert @acl * @size: size of @buffer * * This converts @acl from the VFS representation in the filesystem idmapping * to the uapi form reportable to userspace. And mount and caller idmappings * are handled appropriately. * * Return: On success, the size of the stored uapi posix acls, on error a * negative errno. */ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; struct user_namespace *fs_userns, *caller_userns; ssize_t real_size, n; vfsuid_t vfsuid; vfsgid_t vfsgid; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); fs_userns = i_user_ns(inode); caller_userns = current_user_ns(); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid); ext_entry->e_id = cpu_to_le32(from_kuid( caller_userns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid); ext_entry->e_id = cpu_to_le32(from_kgid( caller_userns, vfsgid_into_kgid(vfsgid))); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } int set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type, struct posix_acl *acl) { struct inode *inode = d_inode(dentry); if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (acl) { int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl); if (ret) return ret; } return inode->i_op->set_acl(idmap, dentry, acl, type); } EXPORT_SYMBOL(set_posix_acl); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { int err; if (!IS_POSIXACL(inode)) return 0; if (inode->i_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } return 0; } static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } /* * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs * * This is the legacy POSIX ACL access xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_access = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_access); /* * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs * * This is the legacy POSIX ACL default xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_default = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_default); int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; struct inode *inode = d_inode(dentry); if (type == ACL_TYPE_ACCESS) { error = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (error) return error; } inode_set_ctime_current(inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); set_cached_acl(inode, type, acl); return 0; } int simple_acl_create(struct inode *dir, struct inode *inode) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl); set_cached_acl(inode, ACL_TYPE_ACCESS, acl); if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return 0; } static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap, struct user_namespace *fs_userns, struct posix_acl *acl) { for (int n = 0; n < acl->a_count; n++) { struct posix_acl_entry *acl_e = &acl->a_entries[n]; switch (acl_e->e_tag) { case ACL_USER: acl_e->e_uid = from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(acl_e->e_uid)); break; case ACL_GROUP: acl_e->e_gid = from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(acl_e->e_gid)); break; } } return 0; } /** * vfs_set_acl - set posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to set the posix acls * @acl_name: the name of the posix acl * @kacl: the posix acls in the appropriate VFS format * * This function sets @kacl. The caller must all posix_acl_release() on @kacl * afterwards. * * Return: On success 0, on error negative errno. */ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct delegated_inode delegated_inode = { }; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; if (kacl) { /* * If we're on an idmapped mount translate from mount specific * vfs{g,u}id_t into global filesystem k{g,u}id_t. * Afterwards we can cache the POSIX ACLs filesystem wide and - * if this is a filesystem with a backing store - ultimately * translate them to backing store values. */ error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl); if (error) return error; } retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_set_acl(idmap, dentry, acl_name, kacl); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, kacl); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_set_acl(dentry, acl_name, kacl); } out_inode_unlock: inode_unlock(inode); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_set_acl); /** * vfs_get_acl - get posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function retrieves @kacl from the filesystem. The caller must all * posix_acl_release() on @kacl. * * Return: On success POSIX ACLs in VFS format, on error negative errno. */ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int acl_type, error; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return ERR_PTR(-EINVAL); /* * The VFS has no restrictions on reading POSIX ACLs so calling * something like xattr_permission() isn't needed. Only LSMs get a say. */ error = security_inode_get_acl(idmap, dentry, acl_name); if (error) return ERR_PTR(error); if (!IS_POSIXACL(inode)) return ERR_PTR(-EOPNOTSUPP); if (S_ISLNK(inode->i_mode)) return ERR_PTR(-EOPNOTSUPP); acl = __get_acl(idmap, dentry, inode, acl_type); if (IS_ERR(acl)) return acl; if (!acl) return ERR_PTR(-ENODATA); return acl; } EXPORT_SYMBOL_GPL(vfs_get_acl); /** * vfs_remove_acl - remove posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function removes posix acls. * * Return: On success 0, on error negative errno. */ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct delegated_inode delegated_inode = { }; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_remove_acl(idmap, dentry, acl_name); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, NULL); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: inode_unlock(inode); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_remove_acl); int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { int error; struct posix_acl *acl = NULL; if (size) { /* * Note that posix_acl_from_xattr() uses GFP_NOFS when it * probably doesn't need to here. */ acl = posix_acl_from_xattr(current_user_ns(), kvalue, size); if (IS_ERR(acl)) return PTR_ERR(acl); } error = vfs_set_acl(idmap, dentry, acl_name, acl); posix_acl_release(acl); return error; } ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { ssize_t error; struct posix_acl *acl; acl = vfs_get_acl(idmap, dentry, acl_name); if (IS_ERR(acl)) return PTR_ERR(acl); error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry), acl, kvalue, size); posix_acl_release(acl); return error; } |
| 86 64 211 89 88 5 86 89 89 89 228 228 228 82 227 228 228 228 228 227 228 82 165 165 165 165 165 275 272 157 209 64 182 209 64 63 64 64 193 194 164 164 164 52 117 405 192 462 405 149 149 149 404 403 405 405 8 397 404 405 404 404 148 149 149 148 149 149 150 150 150 150 149 150 64 64 64 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <linux/oom.h> #include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> #include "internal.h" #include "swap.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_assign(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } static void check_anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { /* The write lock must be held. */ mmap_assert_write_locked(src->vm_mm); /* If not a fork then must be on same mm. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && dst->vm_mm != src->vm_mm); /* If we have anything to do src->anon_vma must be provided. */ VM_WARN_ON_ONCE(!src->anon_vma && !list_empty(&src->anon_vma_chain)); VM_WARN_ON_ONCE(!src->anon_vma && dst->anon_vma); /* We are establishing a new anon_vma_chain. */ VM_WARN_ON_ONCE(!list_empty(&dst->anon_vma_chain)); /* * On fork, dst->anon_vma is set NULL (temporarily). Otherwise, anon_vma * must be the same across dst and src. */ VM_WARN_ON_ONCE(dst->anon_vma && dst->anon_vma != src->anon_vma); /* * Essentially equivalent to above - if not a no-op, we should expect * dst->anon_vma to be set for everything except a fork. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && src->anon_vma && !dst->anon_vma); /* For the anon_vma to be compatible, it can only be singular. */ VM_WARN_ON_ONCE(operation == VMA_OP_MERGE_UNFAULTED && !list_is_singular(&src->anon_vma_chain)); #ifdef CONFIG_PER_VMA_LOCK /* Only merging an unfaulted VMA leaves the destination attached. */ VM_WARN_ON_ONCE(operation != VMA_OP_MERGE_UNFAULTED && vma_is_attached(dst)); #endif } static void maybe_reuse_anon_vma(struct vm_area_struct *dst, struct anon_vma *anon_vma) { /* If already populated, nothing to do.*/ if (dst->anon_vma) return; /* * We reuse an anon_vma if any linking VMAs were unmapped and it has * only a single child at most. */ if (anon_vma->num_active_vmas > 0) return; if (anon_vma->num_children > 1) return; dst->anon_vma = anon_vma; anon_vma->num_active_vmas++; } static void cleanup_partial_anon_vmas(struct vm_area_struct *vma); /** * anon_vma_clone - Establishes new anon_vma_chain objects in @dst linking to * all of the anon_vma objects contained within @src anon_vma_chain's. * @dst: The destination VMA with an empty anon_vma_chain. * @src: The source VMA we wish to duplicate. * @operation: The type of operation which resulted in the clone. * * This is the heart of the VMA side of the anon_vma implementation - we invoke * this function whenever we need to set up a new VMA's anon_vma state. * * This is invoked for: * * - VMA Merge, but only when @dst is unfaulted and @src is faulted - meaning we * clone @src into @dst. * - VMA split. * - VMA (m)remap. * - Fork of faulted VMA. * * In all cases other than fork this is simply a duplication. Fork additionally * adds a new active anon_vma. * * ONLY in the case of fork do we try to 'reuse' existing anon_vma's in an * anon_vma hierarchy, reusing anon_vma's which have no VMA associated with them * but do have a single child. This is to avoid waste of memory when repeatedly * forking. * * Returns: 0 on success, -ENOMEM on failure. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { struct anon_vma_chain *avc, *pavc; struct anon_vma *active_anon_vma = src->anon_vma; check_anon_vma_clone(dst, src, operation); if (!active_anon_vma) return 0; /* * Allocate AVCs. We don't need an anon_vma lock for this as we * are not updating the anon_vma rbtree nor are we changing * anon_vma statistics. * * Either src, dst have the same mm for which we hold an exclusive mmap * write lock, or we are forking and we hold it on src->vm_mm and dst is * not yet accessible to other threads so there's no possibliity of the * unlinked AVC's being observed yet. */ list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; anon_vma_chain_assign(dst, avc, pavc->anon_vma); } /* * Now link the anon_vma's back to the newly inserted AVCs. * Note that all anon_vma's share the same root. */ anon_vma_lock_write(src->anon_vma); list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); if (operation == VMA_OP_FORK) maybe_reuse_anon_vma(dst, anon_vma); } if (operation != VMA_OP_FORK) dst->anon_vma->num_active_vmas++; anon_vma_unlock_write(active_anon_vma); return 0; enomem_failure: cleanup_partial_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int rc; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; anon_vma = anon_vma_alloc(); if (!anon_vma) return -ENOMEM; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) { put_anon_vma(anon_vma); return -ENOMEM; } /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ rc = anon_vma_clone(vma, pvma, VMA_OP_FORK); /* An error arose or an existing anon_vma was reused, all done then. */ if (rc || vma->anon_vma) { put_anon_vma(anon_vma); anon_vma_chain_free(avc); return rc; } /* * OK no reuse, so add our own anon_vma. * * Since it is not linked anywhere we can safely manipulate anon_vma * fields without a lock. */ anon_vma->num_active_vmas = 1; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); /* Now let rmap see it. */ anon_vma_lock_write(anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; } /* * In the unfortunate case of anon_vma_clone() failing to allocate memory we * have to clean things up. * * Since we allocate anon_vma_chain's before we insert them into the interval * trees, we simply have to free up the AVC's and remove the entries from the * VMA's anon_vma_chain. */ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { list_del(&avc->same_vma); anon_vma_chain_free(avc); } } /** * unlink_anon_vmas() - remove all links between a VMA and anon_vma's, freeing * anon_vma_chain objects. * @vma: The VMA whose links to anon_vma objects is to be severed. * * As part of the process anon_vma_chain's are freed, * anon_vma->num_children,num_active_vmas is updated as required and, if the * relevant anon_vma references no further VMAs, its reference count is * decremented. */ void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *active_anon_vma = vma->anon_vma; /* Always hold mmap lock, read-lock on unmap possibly. */ mmap_assert_locked(vma->vm_mm); /* Unfaulted is a no-op. */ if (!active_anon_vma) { VM_WARN_ON_ONCE(!list_empty(&vma->anon_vma_chain)); return; } anon_vma_lock_write(active_anon_vma); /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } active_anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; anon_vma_unlock_write(active_anon_vma); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should hold folio lock when calling this. */ struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, start, end); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { flush_tlb_mm(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibility to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { if (folio_test_anon(folio)) { struct anon_vma *anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !anon_vma || vma->anon_vma->root != anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* KSM folios don't reach here because of the !anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; vm_flags_t vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int ptes = 0, referenced = 0; unsigned int nr; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; nr = 1; if (vma->vm_flags & VM_LOCKED) { ptes++; pra->mapcount--; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) continue; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_maybe_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (lru_gen_enabled() && pvmw.pte) { if (lru_gen_look_around(&pvmw)) referenced++; } else if (pvmw.pte) { if (folio_test_large(folio)) { unsigned long end_addr = pmd_addr_end(address, vma->vm_end); unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT; pte_t pteval = ptep_get(pvmw.pte); nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr); } ptes += nr; if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr)) referenced++; /* Skip the batched PTEs */ pvmw.pte += nr - 1; pvmw.address += (nr - 1) * PAGE_SIZE; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } pra->mapcount -= nr; /* * If we are sure that we batched the entire folio, * we can just optimize and stop right here. */ if (ptes == pvmw.nr_pages) { page_vma_mapped_walk_done(&pvmw); break; } } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, vm_flags_t *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); /* * PFN swap PTEs, such as device-exclusive ones, that * actually map pages are clean and not writable from a * CPU perspective. The MMU notifier takes care of any * device aspects. */ if (!pte_present(entry)) continue; if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry = pmdp_get(pmd); /* * Please see the comment above (!pte_present). * A non present PMD is not writable from a CPU * perspective. */ if (!pmd_present(entry)) continue; if (!pmd_dirty(entry) && !pmd_write(entry)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); struct wrprotect_file_state { int cleaned; pgoff_t pgoff; unsigned long pfn; unsigned long nr_pages; }; static bool mapping_wrprotect_range_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg; struct page_vma_mapped_walk pvmw = { .pfn = state->pfn, .nr_pages = state->nr_pages, .pgoff = state->pgoff, .vma = vma, .address = address, .flags = PVMW_SYNC, }; state->cleaned += page_vma_mkclean_one(&pvmw); return true; } static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked); /** * mapping_wrprotect_range() - Write-protect all mappings in a specified range. * * @mapping: The mapping whose reverse mapping should be traversed. * @pgoff: The page offset at which @pfn is mapped within @mapping. * @pfn: The PFN of the page mapped in @mapping at @pgoff. * @nr_pages: The number of physically contiguous base pages spanned. * * Traverses the reverse mapping, finding all VMAs which contain a shared * mapping of the pages in the specified range in @mapping, and write-protects * them (that is, updates the page tables to mark the mappings read-only such * that a write protection fault arises when the mappings are written to). * * The @pfn value need not refer to a folio, but rather can reference a kernel * allocation which is mapped into userland. We therefore do not require that * the page maps to a folio with a valid mapping or index field, rather the * caller specifies these in @mapping and @pgoff. * * Return: the number of write-protected PTEs, or an error. */ int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff, unsigned long pfn, unsigned long nr_pages) { struct wrprotect_file_state state = { .cleaned = 0, .pgoff = pgoff, .pfn = pfn, .nr_pages = nr_pages, }; struct rmap_walk_control rwc = { .arg = (void *)&state, .rmap_one = mapping_wrprotect_range_one, .invalid_vma = invalid_mkclean_vma, }; if (!mapping) return 0; __rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc, /* locked = */false); return state.cleaned; } EXPORT_SYMBOL_GPL(mapping_wrprotect_range); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first = 0, nr = 0, nr_pmdmapped = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_add_return_large_mapcount(folio, orig_nr_pages, vma); if (nr == orig_nr_pages) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; folio_add_large_mapcount(folio, orig_nr_pages, vma); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { if (level == PGTABLE_LEVEL_PMD && first) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_inc_return_large_mapcount(folio, vma); if (nr == 1) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); /* * We only track PMD mappings of PMD-sized * folios separately. */ if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } folio_inc_large_mapcount(folio, vma); break; default: BUILD_BUG(); } __folio_mod_stat(folio, nr, nr_pmdmapped); } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += FOLIO_MAPPING_ANON; /* * Ensure that anon_vma and the FOLIO_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the FOLIO_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + FOLIO_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(const struct folio *folio, const struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum pgtable_level level) { int i; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); if (flags & RMAP_EXCLUSIVE) { switch (level) { case PGTABLE_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case PGTABLE_LEVEL_PMD: SetPageAnonExclusive(page); break; case PGTABLE_LEVEL_PUD: /* * Keep the compiler happy, we don't support anonymous * PUD mappings. */ WARN_ON_ONCE(1); break; default: BUILD_BUG(); } } VM_WARN_ON_FOLIO(!folio_test_large(folio) && PageAnonExclusive(page) && atomic_read(&folio->_mapcount) > 0, folio); for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; VM_WARN_ON_FOLIO(folio_test_large(folio) && folio_entire_mapcount(folio) > 1 && PageAnonExclusive(cur_page), folio); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) continue; /* * While PTE-mapping a THP we have a PMD and a PTE * mapping. */ VM_WARN_ON_FOLIO(atomic_read(&cur_page->_mapcount) > 0 && PageAnonExclusive(cur_page), folio); } /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, PGTABLE_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const bool exclusive = flags & RMAP_EXCLUSIVE; int nr = 1, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; nr = folio_large_nr_pages(folio); for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } folio_set_large_mapcount(folio, nr, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, nr); } else { nr = folio_large_nr_pages(folio); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_set_large_mapcount(folio, 1, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } VM_WARN_ON_ONCE(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end); __folio_mod_stat(folio, nr, nr_pmdmapped); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last = 0, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_sub_return_large_mapcount(folio, nr_pages, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = nr < folio_large_nr_pages(folio) && !folio_entire_mapcount(folio); nr = 0; } break; } folio_sub_large_mapcount(folio, nr_pages, vma); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; partially_mapped = nr && atomic_read(mapped); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { last = atomic_add_negative(-1, &folio->_entire_mapcount); if (level == PGTABLE_LEVEL_PMD && last) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_dec_return_large_mapcount(folio, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = last && nr < folio_large_nr_pages(folio); nr = 0; } break; } folio_dec_large_mapcount(folio, vma); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - nr; /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr && nr < nr_pmdmapped; break; default: BUILD_BUG(); } /* * Queue anon large folio for deferred split if at least one page of * the folio is unmapped and at least one page is still mapped. * * Check partially_mapped first to ensure it is a large folio. * * Device private folios do not support deferred splitting and * shrinker based scanning of the folios to free. */ if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio) && !folio_is_device_private(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static inline unsigned int folio_unmap_pte_batch(struct folio *folio, struct page_vma_mapped_walk *pvmw, enum ttu_flags flags, pte_t pte) { unsigned long end_addr, addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; unsigned int max_nr; if (flags & TTU_HWPOISON) return 1; if (!folio_test_large(folio)) return 1; /* We may only batch within a single VMA and a single page table. */ end_addr = pmd_addr_end(addr, vma->vm_end); max_nr = (end_addr - addr) >> PAGE_SHIFT; /* We only support lazyfree or file folios batching for now ... */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) return 1; if (pte_unused(pte)) return 1; if (userfaultfd_wp(vma)) return 1; return folio_pte_batch(folio, pvmw->pte, pte, max_nr); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long nr_pages = 1, end_addr; unsigned long pfn; unsigned long hsz = 0; int ptes = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { ptes++; /* * Set 'ret' to indicate the page cannot be unmapped. * * Do not jump to walk_abort immediately as additional * iteration might be required to detect fully mapped * folio an mlock it. */ ret = false; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) goto walk_done; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); goto walk_done; } if (!pvmw.pte) { if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; /* * unmap_huge_pmd_locked has either already marked * the folio as swap-backed or decided to retain it * due to GUP or speculative references. */ goto walk_abort; } if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); /* Nuke the page table entry. */ pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages); /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ if (should_defer_flush(mm, flags)) set_tlb_ubc_flush_pending(mm, pteval, address, end_addr); else flush_tlb_range(vma, address, end_addr); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else { pte_clear(mm, address, pvmw.pte); } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { /* * redirtied either using the page table or a previously * obtained GUP reference. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); folio_set_swapbacked(folio); goto walk_abort; } else if (ref_count != 1 + map_count) { /* * Additional reference. Could be a GUP reference or any * speculative reference. GUP users must mark the folio * dirty if there was a modification. This folio cannot be * reclaimed right now either way, so act just like nothing * happened. * We'll come back here later and detect if the folio was * dirtied when the additional reference is gone. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); goto walk_abort; } add_mm_counter(mm, MM_ANONPAGES, -nr_pages); goto discard; } if (folio_dup_swap(folio, subpage) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (likely(pte_present(pteval))) { if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ add_mm_counter(mm, mm_counter_file(folio), -nr_pages); } discard: if (unlikely(folio_test_hugetlb(folio))) { hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put_refs(folio, nr_pages); /* * If we are sure that we batched the entire folio and cleared * all PTEs, we can just optimize and stop right here. */ if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, writable, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* PMD-mapped THP migration entry */ if (!pvmw.pte) { __maybe_unused unsigned long pfn; __maybe_unused pmd_t pmdval; if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, true); ret = false; page_vma_mapped_walk_done(&pvmw); break; } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION pmdval = pmdp_get(pvmw.pmd); if (likely(pmd_present(pmdval))) pfn = pmd_pfn(pmdval); else pfn = softleaf_to_pfn(softleaf_from_pmd(pmdval)); subpage = folio_page(folio, pfn - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; #endif } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else if (likely(pte_present(pteval))) { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pte_clear(mm, address, pvmw.pte); writable = softleaf_is_device_private_write(entry); } VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) && !anon_exclusive, folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage)) { VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio); pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else { swp_entry_t entry; pte_t swp_pte; /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (writable) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (likely(pte_present(pteval))) { if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { swp_pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE /** * make_device_exclusive() - Mark a page for exclusive use by a device * @mm: mm_struct of associated target process * @addr: the virtual address to mark for exclusive device access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * @foliop: folio pointer will be stored here on success. * * This function looks up the page mapped at the given address, grabs a * folio reference, locks the folio and replaces the PTE with special * device-exclusive PFN swap entry, preventing access through the process * page tables. The function will return with the folio locked and referenced. * * On fault, the device-exclusive entries are replaced with the original PTE * under folio lock, after calling MMU notifiers. * * Only anonymous non-hugetlb folios are supported and the VMA must have * write permissions such that we can fault in the anonymous page writable * in order to mark it exclusive. The caller must hold the mmap_lock in read * mode. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the folio lock and reference after * which point CPU access to the page will revoke the exclusive access. * * Notes: * #. This function always operates on individual PTEs mapping individual * pages. PMD-sized THPs are first remapped to be mapped by PTEs before * the conversion happens on a single PTE corresponding to @addr. * #. While concurrent access through the process page tables is prevented, * concurrent access through other page references (e.g., earlier GUP * invocation) is not handled and not supported. * #. device-exclusive entries are considered "clean" and "old" by core-mm. * Device drivers must update the folio state when informed by MMU * notifiers. * * Returns: pointer to mapped page on success, otherwise a negative error. */ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, void *owner, struct folio **foliop) { struct mmu_notifier_range range; struct folio *folio, *fw_folio; struct vm_area_struct *vma; struct folio_walk fw; struct page *page; swp_entry_t entry; pte_t swp_pte; int ret; mmap_assert_locked(mm); addr = PAGE_ALIGN_DOWN(addr); /* * Fault in the page writable and try to lock it; note that if the * address would already be marked for exclusive use by a device, * the GUP call would undo that first by triggering a fault. * * If any other device would already map this page exclusively, the * fault will trigger a conversion to an ordinary * (non-device-exclusive) PTE and issue a MMU_NOTIFY_EXCLUSIVE. */ retry: page = get_user_page_vma_remote(mm, addr, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, &vma); if (IS_ERR(page)) return page; folio = page_folio(page); if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) { folio_put(folio); return ERR_PTR(-EOPNOTSUPP); } ret = folio_lock_killable(folio); if (ret) { folio_put(folio); return ERR_PTR(ret); } /* * Inform secondary MMUs that we are going to convert this PTE to * device-exclusive, such that they unmap it now. Note that the * caller must filter this event out to prevent livelocks. */ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, mm, addr, addr + PAGE_SIZE, owner); mmu_notifier_invalidate_range_start(&range); /* * Let's do a second walk and make sure we still find the same page * mapped writable. Note that any page of an anonymous folio can * only be mapped writable using exactly one PTE ("exclusive"), so * there cannot be other mappings. */ fw_folio = folio_walk_start(&fw, vma, addr, 0); if (fw_folio != folio || fw.page != page || fw.level != FW_LEVEL_PTE || !pte_write(fw.pte)) { if (fw_folio) folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); folio_unlock(folio); folio_put(folio); goto retry; } /* Nuke the page table entry so we get the uptodate dirty bit. */ flush_cache_page(vma, addr, page_to_pfn(page)); fw.pte = ptep_clear_flush(vma, addr, fw.ptep); /* Set the dirty flag on the folio now the PTE is gone. */ if (pte_dirty(fw.pte)) folio_mark_dirty(folio); /* * Store the pfn of the page in a special device-exclusive PFN swap PTE. * do_swap_page() will trigger the conversion back while holding the * folio lock. */ entry = make_device_exclusive_entry(page_to_pfn(page)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(fw.pte)) swp_pte = pte_swp_mksoft_dirty(swp_pte); /* The pte is writable, uffd-wp does not apply. */ set_pte_at(mm, addr, fw.ptep, swp_pte); folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); *foliop = folio; return page; } EXPORT_SYMBOL_GPL(make_device_exclusive); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; /* * The folio lock ensures that folio->mapping can't be changed under us * to an anon_vma with different root. */ VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /** * __rmap_walk_file() - Traverse the reverse mapping for a file-backed mapping * of a page mapped within a specified page cache object at a specified offset. * * @folio: Either the folio whose mappings to traverse, or if NULL, * the callbacks specified in @rwc will be configured such * as to be able to look up mappings correctly. * @mapping: The page cache object whose mapping VMAs we intend to * traverse. If @folio is non-NULL, this should be equal to * folio_mapping(folio). * @pgoff_start: The offset within @mapping of the page which we are * looking up. If @folio is non-NULL, this should be equal * to folio_pgoff(folio). * @nr_pages: The number of pages mapped by the mapping. If @folio is * non-NULL, this should be equal to folio_nr_pages(folio). * @rwc: The reverse mapping walk control object describing how * the traversal should proceed. * @locked: Is the @mapping already locked? If not, we acquire the * lock. */ static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked) { pgoff_t pgoff_end = pgoff_start + nr_pages - 1; struct vm_area_struct *vma; VM_WARN_ON_FOLIO(folio && mapping != folio_mapping(folio), folio); VM_WARN_ON_FOLIO(folio && pgoff_start != folio_pgoff(folio), folio); VM_WARN_ON_FOLIO(folio && nr_pages != folio_nr_pages(folio), folio); if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, nr_pages); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { /* * The folio lock not only makes sure that folio->mapping cannot * suddenly be NULLified by truncation, it makes sure that the structure * at mapping cannot be freed and reused yet, so we can safely take * mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio->mapping) return; __rmap_walk_file(folio, folio->mapping, folio->index, folio_nr_pages(folio), rwc, locked); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_mirred.c packet mirroring and redirect actions * * Authors: Jamal Hadi Salim (2002-4) * * TODO: Add ingress support (and socket redirect support) */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <linux/gfp.h> #include <linux/if_arp.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_wrapper.h> static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); static bool tcf_mirred_is_act_redirect(int action) { return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR; } static bool tcf_mirred_act_wants_ingress(int action) { switch (action) { case TCA_EGRESS_REDIR: case TCA_EGRESS_MIRROR: return false; case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: return true; default: BUG(); } } static bool tcf_mirred_can_reinsert(int action) { switch (action) { case TC_ACT_SHOT: case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: return true; } return false; } static struct net_device *tcf_mirred_dev_dereference(struct tcf_mirred *m) { return rcu_dereference_protected(m->tcfm_dev, lockdep_is_held(&m->tcf_lock)); } static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; spin_lock(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock(&mirred_list_lock); /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); netdev_put(dev, &m->tcfm_dev_tracker); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, [TCA_MIRRED_BLOCKID] = NLA_POLICY_MIN(NLA_U32, 1), }; static struct tc_action_ops act_mirred_ops; static void tcf_mirred_replace_dev(struct tcf_mirred *m, struct net_device *ndev) { struct net_device *odev; odev = rcu_replace_pointer(m->tcfm_dev, ndev, lockdep_is_held(&m->tcf_lock)); netdev_put(odev, &m->tcfm_dev_tracker); } static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_mirred_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool mac_header_xmit = false; struct tc_mirred *parm; struct tcf_mirred *m; bool exists = false; int ret, err; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); return -EINVAL; } ret = nla_parse_nested_deprecated(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack); if (ret < 0) return ret; if (!tb[TCA_MIRRED_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters"); return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Cannot specify Block ID and dev simultaneously"); if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } switch (parm->eaction) { case TCA_EGRESS_MIRROR: case TCA_EGRESS_REDIR: case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) { tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Must specify device or block"); return -EINVAL; } ret = tcf_idr_create_from_flags(tn, index, est, a, &act_mirred_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } m = to_mirred(*a); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&m->tcfm_list); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; spin_lock_bh(&m->tcf_lock); if (parm->ifindex) { struct net_device *ndev; ndev = dev_get_by_index(net, parm->ifindex); if (!ndev) { spin_unlock_bh(&m->tcf_lock); err = -ENODEV; goto put_chain; } mac_header_xmit = dev_is_mac_header_xmit(ndev); tcf_mirred_replace_dev(m, ndev); netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; m->tcfm_blockid = 0; } else if (tb[TCA_MIRRED_BLOCKID]) { tcf_mirred_replace_dev(m, NULL); m->tcfm_mac_header_xmit = false; m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]); } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); m->tcfm_eaction = parm->eaction; spin_unlock_bh(&m->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) { spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock(&mirred_list_lock); } return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = tcf_dev_queue_xmit(skb, dev_queue_xmit); else if (!at_ingress) err = netif_rx(skb); else err = netif_receive_skb(skb); return err; } static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, struct net_device *dev, const bool m_mac_header_xmit, int m_eaction, int retval) { struct sk_buff *skb_to_send = skb; bool want_ingress; bool is_redirect; bool expects_nh; bool at_ingress; bool dont_clone; int mac_len; bool at_nh; int err; is_redirect = tcf_mirred_is_act_redirect(m_eaction); if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto err_cant_do; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); at_ingress = skb_at_tc_ingress(skb); if (dev == skb->dev && want_ingress == at_ingress) { pr_notice_once("tc mirred: Loop (%s:%s --> %s:%s)\n", netdev_name(skb->dev), at_ingress ? "ingress" : "egress", netdev_name(dev), want_ingress ? "ingress" : "egress"); goto err_cant_do; } /* we could easily avoid the clone only if called by ingress and clsact; * since we can't easily detect the clsact caller, skip clone only for * ingress - that covers the TC S/W datapath. */ dont_clone = skb_at_tc_ingress(skb) && is_redirect && tcf_mirred_can_reinsert(retval); if (!dont_clone) { skb_to_send = skb_clone(skb, GFP_ATOMIC); if (!skb_to_send) goto err_cant_do; } /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb_to_send); if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ skb_dst_drop(skb_to_send); expects_nh = want_ingress || !m_mac_header_xmit; at_nh = skb->data == skb_network_header(skb); if (at_nh != expects_nh) { mac_len = at_ingress ? skb->mac_len : skb_network_offset(skb); if (expects_nh) { /* target device/action expect data at nh */ skb_pull_rcsum(skb_to_send, mac_len); } else { /* target device/action expect data at mac */ skb_push_rcsum(skb_to_send, mac_len); } } skb_to_send->skb_iif = skb->dev->ifindex; skb_to_send->dev = dev; if (is_redirect) { if (skb == skb_to_send) retval = TC_ACT_CONSUMED; skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } else { err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } if (err) tcf_action_inc_overlimit_qstats(&m->common); return retval; err_cant_do: if (is_redirect) retval = TC_ACT_SHOT; tcf_action_inc_overlimit_qstats(&m->common); return retval; } static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, struct tcf_block *block, int m_eaction, const u32 exception_ifindex, int retval) { struct net_device *dev_prev = NULL; struct net_device *dev = NULL; unsigned long index; int mirred_eaction; mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ? TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR; xa_for_each(&block->ports, index, dev) { if (index == exception_ifindex) continue; if (!dev_prev) goto assign_prev; tcf_mirred_to_dev(skb, m, dev_prev, dev_is_mac_header_xmit(dev), mirred_eaction, retval); assign_prev: dev_prev = dev; } if (dev_prev) return tcf_mirred_to_dev(skb, m, dev_prev, dev_is_mac_header_xmit(dev_prev), m_eaction, retval); return retval; } static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m, struct tcf_block *block, int m_eaction, const u32 exception_ifindex, int retval) { struct net_device *dev = NULL; unsigned long index; xa_for_each(&block->ports, index, dev) { if (index == exception_ifindex) continue; tcf_mirred_to_dev(skb, m, dev, dev_is_mac_header_xmit(dev), m_eaction, retval); } return retval; } static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m, const u32 blockid, struct tcf_result *res, int retval) { const u32 exception_ifindex = skb->dev->ifindex; struct tcf_block *block; bool is_redirect; int m_eaction; m_eaction = READ_ONCE(m->tcfm_eaction); is_redirect = tcf_mirred_is_act_redirect(m_eaction); /* we are already under rcu protection, so can call block lookup * directly. */ block = tcf_block_lookup(dev_net(skb->dev), blockid); if (!block || xa_empty(&block->ports)) { tcf_action_inc_overlimit_qstats(&m->common); return retval; } if (is_redirect) return tcf_blockcast_redir(skb, m, block, m_eaction, exception_ifindex, retval); /* If it's not redirect, it is mirror */ return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex, retval); } TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mirred *m = to_mirred(a); int retval = READ_ONCE(m->tcf_action); struct netdev_xmit *xmit; bool m_mac_header_xmit; struct net_device *dev; int i, m_eaction; u32 blockid; #ifdef CONFIG_PREEMPT_RT xmit = ¤t->net_xmit; #else xmit = this_cpu_ptr(&softnet_data.xmit); #endif if (unlikely(xmit->sched_mirred_nest >= MIRRED_NEST_LIMIT)) { net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", netdev_name(skb->dev)); return TC_ACT_SHOT; } tcf_lastuse_update(&m->tcf_tm); tcf_action_update_bstats(&m->common, skb); blockid = READ_ONCE(m->tcfm_blockid); if (blockid) return tcf_blockcast(skb, m, blockid, res, retval); dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); tcf_action_inc_overlimit_qstats(&m->common); return retval; } for (i = 0; i < xmit->sched_mirred_nest; i++) { if (xmit->sched_mirred_dev[i] != dev) continue; pr_notice_once("tc mirred: loop on device %s\n", netdev_name(dev)); tcf_action_inc_overlimit_qstats(&m->common); return retval; } xmit->sched_mirred_dev[xmit->sched_mirred_nest++] = dev; m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction, retval); xmit->sched_mirred_nest--; return retval; } static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_mirred *m = to_mirred(a); struct tc_mirred opt = { .index = m->tcf_index, .refcnt = refcount_read(&m->tcf_refcnt) - ref, .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, }; struct net_device *dev; struct tcf_t t; u32 blockid; spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; opt.eaction = m->tcfm_eaction; dev = tcf_mirred_dev_dereference(m); if (dev) opt.ifindex = dev->ifindex; if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; blockid = m->tcfm_blockid; if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid)) goto nla_put_failure; tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; spin_unlock_bh(&m->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&m->tcf_lock); nlmsg_trim(skb, b); return -1; } static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) { spin_lock(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { spin_lock_bh(&m->tcf_lock); if (tcf_mirred_dev_dereference(m) == dev) { netdev_put(dev, &m->tcfm_dev_tracker); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } spin_unlock_bh(&m->tcf_lock); } spin_unlock(&mirred_list_lock); } return NOTIFY_DONE; } static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; static void tcf_mirred_dev_put(void *priv) { struct net_device *dev = priv; dev_put(dev); } static struct net_device * tcf_mirred_get_dev(const struct tc_action *a, tc_action_priv_destructor *destructor) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(m->tcfm_dev); if (dev) { dev_hold(dev); *destructor = tcf_mirred_dev_put; } rcu_read_unlock(); return dev; } static size_t tcf_mirred_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_mirred)); } static void tcf_offload_mirred_get_dev(struct flow_action_entry *entry, const struct tc_action *act) { entry->dev = act->ops->get_dev(act, &entry->destructor); if (!entry->dev) return; entry->destructor_priv = entry->dev; } static int tcf_mirred_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; if (is_tcf_mirred_egress_redirect(act)) { entry->id = FLOW_ACTION_REDIRECT; tcf_offload_mirred_get_dev(entry, act); } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; tcf_offload_mirred_get_dev(entry, act); } else if (is_tcf_mirred_ingress_redirect(act)) { entry->id = FLOW_ACTION_REDIRECT_INGRESS; tcf_offload_mirred_get_dev(entry, act); } else if (is_tcf_mirred_ingress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED_INGRESS; tcf_offload_mirred_get_dev(entry, act); } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported mirred offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; if (is_tcf_mirred_egress_redirect(act)) fl_action->id = FLOW_ACTION_REDIRECT; else if (is_tcf_mirred_egress_mirror(act)) fl_action->id = FLOW_ACTION_MIRRED; else if (is_tcf_mirred_ingress_redirect(act)) fl_action->id = FLOW_ACTION_REDIRECT_INGRESS; else if (is_tcf_mirred_ingress_mirror(act)) fl_action->id = FLOW_ACTION_MIRRED_INGRESS; else return -EOPNOTSUPP; } return 0; } static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .id = TCA_ID_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred_act, .stats_update = tcf_stats_update, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_release, .init = tcf_mirred_init, .get_fill_size = tcf_mirred_get_fill_size, .offload_act_setup = tcf_mirred_offload_act_setup, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, }; MODULE_ALIAS_NET_ACT("mirred"); static __net_init int mirred_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_mirred_ops.net_id); return tc_action_net_init(net, tn, &act_mirred_ops); } static void __net_exit mirred_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_mirred_ops.net_id); } static struct pernet_operations mirred_net_ops = { .init = mirred_init_net, .exit_batch = mirred_exit_net, .id = &act_mirred_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); MODULE_DESCRIPTION("Device Mirror/redirect actions"); MODULE_LICENSE("GPL"); static int __init mirred_init_module(void) { int err = register_netdevice_notifier(&mirred_device_notifier); if (err) return err; pr_info("Mirror/redirect action on\n"); err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); if (err) unregister_netdevice_notifier(&mirred_device_notifier); return err; } static void __exit mirred_cleanup_module(void) { tcf_unregister_action(&act_mirred_ops, &mirred_net_ops); unregister_netdevice_notifier(&mirred_device_notifier); } module_init(mirred_init_module); module_exit(mirred_cleanup_module); |
| 75 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SHMEM_FS_H #define __SHMEM_FS_H #include <linux/file.h> #include <linux/swap.h> #include <linux/mempolicy.h> #include <linux/pagemap.h> #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> #include <linux/userfaultfd_k.h> #include <linux/bits.h> struct swap_iocb; /* inode in-kernel data */ #ifdef CONFIG_TMPFS_QUOTA #define SHMEM_MAXQUOTAS 2 #endif /* Suppress pre-accounting of the entire object size. */ #define SHMEM_F_NORESERVE BIT(0) /* Disallow swapping. */ #define SHMEM_F_LOCKED BIT(1) /* * Disallow growing, shrinking, or hole punching in the inode. Combined with * folio pinning, makes sure the inode's mapping stays fixed. * * In some ways similar to F_SEAL_GROW | F_SEAL_SHRINK, but can be removed and * isn't directly visible to userspace. */ #define SHMEM_F_MAPPING_FROZEN BIT(2) struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ union { struct offset_ctx dir_offsets; /* stable directory offsets */ struct { struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ }; }; struct timespec64 i_crtime; /* file creation time */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ pgoff_t fallocend; /* highest fallocate endindex */ unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ #ifdef CONFIG_TMPFS_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; }; #define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) #define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */ qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */ qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */ }; struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_ispace; /* How much ispace left for allocation */ raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ unsigned long shrinklist_len; /* Length of shrinklist */ struct shmem_quota_limits qlimits; /* Default quota limits */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) { return container_of(inode, struct shmem_inode_info, vfs_inode); } /* * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); struct file *shmem_file_setup(const char *name, loff_t size, vma_flags_t flags); struct file *shmem_kernel_file_setup(const char *name, loff_t size, vma_flags_t vma_flags); extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, vma_flags_t flags); int shmem_zero_setup(struct vm_area_struct *vma); int shmem_zero_setup_desc(struct vm_area_desc *desc); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM bool shmem_mapping(const struct address_space *mapping); #else static inline bool shmem_mapping(const struct address_space *mapping) { return false; } #endif /* CONFIG_SHMEM */ void shmem_unlock_mapping(struct address_space *mapping); struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int shmem_writeout(struct folio *folio, struct swap_iocb **plug, struct list_head *folio_list); void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force); bool shmem_hpage_pmd_enabled(void); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force) { return 0; } static inline bool shmem_hpage_pmd_enabled(void) { return false; } #endif #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern void shmem_uncharge(struct inode *inode, long pages); #else static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) { return 0; } static inline void shmem_uncharge(struct inode *inode, long pages) { } #endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); /* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, struct folio **foliop, enum sgp_type sgp); struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp); static inline struct folio *shmem_read_folio(struct address_space *mapping, pgoff_t index) { return shmem_read_folio_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { return shmem_read_mapping_page_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline bool shmem_file(struct file *file) { if (!IS_ENABLED(CONFIG_SHMEM)) return false; if (!file || !file->f_mapping) return false; return shmem_mapping(file->f_mapping); } /* Must be called with inode lock taken exclusive. */ static inline void shmem_freeze(struct inode *inode, bool freeze) { if (freeze) SHMEM_I(inode)->flags |= SHMEM_F_MAPPING_FROZEN; else SHMEM_I(inode)->flags &= ~SHMEM_F_MAPPING_FROZEN; } /* * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages * beyond i_size's notion of EOF, which fallocate has committed to reserving: * which split_huge_page() must therefore not delete. This use of a single * "fallocend" per inode errs on the side of not deleting a reservation when * in doubt: there are plenty of cases when it preserves unreserved pages. */ static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof) { return max(eof, SHMEM_I(inode)->fallocend); } extern bool shmem_charge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ #define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */ #define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL #ifdef CONFIG_TMPFS_QUOTA extern const struct dquot_operations shmem_quota_operations; extern struct quota_format_type shmem_quota_format; #endif /* CONFIG_TMPFS_QUOTA */ #endif |
| 4 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #include <linux/init.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/dma-mapping.h> #include <net/addrconf.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/rdma_netlink.h> #include <linux/kthread.h> #include "siw.h" #include "siw_verbs.h" MODULE_AUTHOR("Bernard Metzler"); MODULE_DESCRIPTION("Software iWARP Driver"); MODULE_LICENSE("Dual BSD/GPL"); /* transmit from user buffer, if possible */ const bool zcopy_tx = true; /* Restrict usage of GSO, if hardware peer iwarp is unable to process * large packets. try_gso = true lets siw try to use local GSO, * if peer agrees. Not using GSO severly limits siw maximum tx bandwidth. */ const bool try_gso; /* Attach siw also with loopback devices */ const bool loopback_enabled = true; /* We try to negotiate CRC on, if true */ const bool mpa_crc_required; /* MPA CRC on/off enforced */ const bool mpa_crc_strict; /* Control TCP_NODELAY socket option */ const bool siw_tcp_nagle; /* Select MPA version to be used during connection setup */ u_char mpa_version = MPA_REVISION_2; /* Selects MPA P2P mode (additional handshake during connection * setup, if true. */ const bool peer_to_peer; struct task_struct *siw_tx_thread[NR_CPUS]; static int siw_device_register(struct siw_device *sdev, const char *name) { struct ib_device *base_dev = &sdev->base_dev; static int dev_id = 1; int rv; sdev->vendor_part_id = dev_id++; rv = ib_register_device(base_dev, name, NULL); if (rv) { pr_warn("siw: device registration error %d\n", rv); return rv; } siw_dbg(base_dev, "HWaddr=%pM\n", sdev->raw_gid); return 0; } static void siw_device_cleanup(struct ib_device *base_dev) { struct siw_device *sdev = to_siw_dev(base_dev); xa_destroy(&sdev->qp_xa); xa_destroy(&sdev->mem_xa); } static int siw_dev_qualified(struct net_device *netdev) { /* * Additional hardware support can be added here * (e.g. ARPHRD_FDDI, ARPHRD_ATM, ...) - see * <linux/if_arp.h> for type identifiers. */ if (netdev->type == ARPHRD_ETHER || netdev->type == ARPHRD_IEEE802 || netdev->type == ARPHRD_NONE || (netdev->type == ARPHRD_LOOPBACK && loopback_enabled)) return 1; return 0; } static DEFINE_PER_CPU(atomic_t, siw_use_cnt); static struct { struct cpumask **tx_valid_cpus; int num_nodes; } siw_cpu_info; static void siw_destroy_cpulist(int number) { int i = 0; while (i < number) kfree(siw_cpu_info.tx_valid_cpus[i++]); kfree(siw_cpu_info.tx_valid_cpus); siw_cpu_info.tx_valid_cpus = NULL; } static int siw_init_cpulist(void) { int i, num_nodes = nr_node_ids; memset(siw_tx_thread, 0, sizeof(siw_tx_thread)); siw_cpu_info.num_nodes = num_nodes; siw_cpu_info.tx_valid_cpus = kzalloc_objs(struct cpumask *, num_nodes); if (!siw_cpu_info.tx_valid_cpus) { siw_cpu_info.num_nodes = 0; return -ENOMEM; } for (i = 0; i < siw_cpu_info.num_nodes; i++) { siw_cpu_info.tx_valid_cpus[i] = kzalloc_obj(struct cpumask); if (!siw_cpu_info.tx_valid_cpus[i]) goto out_err; cpumask_clear(siw_cpu_info.tx_valid_cpus[i]); } for_each_possible_cpu(i) cpumask_set_cpu(i, siw_cpu_info.tx_valid_cpus[cpu_to_node(i)]); return 0; out_err: siw_cpu_info.num_nodes = 0; siw_destroy_cpulist(i); return -ENOMEM; } /* * Choose CPU with least number of active QP's from NUMA node of * TX interface. */ int siw_get_tx_cpu(struct siw_device *sdev) { const struct cpumask *tx_cpumask; int i, num_cpus, cpu, min_use, node = sdev->numa_node, tx_cpu = -1; if (node < 0) tx_cpumask = cpu_online_mask; else tx_cpumask = siw_cpu_info.tx_valid_cpus[node]; num_cpus = cpumask_weight(tx_cpumask); if (!num_cpus) { /* no CPU on this NUMA node */ tx_cpumask = cpu_online_mask; num_cpus = cpumask_weight(tx_cpumask); } if (!num_cpus) goto out; cpu = cpumask_first(tx_cpumask); for (i = 0, min_use = SIW_MAX_QP; i < num_cpus; i++, cpu = cpumask_next(cpu, tx_cpumask)) { int usage; /* Skip any cores which have no TX thread */ if (!siw_tx_thread[cpu]) continue; usage = atomic_read(&per_cpu(siw_use_cnt, cpu)); if (usage <= min_use) { tx_cpu = cpu; min_use = usage; } } siw_dbg(&sdev->base_dev, "tx cpu %d, node %d, %d qp's\n", tx_cpu, node, min_use); out: if (tx_cpu >= 0) atomic_inc(&per_cpu(siw_use_cnt, tx_cpu)); else pr_warn("siw: no tx cpu found\n"); return tx_cpu; } void siw_put_tx_cpu(int cpu) { atomic_dec(&per_cpu(siw_use_cnt, cpu)); } static struct ib_qp *siw_get_base_qp(struct ib_device *base_dev, int id) { struct siw_qp *qp = siw_qp_id2obj(to_siw_dev(base_dev), id); if (qp) { /* * siw_qp_id2obj() increments object reference count */ siw_qp_put(qp); return &qp->base_qp; } return NULL; } static const struct ib_device_ops siw_device_ops = { .owner = THIS_MODULE, .uverbs_abi_ver = SIW_ABI_VERSION, .driver_id = RDMA_DRIVER_SIW, .alloc_mr = siw_alloc_mr, .alloc_pd = siw_alloc_pd, .alloc_ucontext = siw_alloc_ucontext, .create_cq = siw_create_cq, .create_qp = siw_create_qp, .create_srq = siw_create_srq, .dealloc_driver = siw_device_cleanup, .dealloc_pd = siw_dealloc_pd, .dealloc_ucontext = siw_dealloc_ucontext, .dereg_mr = siw_dereg_mr, .destroy_cq = siw_destroy_cq, .destroy_qp = siw_destroy_qp, .destroy_srq = siw_destroy_srq, .get_dma_mr = siw_get_dma_mr, .get_port_immutable = siw_get_port_immutable, .iw_accept = siw_accept, .iw_add_ref = siw_qp_get_ref, .iw_connect = siw_connect, .iw_create_listen = siw_create_listen, .iw_destroy_listen = siw_destroy_listen, .iw_get_qp = siw_get_base_qp, .iw_reject = siw_reject, .iw_rem_ref = siw_qp_put_ref, .map_mr_sg = siw_map_mr_sg, .mmap = siw_mmap, .mmap_free = siw_mmap_free, .modify_qp = siw_verbs_modify_qp, .modify_srq = siw_modify_srq, .poll_cq = siw_poll_cq, .post_recv = siw_post_receive, .post_send = siw_post_send, .post_srq_recv = siw_post_srq_recv, .query_device = siw_query_device, .query_gid = siw_query_gid, .query_port = siw_query_port, .query_qp = siw_query_qp, .query_srq = siw_query_srq, .req_notify_cq = siw_req_notify_cq, .reg_user_mr = siw_reg_user_mr, INIT_RDMA_OBJ_SIZE(ib_cq, siw_cq, base_cq), INIT_RDMA_OBJ_SIZE(ib_pd, siw_pd, base_pd), INIT_RDMA_OBJ_SIZE(ib_qp, siw_qp, base_qp), INIT_RDMA_OBJ_SIZE(ib_srq, siw_srq, base_srq), INIT_RDMA_OBJ_SIZE(ib_ucontext, siw_ucontext, base_ucontext), }; static struct siw_device *siw_device_create(struct net_device *netdev) { struct siw_device *sdev = NULL; struct ib_device *base_dev; int rv; sdev = ib_alloc_device(siw_device, base_dev); if (!sdev) return NULL; base_dev = &sdev->base_dev; if (netdev->addr_len) { memcpy(sdev->raw_gid, netdev->dev_addr, min_t(unsigned int, netdev->addr_len, ETH_ALEN)); } else { /* * This device does not have a HW address, but * connection mangagement requires a unique gid. */ eth_random_addr(sdev->raw_gid); } addrconf_addr_eui48((u8 *)&base_dev->node_guid, sdev->raw_gid); base_dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND); base_dev->node_type = RDMA_NODE_RNIC; memcpy(base_dev->node_desc, SIW_NODE_DESC_COMMON, sizeof(SIW_NODE_DESC_COMMON)); /* * Current model (one-to-one device association): * One Softiwarp device per net_device or, equivalently, * per physical port. */ base_dev->phys_port_cnt = 1; base_dev->num_comp_vectors = num_possible_cpus(); xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1); ib_set_device_ops(base_dev, &siw_device_ops); rv = ib_device_set_netdev(base_dev, netdev, 1); if (rv) goto error; memcpy(base_dev->iw_ifname, netdev->name, sizeof(base_dev->iw_ifname)); /* Disable TCP port mapping */ base_dev->iw_driver_flags = IW_F_NO_PORT_MAP; sdev->attrs.max_qp = SIW_MAX_QP; sdev->attrs.max_qp_wr = SIW_MAX_QP_WR; sdev->attrs.max_ord = SIW_MAX_ORD_QP; sdev->attrs.max_ird = SIW_MAX_IRD_QP; sdev->attrs.max_sge = SIW_MAX_SGE; sdev->attrs.max_sge_rd = SIW_MAX_SGE_RD; sdev->attrs.max_cq = SIW_MAX_CQ; sdev->attrs.max_cqe = SIW_MAX_CQE; sdev->attrs.max_mr = SIW_MAX_MR; sdev->attrs.max_pd = SIW_MAX_PD; sdev->attrs.max_mw = SIW_MAX_MW; sdev->attrs.max_srq = SIW_MAX_SRQ; sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR; sdev->attrs.max_srq_sge = SIW_MAX_SGE; INIT_LIST_HEAD(&sdev->cep_list); INIT_LIST_HEAD(&sdev->qp_list); atomic_set(&sdev->num_ctx, 0); atomic_set(&sdev->num_srq, 0); atomic_set(&sdev->num_qp, 0); atomic_set(&sdev->num_cq, 0); atomic_set(&sdev->num_mr, 0); atomic_set(&sdev->num_pd, 0); sdev->numa_node = dev_to_node(&netdev->dev); spin_lock_init(&sdev->lock); return sdev; error: ib_dealloc_device(base_dev); return NULL; } static int siw_netdev_event(struct notifier_block *nb, unsigned long event, void *arg) { struct net_device *netdev = netdev_notifier_info_to_dev(arg); struct ib_device *base_dev; struct siw_device *sdev; dev_dbg(&netdev->dev, "siw: event %lu\n", event); base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (!base_dev) return NOTIFY_OK; sdev = to_siw_dev(base_dev); switch (event) { case NETDEV_REGISTER: /* * Device registration now handled only by * rdma netlink commands. So it shall be impossible * to end up here with a valid siw device. */ siw_dbg(base_dev, "unexpected NETDEV_REGISTER event\n"); break; case NETDEV_UNREGISTER: ib_unregister_device_queued(&sdev->base_dev); break; case NETDEV_CHANGEADDR: siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* * All other events are not handled */ default: break; } ib_device_put(&sdev->base_dev); return NOTIFY_OK; } static struct notifier_block siw_netdev_nb = { .notifier_call = siw_netdev_event, }; static int siw_newlink(const char *basedev_name, struct net_device *netdev) { struct ib_device *base_dev; struct siw_device *sdev = NULL; int rv = -ENOMEM; if (!siw_dev_qualified(netdev)) return -EINVAL; base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (base_dev) { ib_device_put(base_dev); return -EEXIST; } sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); ib_mark_name_assigned_by_user(&sdev->base_dev); rv = siw_device_register(sdev, basedev_name); if (rv) ib_dealloc_device(&sdev->base_dev); } return rv; } static struct rdma_link_ops siw_link_ops = { .type = "siw", .newlink = siw_newlink, }; /* * siw_init_module - Initialize Softiwarp module and register with netdev * subsystem. */ static __init int siw_init_module(void) { int rv; if (SENDPAGE_THRESH < SIW_MAX_INLINE) { pr_info("siw: sendpage threshold too small: %u\n", (int)SENDPAGE_THRESH); rv = -EINVAL; goto out_error; } rv = siw_init_cpulist(); if (rv) goto out_error; rv = siw_cm_init(); if (rv) goto out_error; if (!siw_create_tx_threads()) { pr_info("siw: Could not start any TX thread\n"); rv = -ENOMEM; goto out_error; } rv = register_netdevice_notifier(&siw_netdev_nb); if (rv) goto out_error; rdma_link_register(&siw_link_ops); pr_info("SoftiWARP attached\n"); return 0; out_error: siw_stop_tx_threads(); pr_info("SoftIWARP attach failed. Error: %d\n", rv); siw_cm_exit(); siw_destroy_cpulist(siw_cpu_info.num_nodes); return rv; } static void __exit siw_exit_module(void) { siw_stop_tx_threads(); unregister_netdevice_notifier(&siw_netdev_nb); rdma_link_unregister(&siw_link_ops); ib_unregister_driver(RDMA_DRIVER_SIW); siw_cm_exit(); siw_destroy_cpulist(siw_cpu_info.num_nodes); pr_info("SoftiWARP detached\n"); } module_init(siw_init_module); module_exit(siw_exit_module); MODULE_ALIAS_RDMA_LINK("siw"); |
| 3 5 3 2 12 3 1 1 2 5 8 | 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2020 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <kvm/arm_hypercalls.h> #define ARM_SMCCC_TRNG_VERSION_1_0 0x10000UL /* Those values are deliberately separate from the generic SMCCC definitions. */ #define TRNG_SUCCESS 0UL #define TRNG_NOT_SUPPORTED ((unsigned long)-1) #define TRNG_INVALID_PARAMETER ((unsigned long)-2) #define TRNG_NO_ENTROPY ((unsigned long)-3) #define TRNG_MAX_BITS64 192 static const uuid_t arm_smc_trng_uuid __aligned(4) = UUID_INIT( 0x0d21e000, 0x4384, 0x11eb, 0x80, 0x70, 0x52, 0x44, 0x55, 0x4e, 0x5a, 0x4c); static int kvm_trng_do_rnd(struct kvm_vcpu *vcpu, int size) { DECLARE_BITMAP(bits, TRNG_MAX_BITS64); u32 num_bits = smccc_get_arg1(vcpu); int i; if (num_bits > 3 * size) { smccc_set_retval(vcpu, TRNG_INVALID_PARAMETER, 0, 0, 0); return 1; } /* get as many bits as we need to fulfil the request */ for (i = 0; i < DIV_ROUND_UP(num_bits, BITS_PER_LONG); i++) bits[i] = get_random_long(); bitmap_clear(bits, num_bits, TRNG_MAX_BITS64 - num_bits); if (size == 32) smccc_set_retval(vcpu, TRNG_SUCCESS, lower_32_bits(bits[1]), upper_32_bits(bits[0]), lower_32_bits(bits[0])); else smccc_set_retval(vcpu, TRNG_SUCCESS, bits[2], bits[1], bits[0]); memzero_explicit(bits, sizeof(bits)); return 1; } int kvm_trng_call(struct kvm_vcpu *vcpu) { const __le32 *u = (__le32 *)arm_smc_trng_uuid.b; u32 func_id = smccc_get_function(vcpu); unsigned long val = TRNG_NOT_SUPPORTED; int size = 64; switch (func_id) { case ARM_SMCCC_TRNG_VERSION: val = ARM_SMCCC_TRNG_VERSION_1_0; break; case ARM_SMCCC_TRNG_FEATURES: switch (smccc_get_arg1(vcpu)) { case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: val = TRNG_SUCCESS; } break; case ARM_SMCCC_TRNG_GET_UUID: smccc_set_retval(vcpu, le32_to_cpu(u[0]), le32_to_cpu(u[1]), le32_to_cpu(u[2]), le32_to_cpu(u[3])); return 1; case ARM_SMCCC_TRNG_RND32: size = 32; fallthrough; case ARM_SMCCC_TRNG_RND64: return kvm_trng_do_rnd(vcpu, size); } smccc_set_retval(vcpu, val, 0, 0, 0); return 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/crc-ccitt.h> #include <linux/export.h> #include <linux/module.h> #include <linux/types.h> /* * This mysterious table is just the CRC of each possible byte. It can be * computed using the standard bit-at-a-time methods. The polynomial can * be seen in entry 128, 0x8408. This corresponds to x^0 + x^5 + x^12. * Add the implicit x^16, and you have the standard CRC-CCITT. */ u16 const crc_ccitt_table[256] = { 0x0000, 0x1189, 0x2312, 0x329b, 0x4624, 0x57ad, 0x6536, 0x74bf, 0x8c48, 0x9dc1, 0xaf5a, 0xbed3, 0xca6c, 0xdbe5, 0xe97e, 0xf8f7, 0x1081, 0x0108, 0x3393, 0x221a, 0x56a5, 0x472c, 0x75b7, 0x643e, 0x9cc9, 0x8d40, 0xbfdb, 0xae52, 0xdaed, 0xcb64, 0xf9ff, 0xe876, 0x2102, 0x308b, 0x0210, 0x1399, 0x6726, 0x76af, 0x4434, 0x55bd, 0xad4a, 0xbcc3, 0x8e58, 0x9fd1, 0xeb6e, 0xfae7, 0xc87c, 0xd9f5, 0x3183, 0x200a, 0x1291, 0x0318, 0x77a7, 0x662e, 0x54b5, 0x453c, 0xbdcb, 0xac42, 0x9ed9, 0x8f50, 0xfbef, 0xea66, 0xd8fd, 0xc974, 0x4204, 0x538d, 0x6116, 0x709f, 0x0420, 0x15a9, 0x2732, 0x36bb, 0xce4c, 0xdfc5, 0xed5e, 0xfcd7, 0x8868, 0x99e1, 0xab7a, 0xbaf3, 0x5285, 0x430c, 0x7197, 0x601e, 0x14a1, 0x0528, 0x37b3, 0x263a, 0xdecd, 0xcf44, 0xfddf, 0xec56, 0x98e9, 0x8960, 0xbbfb, 0xaa72, 0x6306, 0x728f, 0x4014, 0x519d, 0x2522, 0x34ab, 0x0630, 0x17b9, 0xef4e, 0xfec7, 0xcc5c, 0xddd5, 0xa96a, 0xb8e3, 0x8a78, 0x9bf1, 0x7387, 0x620e, 0x5095, 0x411c, 0x35a3, 0x242a, 0x16b1, 0x0738, 0xffcf, 0xee46, 0xdcdd, 0xcd54, 0xb9eb, 0xa862, 0x9af9, 0x8b70, 0x8408, 0x9581, 0xa71a, 0xb693, 0xc22c, 0xd3a5, 0xe13e, 0xf0b7, 0x0840, 0x19c9, 0x2b52, 0x3adb, 0x4e64, 0x5fed, 0x6d76, 0x7cff, 0x9489, 0x8500, 0xb79b, 0xa612, 0xd2ad, 0xc324, 0xf1bf, 0xe036, 0x18c1, 0x0948, 0x3bd3, 0x2a5a, 0x5ee5, 0x4f6c, 0x7df7, 0x6c7e, 0xa50a, 0xb483, 0x8618, 0x9791, 0xe32e, 0xf2a7, 0xc03c, 0xd1b5, 0x2942, 0x38cb, 0x0a50, 0x1bd9, 0x6f66, 0x7eef, 0x4c74, 0x5dfd, 0xb58b, 0xa402, 0x9699, 0x8710, 0xf3af, 0xe226, 0xd0bd, 0xc134, 0x39c3, 0x284a, 0x1ad1, 0x0b58, 0x7fe7, 0x6e6e, 0x5cf5, 0x4d7c, 0xc60c, 0xd785, 0xe51e, 0xf497, 0x8028, 0x91a1, 0xa33a, 0xb2b3, 0x4a44, 0x5bcd, 0x6956, 0x78df, 0x0c60, 0x1de9, 0x2f72, 0x3efb, 0xd68d, 0xc704, 0xf59f, 0xe416, 0x90a9, 0x8120, 0xb3bb, 0xa232, 0x5ac5, 0x4b4c, 0x79d7, 0x685e, 0x1ce1, 0x0d68, 0x3ff3, 0x2e7a, 0xe70e, 0xf687, 0xc41c, 0xd595, 0xa12a, 0xb0a3, 0x8238, 0x93b1, 0x6b46, 0x7acf, 0x4854, 0x59dd, 0x2d62, 0x3ceb, 0x0e70, 0x1ff9, 0xf78f, 0xe606, 0xd49d, 0xc514, 0xb1ab, 0xa022, 0x92b9, 0x8330, 0x7bc7, 0x6a4e, 0x58d5, 0x495c, 0x3de3, 0x2c6a, 0x1ef1, 0x0f78 }; EXPORT_SYMBOL(crc_ccitt_table); /** * crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data * buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer */ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len) { while (len--) crc = crc_ccitt_byte(crc, *buffer++); return crc; } EXPORT_SYMBOL(crc_ccitt); MODULE_DESCRIPTION("CRC-CCITT calculations"); MODULE_LICENSE("GPL"); |
| 7 7 | 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 | #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 38 | 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 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> #include <linux/fs_struct.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW BIT(0) /* follow links at the end */ #define LOOKUP_DIRECTORY BIT(1) /* require a directory */ #define LOOKUP_AUTOMOUNT BIT(2) /* force terminal automount */ #define LOOKUP_EMPTY BIT(3) /* accept empty path [user_... only] */ #define LOOKUP_LINKAT_EMPTY BIT(4) /* Linkat request with empty path. */ #define LOOKUP_DOWN BIT(5) /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT BIT(6) /* follow mounts in the end */ #define LOOKUP_REVAL BIT(7) /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU BIT(8) /* RCU pathwalk mode; semi-internal */ #define LOOKUP_CACHED BIT(9) /* Only do cached lookup */ #define LOOKUP_PARENT BIT(10) /* Looking up final parent in path */ /* 5 spare bits for pathwalk */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN BIT(16) /* ... in open */ #define LOOKUP_CREATE BIT(17) /* ... in object creation */ #define LOOKUP_EXCL BIT(18) /* ... in target must not exist */ #define LOOKUP_RENAME_TARGET BIT(19) /* ... in destination of rename() */ /* 4 spare bits for intent */ /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS BIT(24) /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS BIT(25) /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV BIT(26) /* No mountpoint crossing. */ #define LOOKUP_BENEATH BIT(27) /* No escaping from starting point. */ #define LOOKUP_IN_ROOT BIT(28) /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) /* 3 spare bits for scoping */ extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); struct dentry *kern_path_parent(const char *name, struct path *parent); extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int); extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int); extern void end_creating_path(const struct path *, struct dentry *); extern struct dentry *start_removing_path(const char *, struct path *); extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *); static inline void end_removing_path(const struct path *path , struct dentry *dentry) { end_creating_path(path, dentry); } int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_unlocked(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_positive_unlocked(struct qstr *, struct dentry *); struct dentry *lookup_one(struct mnt_idmap *, struct qstr *, struct dentry *); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_creating_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_removing_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name); struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name); struct dentry *start_creating_dentry(struct dentry *parent, struct dentry *child); struct dentry *start_removing_dentry(struct dentry *parent, struct dentry *child); /* end_creating - finish action started with start_creating * @child: dentry returned by start_creating() or vfs_mkdir() * * Unlock and release the child. This can be called after * start_creating() whether that function succeeded or not, * but it is not needed on failure. * * If vfs_mkdir() was called then the value returned from that function * should be given for @child rather than the original dentry, as vfs_mkdir() * may have provided a new dentry. * * * If vfs_mkdir() was not called, then @child will be a valid dentry and * @parent will be ignored. */ static inline void end_creating(struct dentry *child) { end_dirop(child); } /* end_creating_keep - finish action started with start_creating() and return result * @child: dentry returned by start_creating() or vfs_mkdir() * * Unlock and return the child. This can be called after * start_creating() whether that function succeeded or not, * but it is not needed on failure. * * If vfs_mkdir() was called then the value returned from that function * should be given for @child rather than the original dentry, as vfs_mkdir() * may have provided a new dentry. * * Returns: @child, which may be a dentry or an error. * */ static inline struct dentry *end_creating_keep(struct dentry *child) { if (!IS_ERR(child)) dget(child); end_dirop(child); return child; } /** * end_removing - finish action started with start_removing * @child: dentry returned by start_removing() * @parent: dentry given to start_removing() * * Unlock and release the child. * * This is identical to end_dirop(). It can be passed the result of * start_removing() whether that was successful or not, but it not needed * if start_removing() failed. */ static inline void end_removing(struct dentry *child) { end_dirop(child); } extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); int start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last); int start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last); int start_renaming_two_dentries(struct renamedata *rd, struct dentry *old_dentry, struct dentry *new_dentry); void end_renaming(struct renamedata *rd); /** * 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 * * In most filesystems, 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(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_GENERIC_NETLINK_H #define __NET_GENERIC_NETLINK_H #include <linux/net.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <uapi/linux/genetlink.h> #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) /* Non-parallel generic netlink requests are serialized by a global lock. */ void genl_lock(void); void genl_unlock(void); #define MODULE_ALIAS_GENL_FAMILY(family) \ MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) /* Binding to multicast group requires %CAP_NET_ADMIN */ #define GENL_MCAST_CAP_NET_ADMIN BIT(0) /* Binding to multicast group requires %CAP_SYS_ADMIN */ #define GENL_MCAST_CAP_SYS_ADMIN BIT(1) /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family * @flags: GENL_MCAST_* flags */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; }; struct genl_split_ops; struct genl_info; /** * struct genl_family - generic netlink family * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version * @maxattr: maximum number of attributes supported * @policy: netlink policy * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them * @parallel_ops: operations can be called in parallel and aren't * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks * @bind: called when family multicast group is added to a netlink socket * @unbind: called when family multicast group is removed from a netlink socket * @module: pointer to the owning module (set to THIS_MODULE) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header * can be validated and policies are required (see below); * new families should leave this field at zero * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family * @split_ops: the split do/dump form of operation definition * @n_split_ops: number of entries in @split_ops, note that with split do/dump * ops the number of entries is not the same as number of commands * @sock_priv_size: the size of per-socket private memory * @sock_priv_init: the per-socket private memory initializer * @sock_priv_destroy: the per-socket private memory destructor * * Attribute policies (the combination of @policy and @maxattr fields) * can be attached at the family level or at the operation level. * If both are present the per-operation policy takes precedence. * For operations before @resv_start_op lack of policy means that the core * will perform no attribute parsing or validation. For newer operations * if policy is not provided core will reject all TLV attributes. */ struct genl_family { unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; u8 n_small_ops; u8 n_split_ops; u8 n_mcgrps; u8 resv_start_op; const struct nla_policy *policy; int (*pre_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); void (*post_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); int (*bind)(int mcgrp); void (*unbind)(int mcgrp); const struct genl_ops * ops; const struct genl_small_ops *small_ops; const struct genl_split_ops *split_ops; const struct genl_multicast_group *mcgrps; struct module *module; size_t sock_priv_size; void (*sock_priv_init)(void *priv); void (*sock_priv_destroy)(void *priv); /* private: internal use only */ /* protocol family identifier */ int id; /* starting number of multicast group IDs in this family */ unsigned int mcgrp_offset; /* list of per-socket privs */ struct xarray *sock_privs; }; /** * struct genl_info - receiving information * @snd_seq: sending sequence number * @snd_portid: netlink portid of sender * @family: generic netlink family * @nlhdr: netlink message header * @genlhdr: generic netlink message header * @attrs: netlink attributes * @_net: network namespace * @ctx: storage space for the use by the family * @user_ptr: user pointers (deprecated, use ctx instead) * @extack: extended ACK report struct */ struct genl_info { u32 snd_seq; u32 snd_portid; const struct genl_family *family; const struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; struct nlattr ** attrs; possible_net_t _net; union { u8 ctx[NETLINK_CTX_SIZE]; void * user_ptr[2]; }; struct netlink_ext_ack *extack; }; static inline struct net *genl_info_net(const struct genl_info *info) { return read_pnet(&info->_net); } static inline void genl_info_net_set(struct genl_info *info, struct net *net) { write_pnet(&info->_net, net); } static inline void *genl_info_userhdr(const struct genl_info *info) { return (u8 *)info->genlhdr + GENL_HDRLEN; } #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) #define GENL_SET_ERR_MSG_FMT(info, msg, args...) \ NL_SET_ERR_MSG_FMT((info)->extack, msg, ##args) /* Report that a root attribute is missing */ #define GENL_REQ_ATTR_CHECK(info, attr) ({ \ const struct genl_info *__info = (info); \ \ NL_REQ_ATTR_CHECK(__info->extack, NULL, __info->attrs, (attr)); \ }) enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), GENL_DONT_VALIDATE_DUMP_STRICT = BIT(2), }; /** * struct genl_small_ops - generic netlink operations (small version) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @dumpit: callback for dumpers * * This is a cut-down version of struct genl_ops for users who don't need * most of the ancillary infra and want to save space. */ struct genl_small_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) * @maxattr: maximum number of attributes supported * @policy: netlink policy (takes precedence over family policy) * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps */ struct genl_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); const struct nla_policy *policy; unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_split_ops - generic netlink operations (do/dump split version) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) * @validate: validation flags from enum genl_validate_flags * @policy: netlink policy (takes precedence over family policy) * @maxattr: maximum number of attributes supported * * Do callbacks: * @pre_doit: called before an operation's @doit callback, it may * do additional, common, filtering and return an error * @doit: standard command callback * @post_doit: called after an operation's @doit callback, it may * undo operations done by pre_doit, for example release locks * * Dump callbacks: * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps * * Do callbacks can be used if %GENL_CMD_CAP_DO is set in @flags. * Dump callbacks can be used if %GENL_CMD_CAP_DUMP is set in @flags. * Exactly one of those flags must be set. */ struct genl_split_ops { union { struct { int (*pre_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); int (*doit)(struct sk_buff *skb, struct genl_info *info); void (*post_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); }; struct { int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); }; }; const struct nla_policy *policy; unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_dumpit_info - info that is available during dumpit op call * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes * @info: struct genl_info describing the request */ struct genl_dumpit_info { struct genl_split_ops op; struct genl_info info; }; static inline const struct genl_dumpit_info * genl_dumpit_info(struct netlink_callback *cb) { return cb->data; } static inline const struct genl_info * genl_info_dump(struct netlink_callback *cb) { return &genl_dumpit_info(cb)->info; } /** * genl_info_init_ntf() - initialize genl_info for notifications * @info: genl_info struct to set up * @family: pointer to the genetlink family * @cmd: command to be used in the notification * * Initialize a locally declared struct genl_info to pass to various APIs. * Intended to be used when creating notifications. */ static inline void genl_info_init_ntf(struct genl_info *info, const struct genl_family *family, u8 cmd) { struct genlmsghdr *hdr = (void *) &info->user_ptr[0]; memset(info, 0, sizeof(*info)); info->family = family; info->genlhdr = hdr; hdr->cmd = cmd; } static inline bool genl_info_is_ntf(const struct genl_info *info) { return !info->nlhdr; } void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk); void *genl_sk_priv_get(struct genl_family *family, struct sock *sk); int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd); static inline void * __genlmsg_iput(struct sk_buff *skb, const struct genl_info *info, int flags) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, info->family, flags, info->genlhdr->cmd); } /** * genlmsg_iput - start genetlink message based on genl_info * @skb: skb in which message header will be placed * @info: genl_info as provided to do/dump handlers * * Convenience wrapper which starts a genetlink message based on * information in user request. @info should be either the struct passed * by genetlink core to do/dump handlers (when constructing replies to * such requests) or a struct initialized by genl_info_init_ntf() * when constructing notifications. * * Returns: pointer to new genetlink header. */ static inline void * genlmsg_iput(struct sk_buff *skb, const struct genl_info *info) { return __genlmsg_iput(skb, info, 0); } /** * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() * * Returns: pointer to netlink header. */ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) { return (struct nlmsghdr *)((char *)user_hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_parse_deprecated - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * genlmsg_parse - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * genl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @user_hdr: user header as returned from genlmsg_put() * * Cf. nl_dump_check_consistent(), this just provides a wrapper to make it * simpler to use with generic netlink. */ static inline void genl_dump_check_consistent(struct netlink_callback *cb, void *user_hdr) { nl_dump_check_consistent(cb, genlmsg_nlhdr(user_hdr)); } /** * genlmsg_put_reply - Add generic netlink header to a reply message * @skb: socket buffer holding the message * @info: receiver info * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns: pointer to user specific header */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, const struct genl_family *family, int flags, u8 cmd) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, flags, cmd); } /** * genlmsg_end - Finalize a generic netlink message * @skb: socket buffer the message is stored in * @hdr: user specific header */ static inline void genlmsg_end(struct sk_buff *skb, void *hdr) { nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_cancel - Cancel construction of a generic netlink message * @skb: socket buffer the message is stored in * @hdr: generic netlink message header */ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { if (hdr) nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_multicast_netns_filtered - multicast a netlink message * to a specific netns with filter * function * @family: the generic netlink family * @net: the net namespace * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags * @filter: filter function * @filter_data: filter function private data * * Return: 0 on success, negative error code for failure. */ static inline int genlmsg_multicast_netns_filtered(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags, netlink_filter_fn filter, void *filter_data) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group, flags, filter, filter_data); } /** * genlmsg_multicast_netns - multicast a netlink message to a specific netns * @family: the generic netlink family * @net: the net namespace * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return genlmsg_multicast_netns_filtered(family, net, skb, portid, group, flags, NULL, NULL); } /** * genlmsg_multicast - multicast a netlink message to the default netns * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return genlmsg_multicast_netns(family, &init_net, skb, portid, group, flags); } /** * genlmsg_multicast_allns - multicast a netlink message to all net namespaces * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group); /** * genlmsg_unicast - unicast a netlink message * @net: network namespace to look up @portid in * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 portid) { return nlmsg_unicast(net->genl_sock, skb, portid); } /** * genlmsg_reply - reply to a request * @skb: netlink message to be sent back * @info: receiver information */ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) { return genlmsg_unicast(genl_info_net(info), skb, info->snd_portid); } /** * genlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) { return ((unsigned char *) gnlh + GENL_HDRLEN); } /** * genlmsg_len - length of message payload * @gnlh: genetlink message header */ static inline int genlmsg_len(const struct genlmsghdr *gnlh) { struct nlmsghdr *nlh = (struct nlmsghdr *)((unsigned char *)gnlh - NLMSG_HDRLEN); return (nlh->nlmsg_len - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_msg_size - length of genetlink message not including padding * @payload: length of message payload */ static inline int genlmsg_msg_size(int payload) { return GENL_HDRLEN + payload; } /** * genlmsg_total_size - length of genetlink message including padding * @payload: length of message payload */ static inline int genlmsg_total_size(int payload) { return NLMSG_ALIGN(genlmsg_msg_size(payload)); } /** * genlmsg_new - Allocate a new generic netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. */ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) { return nlmsg_new(genlmsg_total_size(payload), flags); } /** * genl_set_err - report error to genetlink broadcast listeners * @family: the generic netlink family * @net: the network namespace to report the error to * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * (this is the offset of the multicast group in the groups array) * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ static inline int genl_set_err(const struct genl_family *family, struct net *net, u32 portid, u32 group, int code) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_set_err(net->genl_sock, portid, group, code); } static inline int genl_has_listeners(const struct genl_family *family, struct net *net, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_has_listeners(net->genl_sock, group); } #endif /* __NET_GENERIC_NETLINK_H */ |
| 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SNAP data link layer. Derived from 802.2 * * Alan Cox <alan@lxorguk.ukuu.org.uk>, * from the 802.2 layer by Greg Page. * Merged in additions from Greg Page's psnap.c. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/datalink.h> #include <net/llc.h> #include <net/psnap.h> #include <linux/mm.h> #include <linux/in.h> #include <linux/init.h> #include <linux/rculist.h> static LIST_HEAD(snap_list); static DEFINE_SPINLOCK(snap_lock); static struct llc_sap *snap_sap; /* * Find a snap client by matching the 5 bytes. */ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; list_for_each_entry_rcu(p, &snap_list, node, lockdep_is_held(&snap_lock)) { if (!memcmp(p->type, desc, 5)) { proto = p; break; } } return proto; } /* * A SNAP packet has arrived */ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { int rc = 1; struct datalink_proto *proto; static struct packet_type snap_packet_type = { .type = cpu_to_be16(ETH_P_SNAP), }; if (unlikely(!pskb_may_pull(skb, 5))) goto drop; rcu_read_lock(); proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ skb_pull_rcsum(skb, 5); skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); if (unlikely(!proto)) goto drop; out: return rc; drop: kfree_skb(skb); goto out; } /* * Put a SNAP header on a frame and pass to 802.2 */ static int snap_request(struct datalink_proto *dl, struct sk_buff *skb, const u8 *dest) { memcpy(skb_push(skb, 5), dl->type, 5); llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); return 0; } /* * Set up the SNAP layer */ EXPORT_SYMBOL(register_snap_client); EXPORT_SYMBOL(unregister_snap_client); static const char snap_err_msg[] __initconst = KERN_CRIT "SNAP - unable to register with 802.2\n"; static int __init snap_init(void) { snap_sap = llc_sap_open(0xAA, snap_rcv); if (!snap_sap) { printk(snap_err_msg); return -EBUSY; } return 0; } module_init(snap_init); static void __exit snap_exit(void) { llc_sap_put(snap_sap); } module_exit(snap_exit); /* * Register SNAP clients. We don't yet use this for IP. */ struct datalink_proto *register_snap_client(const unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct datalink_proto *proto = NULL; spin_lock_bh(&snap_lock); if (find_snap_client(desc)) goto out; proto = kmalloc_obj(*proto, GFP_ATOMIC); if (proto) { memcpy(proto->type, desc, 5); proto->rcvfunc = rcvfunc; proto->header_length = 5 + 3; /* snap + 802.2 */ proto->request = snap_request; list_add_rcu(&proto->node, &snap_list); } out: spin_unlock_bh(&snap_lock); return proto; } /* * Unregister SNAP clients. Protocols no longer want to play with us ... */ void unregister_snap_client(struct datalink_proto *proto) { spin_lock_bh(&snap_lock); list_del_rcu(&proto->node); spin_unlock_bh(&snap_lock); synchronize_net(); kfree(proto); } MODULE_DESCRIPTION("SNAP data link layer. Derived from 802.2"); MODULE_LICENSE("GPL"); |
| 276 276 277 277 153 153 276 277 276 16 16 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_gather_mmu_vma() / * tlb_finish_mmu() * * start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_free_vmas() * * tlb_free_vmas() marks the start of unlinking of one or more vmas * and freeing page-tables. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / tlb_remove_page_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() * - __tlb_remove_folio_pages_size() * * __tlb_remove_folio_pages_size() is the basic primitive that queues pages * for freeing. It will return a boolean indicating if the queue is (now) * full and a call to tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * __tlb_remove_folio_pages() is similar to __tlb_remove_page_size(), * however, instead of removing a single page, assume PAGE_SIZE and remove * the given number of consecutive pages that are all part of the * same (large) folio. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() or * use the generic __tlb_remove_table(), which does the actual freeing of these * pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_FLUSH_CACHE * * Indicates the architecture has flush_cache_range() but it needs *NOT* be called * before unmapping a VMA. * * NOTE: strictly speaking we shouldn't have this knob and instead rely on * flush_cache_range() being a NOP, except Sparc64 seems to be * different here. * * MMU_GATHER_MERGE_VMAS * * Indicates the architecture wants to merge ranges over VMAs; typical when * multiple range invalidates are more expensive than a full invalidate. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). This * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) #ifndef CONFIG_HAVE_ARCH_TLB_REMOVE_TABLE static inline void __tlb_remove_table(void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor_free(ptdesc); } #endif extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_TABLE_FREE */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor(ptdesc); tlb_remove_page(tlb, ptdesc_page(ptdesc)); } #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif void tlb_remove_table_sync_one(void); #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif static inline void tlb_remove_table_sync_one(void) { } #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct encoded_page *encoded_pages[]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page, unsigned int nr_pages, bool delay_rmap); #ifdef CONFIG_SMP /* * This both sets 'delayed_rmap', and returns true. It would be an inline * function, except we define it before the 'struct mmu_gather'. */ #define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true) extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma); #endif #endif /* * We have a no-op version of the rmap removal that doesn't * delay anything. That is used on S390, which flushes remote * TLBs synchronously, and on UP, which doesn't have any * remote TLBs to flush and is not preemptible due to this * all happening under the page table lock. */ #ifndef tlb_delay_rmap #define tlb_delay_rmap(tlb) (false) static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * Do we have pending delayed rmap removals? */ unsigned int delayed_rmap : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int vma_pfn : 1; /* * Did we unshare (unmap) any shared page tables? For now only * used for hugetlb PMD table sharing. */ unsigned int unshared_tables : 1; /* * Did we unshare any page tables such that they are now exclusive * and could get reused+modified by the new owner? When setting this * flag, "unshared_tables" will be set as well. For now only used * for hugetlb PMD table sharing. */ unsigned int fully_unshared_tables : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; tlb->unshared_tables = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) #error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); /* * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma * in the tracked range, see tlb_free_vmas(). */ tlb->vma_pfn |= !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* * Anything calling __tlb_adjust_range() also sets at least one of * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds || tlb->unshared_tables)) return; tlb_flush(tlb); __tlb_reset_range(tlb); } static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { if (__tlb_remove_page_size(tlb, page, page_size)) tlb_flush_mmu(tlb); } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline void tlb_remove_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt) { tlb_remove_table(tlb, pt); } static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { #ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); } tlb->page_size = page_size; #endif } static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { if (tlb->cleared_ptes) return PAGE_SHIFT; if (tlb->cleared_pmds) return PMD_SHIFT; if (tlb->cleared_puds) return PUD_SHIFT; if (tlb->cleared_p4ds) return P4D_SHIFT; return PAGE_SHIFT; } static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) { return 1UL << tlb_get_unmap_shift(tlb); } /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); #ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE flush_cache_range(vma, vma->vm_start, vma->vm_end); #endif } static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) return; /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs, * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on * this. */ tlb_flush_mmu_tlbonly(tlb); } static inline void tlb_free_vmas(struct mmu_gather *tlb) { if (tlb->fullmm) return; /* * VM_PFNMAP is more fragile because the core mm will not track the * page mapcount -- there might not be page-frames for these PFNs * after all. * * Specifically() there is a race between munmap() and * unmap_mapping_range(), where munmap() will unlink the VMA, such * that unmap_mapping_range() will no longer observe the VMA and * no-op, without observing the TLBI, returning prematurely. * * So if we're about to unlink such a VMA, and we have pending * TLBI for such a vma, flush things now. */ if (tlb->vma_pfn) tlb_flush_mmu_tlbonly(tlb); } /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, * and set corresponding cleared_*. */ static inline void tlb_flush_pte_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_ptes = 1; } static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_pmds = 1; } static inline void tlb_flush_pud_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_puds = 1; } static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_p4ds = 1; } #ifndef __tlb_remove_tlb_entry static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { } #endif /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * * Record the fact that pte's were really unmapped by updating the range, * so we can later optimise away the tlb invalidate. This helps when * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_tlb_entries - remember unmapping of multiple consecutive ptes for * later tlb invalidation. * * Similar to tlb_remove_tlb_entry(), but remember unmapping of multiple * consecutive ptes instead of only a single one. */ static inline void tlb_remove_tlb_entries(struct mmu_gather *tlb, pte_t *ptep, unsigned int nr, unsigned long address) { tlb_flush_pte_range(tlb, address, PAGE_SIZE * nr); for (;;) { __tlb_remove_tlb_entry(tlb, ptep, address); if (--nr == 0) break; ptep++; address += PAGE_SIZE; } } #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ if (_sz >= P4D_SIZE) \ tlb_flush_p4d_range(tlb, address, _sz); \ else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ else if (_sz >= PMD_SIZE) \ tlb_flush_pmd_range(tlb, address, _sz); \ else \ tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation * This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pmd_tlb_entry #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0) #endif #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) /** * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb * invalidation. This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pud_tlb_entry #define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0) #endif #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) /* * For things like page tables caches (ie caching addresses "inside" the * page tables, like x86 does), for legacy reasons, flushing an * individual page had better flush the page table caches behind it. This * is definitely how x86 works, for example. And if you have an * architected non-legacy page table cache (which I'm not aware of * anybody actually doing), you're going to have some architecturally * explicit flushing for that, likely *separate* from a regular TLB entry * flush, and thus you'd need more than just some range expansion.. * * So if we ever find an architecture * that would want something that odd, I think it is up to that * architecture to do its own odd thing, not cause pain for others * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com * * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef pte_needs_flush static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) { return true; } #endif #ifndef huge_pmd_needs_flush static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) { return true; } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline void tlb_unshare_pmd_ptdesc(struct mmu_gather *tlb, struct ptdesc *pt, unsigned long addr) { /* * The caller must make sure that concurrent unsharing + exclusive * reuse is impossible until tlb_flush_unshared_tables() was called. */ VM_WARN_ON_ONCE(!ptdesc_pmd_is_shared(pt)); ptdesc_pmd_pts_dec(pt); /* Clearing a PUD pointing at a PMD table with PMD leaves. */ tlb_flush_pmd_range(tlb, addr & PUD_MASK, PUD_SIZE); /* * If the page table is now exclusively owned, we fully unshared * a page table. */ if (!ptdesc_pmd_is_shared(pt)) tlb->fully_unshared_tables = true; tlb->unshared_tables = true; } static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb) { /* * As soon as the caller drops locks to allow for reuse of * previously-shared tables, these tables could get modified and * even reused outside of hugetlb context, so we have to make sure that * any page table walkers (incl. TLB, GUP-fast) are aware of that * change. * * Even if we are not fully unsharing a PMD table, we must * flush the TLB for the unsharer now. */ if (tlb->unshared_tables) tlb_flush_mmu_tlbonly(tlb); /* * Similarly, we must make sure that concurrent GUP-fast will not * walk previously-shared page tables that are getting modified+reused * elsewhere. So broadcast an IPI to wait for any concurrent GUP-fast. * * We only perform this when we are the last sharer of a page table, * as the IPI will reach all CPUs: any GUP-fast. * * Note that on configs where tlb_remove_table_sync_one() is a NOP, * the expectation is that the tlb_flush_mmu_tlbonly() would have issued * required IPIs already for us. */ if (tlb->fully_unshared_tables) { tlb_remove_table_sync_one(); tlb->fully_unshared_tables = false; } } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lib/plist.c * * Descending-priority-sorted double-linked list * * (C) 2002-2003 Intel Corp * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>. * * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * * (C) 2005 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> * * Based on simple lists (include/linux/list.h). * * This file contains the add / del functions which are considered to * be too large to inline. See include/linux/plist.h for further * information. */ #include <linux/bug.h> #include <linux/plist.h> #ifdef CONFIG_DEBUG_PLIST static struct plist_head test_head; static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { WARN(n->prev != p || p->next != n, "top: %p, n: %p, p: %p\n" "prev: %p, n: %p, p: %p\n" "next: %p, n: %p, p: %p\n", t, t->next, t->prev, p, p->next, p->prev, n, n->next, n->prev); } static void plist_check_list(struct list_head *top) { struct list_head *prev = top, *next = top->next; plist_check_prev_next(top, prev, next); while (next != top) { prev = next; next = prev->next; plist_check_prev_next(top, prev, next); } } static void plist_check_head(struct plist_head *head) { if (!plist_head_empty(head)) plist_check_list(&plist_first(head)->prio_list); plist_check_list(&head->node_list); } #else # define plist_check_head(h) do { } while (0) #endif /** * plist_add - add @node to @head * * @node: &struct plist_node pointer * @head: &struct plist_head pointer */ void plist_add(struct plist_node *node, struct plist_head *head) { struct plist_node *first, *iter, *prev = NULL, *last, *reverse_iter; struct list_head *node_next = &head->node_list; plist_check_head(head); WARN_ON(!plist_node_empty(node)); WARN_ON(!list_empty(&node->prio_list)); if (plist_head_empty(head)) goto ins_node; first = iter = plist_first(head); last = reverse_iter = list_entry(first->prio_list.prev, struct plist_node, prio_list); do { if (node->prio < iter->prio) { node_next = &iter->node_list; break; } else if (node->prio >= reverse_iter->prio) { prev = reverse_iter; iter = list_entry(reverse_iter->prio_list.next, struct plist_node, prio_list); if (likely(reverse_iter != last)) node_next = &iter->node_list; break; } prev = iter; iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); reverse_iter = list_entry(reverse_iter->prio_list.prev, struct plist_node, prio_list); } while (iter != first); if (!prev || prev->prio != node->prio) list_add_tail(&node->prio_list, &iter->prio_list); ins_node: list_add_tail(&node->node_list, node_next); plist_check_head(head); } /** * plist_del - Remove a @node from plist. * * @node: &struct plist_node pointer - entry to be removed * @head: &struct plist_head pointer - list head */ void plist_del(struct plist_node *node, struct plist_head *head) { plist_check_head(head); if (!list_empty(&node->prio_list)) { if (node->node_list.next != &head->node_list) { struct plist_node *next; next = list_entry(node->node_list.next, struct plist_node, node_list); /* add the next plist_node into prio_list */ if (list_empty(&next->prio_list)) list_add(&next->prio_list, &node->prio_list); } list_del_init(&node->prio_list); } list_del_init(&node->node_list); plist_check_head(head); } /** * plist_requeue - Requeue @node at end of same-prio entries. * * This is essentially an optimized plist_del() followed by * plist_add(). It moves an entry already in the plist to * after any other same-priority entries. * * @node: &struct plist_node pointer - entry to be moved * @head: &struct plist_head pointer - list head */ void plist_requeue(struct plist_node *node, struct plist_head *head) { struct plist_node *iter; struct list_head *node_next = &head->node_list; plist_check_head(head); BUG_ON(plist_head_empty(head)); BUG_ON(plist_node_empty(node)); if (node == plist_last(head)) return; iter = plist_next(node); if (node->prio != iter->prio) return; plist_del(node, head); /* * After plist_del(), iter is the replacement of the node. If the node * was on prio_list, take shortcut to find node_next instead of looping. */ if (!list_empty(&iter->prio_list)) { iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); node_next = &iter->node_list; goto queue; } plist_for_each_continue(iter, head) { if (node->prio != iter->prio) { node_next = &iter->node_list; break; } } queue: list_add_tail(&node->node_list, node_next); plist_check_head(head); } #ifdef CONFIG_DEBUG_PLIST #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/module.h> #include <linux/init.h> static struct plist_node __initdata test_node[241]; static void __init plist_test_check(int nr_expect) { struct plist_node *first, *prio_pos, *node_pos; if (plist_head_empty(&test_head)) { BUG_ON(nr_expect != 0); return; } prio_pos = first = plist_first(&test_head); plist_for_each(node_pos, &test_head) { if (nr_expect-- < 0) break; if (node_pos == first) continue; if (node_pos->prio == prio_pos->prio) { BUG_ON(!list_empty(&node_pos->prio_list)); continue; } BUG_ON(prio_pos->prio > node_pos->prio); BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list); prio_pos = node_pos; } BUG_ON(nr_expect != 0); BUG_ON(prio_pos->prio_list.next != &first->prio_list); } static void __init plist_test_requeue(struct plist_node *node) { plist_requeue(node, &test_head); if (node != plist_last(&test_head)) BUG_ON(node->prio == plist_next(node)->prio); } static int __init plist_test(void) { int nr_expect = 0, i, loop; unsigned int r = local_clock(); printk(KERN_DEBUG "start plist test\n"); plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) plist_node_init(test_node + i, 0); for (loop = 0; loop < 1000; loop++) { r = r * 193939 % 47629; i = r % ARRAY_SIZE(test_node); if (plist_node_empty(test_node + i)) { r = r * 193939 % 47629; test_node[i].prio = r % 99; plist_add(test_node + i, &test_head); nr_expect++; } else { plist_del(test_node + i, &test_head); nr_expect--; } plist_test_check(nr_expect); if (!plist_node_empty(test_node + i)) { plist_test_requeue(test_node + i); plist_test_check(nr_expect); } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { if (plist_node_empty(test_node + i)) continue; plist_del(test_node + i, &test_head); nr_expect--; plist_test_check(nr_expect); } printk(KERN_DEBUG "end plist test\n"); /* Worst case test for plist_add() */ unsigned int test_data[241]; for (i = 0; i < ARRAY_SIZE(test_data); i++) test_data[i] = i; ktime_t start, end, time_elapsed = 0; plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) { plist_node_init(test_node + i, 0); test_node[i].prio = test_data[i]; } for (i = 0; i < ARRAY_SIZE(test_node); i++) { if (plist_node_empty(test_node + i)) { start = ktime_get(); plist_add(test_node + i, &test_head); end = ktime_get(); time_elapsed += (end - start); } } pr_debug("plist_add worst case test time elapsed %lld\n", time_elapsed); return 0; } module_init(plist_test); #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_ #define _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_ /** * __ffs - find first bit in word. * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ static __always_inline __attribute_const__ unsigned int __ffs(unsigned long word) { return __builtin_ctzl(word); } #endif |
| 5 5 481 334 480 139 138 42 43 1 1 1 189 380 191 483 16 239 314 484 10 480 482 339 48 191 1 28 174 176 24 135 29 245 245 2 243 379 136 4 40 478 475 476 1 477 480 403 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/fault.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 1995-2004 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/extable.h> #include <linux/kfence.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/highmem.h> #include <linux/perf_event.h> #include <linux/pkeys.h> #include <linux/preempt.h> #include <linux/hugetlb.h> #include <asm/acpi.h> #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> #include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kprobes.h> #include <asm/mte.h> #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/tlbflush.h> #include <asm/traps.h> #include <asm/virt.h> struct fault_info { int (*fn)(unsigned long far, unsigned long esr, struct pt_regs *regs); int sig; int code; const char *name; }; static const struct fault_info fault_info[]; static inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } static void data_abort_decode(unsigned long esr) { unsigned long iss2 = ESR_ELx_ISS2(esr); pr_alert("Data abort info:\n"); if (esr & ESR_ELx_ISV) { pr_alert(" Access size = %u byte(s)\n", 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT)); pr_alert(" SSE = %lu, SRT = %lu\n", (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT, (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT); pr_alert(" SF = %lu, AR = %lu\n", (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { pr_alert(" ISV = 0, ISS = 0x%08lx, ISS2 = 0x%08lx\n", esr & ESR_ELx_ISS_MASK, iss2); } pr_alert(" CM = %lu, WnR = %lu, TnD = %lu, TagAccess = %lu\n", (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT, (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT, (iss2 & ESR_ELx_TnD) >> ESR_ELx_TnD_SHIFT, (iss2 & ESR_ELx_TagAccess) >> ESR_ELx_TagAccess_SHIFT); pr_alert(" GCS = %ld, Overlay = %lu, DirtyBit = %lu, Xs = %llu\n", (iss2 & ESR_ELx_GCS) >> ESR_ELx_GCS_SHIFT, (iss2 & ESR_ELx_Overlay) >> ESR_ELx_Overlay_SHIFT, (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT, (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT); } static void mem_abort_decode(unsigned long esr) { pr_alert("Mem abort info:\n"); pr_alert(" ESR = 0x%016lx\n", esr); pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); pr_alert(" SET = %lu, FnV = %lu\n", (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT, (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT); pr_alert(" EA = %lu, S1PTW = %lu\n", (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT, (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT); pr_alert(" FSC = 0x%02lx: %s\n", (esr & ESR_ELx_FSC), esr_to_fault_info(esr)->name); if (esr_is_data_abort(esr)) data_abort_decode(esr); } static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ if (mm == &init_mm) return __pa_symbol(mm->pgd); return (unsigned long)virt_to_phys(mm->pgd); } /* * Dump out the page tables associated with 'addr' in the currently active mm. */ static void show_pte(unsigned long addr) { struct mm_struct *mm; pgd_t *pgdp; pgd_t pgd; if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { pr_alert("[%016lx] user address but active_mm is swapper\n", addr); return; } } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { pr_alert("[%016lx] address between user and kernel address ranges\n", addr); return; } pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; if (pgd_none(pgd) || pgd_bad(pgd)) break; p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; ptep = pte_offset_map(pmdp, addr); if (!ptep) break; pte = __ptep_get(ptep); pr_cont(", pte=%016llx", pte_val(pte)); pte_unmap(ptep); } while(0); pr_cont("\n"); } /* * This function sets the access flags (dirty, accessed), as well as write * permission, and only to a more permissive setting. * * It needs to cope with hardware update of the accessed/dirty state by other * agents in the system and can safely skip the __sync_icache_dcache() call as, * like __set_ptes(), the PTE is never changed from no-exec to exec here. * * Returns whether or not the PTE actually changed. */ int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { pteval_t old_pteval, pteval; pte_t pte = __ptep_get(ptep); if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; /* * Setting the flags must be done atomically to avoid racing with the * hardware update of the access/dirty state. The PTE_RDONLY bit must * be set to the most permissive (lowest value) of *ptep and entry * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; pteval |= pte_val(entry); pteval ^= PTE_RDONLY; pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); /* * Invalidate the local stale read-only entry. Remote stale entries * may still cause page faults and be invalidated via * flush_tlb_fix_spurious_fault(). */ if (dirty) local_flush_tlb_page(vma, address); return 1; } static bool is_el1_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; } static bool is_el1_data_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR; } static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; } static bool is_pkvm_stage2_abort(unsigned int esr) { /* * S1PTW should only ever be set in ESR_EL1 if the pkvm hypervisor * injected a stage-2 abort -- see host_inject_mem_abort(). */ return is_pkvm_initialized() && (esr & ESR_ELx_S1PTW); } static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { unsigned long flags; u64 par, dfsc; if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); asm volatile("at s1e1r, %0" :: "r" (addr)); isb(); par = read_sysreg_par(); local_irq_restore(flags); /* * If we now have a valid translation, treat the translation fault as * spurious. */ if (!(par & SYS_PAR_EL1_F)) { if (is_pkvm_stage2_abort(esr)) { par &= SYS_PAR_EL1_PA; return pkvm_force_reclaim_guest_page(par); } return true; } /* * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, unsigned long esr, struct pt_regs *regs) { bust_spinlocks(1); pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg, addr); kasan_non_canonical_hook(addr); mem_abort_decode(esr); show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS static void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ bool is_write = !!(esr & ESR_ELx_WNR); kasan_report((void *)addr, 0, is_write, regs->pc); } #else /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ static inline void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { } #endif static void do_tag_recovery(unsigned long addr, unsigned long esr, struct pt_regs *regs) { report_tag_fault(addr, esr, regs); /* * Disable MTE Tag Checking on the local CPU for the current EL. * It will be done lazily on the other CPUs when they will hit a * tag fault. */ sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF, NONE)); isb(); } static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) { unsigned long fsc = esr & ESR_ELx_FSC; if (!is_el1_data_abort(esr)) return false; if (fsc == ESR_ELx_FSC_MTE) return true; return false; } static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { const char *msg; /* * Are we prepared to handle this kernel fault? * We are almost certainly not prepared to handle instruction faults. */ if (!is_el1_instruction_abort(esr) && fixup_exception(regs, esr)) return; if (is_spurious_el1_translation_fault(addr, esr, regs)) { WARN_RATELIMIT(!is_pkvm_stage2_abort(esr), "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr); return; } if (is_el1_mte_sync_tag_check_fault(esr)) { do_tag_recovery(addr, esr, regs); return; } if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; else if (is_el1_instruction_abort(esr)) msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else if (is_pkvm_stage2_abort(esr)) { msg = "access to hypervisor-protected memory"; } else { if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; } if (efi_runtime_fixup_exception(regs, msg)) return; die_kernel_fault(msg, addr, esr, regs); } static void set_thread_esr(unsigned long address, unsigned long esr) { current->thread.fault_address = address; /* * If the faulting address is in the kernel, we must sanitize the ESR. * From userspace's point of view, kernel-only mappings don't exist * at all, so we report them as level 0 translation faults. * (This is not quite the way that "no mapping there at all" behaves: * an alignment fault not caused by the memory type would take * precedence over translation fault for a real access to empty * space. Unfortunately we can't easily distinguish "alignment fault * not caused by memory type" from "alignment fault caused by memory * type", so we ignore this wrinkle and just return the translation * fault.) */ if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* * These bits provide only information about the * faulting instruction, which userspace knows already. * We explicitly clear bits which are architecturally * RES0 in case they are given meanings in future. * We always report the ESR as if the fault was taken * to EL1 and so ISV and the bits in ISS[23:14] are * clear. (In fact it always will be a fault to EL1.) */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL | ESR_ELx_CM | ESR_ELx_WNR; esr |= ESR_ELx_FSC_FAULT; break; case ESR_ELx_EC_IABT_LOW: /* * Claim a level 0 translation fault. * All other bits are architecturally RES0 for faults * reported with that DFSC value, so we clear them. */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL; esr |= ESR_ELx_FSC_FAULT; break; default: /* * This should never happen (entry.S only brings us * into this code for insn and data aborts from a lower * exception level). Fail safe by not providing an ESR * context record at all. */ WARN(1, "ESR 0x%lx is not DABT or IABT from EL0\n", esr); esr = 0; break; } } current->thread.fault_code = esr; } static void do_bad_area(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (user_mode(regs)) { const struct fault_info *inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); arm64_force_sig_fault(inf->sig, inf->code, far, inf->name); } else { __do_kernel_fault(addr, esr, regs); } } static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags) { if (!system_supports_poe()) return false; /* * We do not check whether an Overlay fault has occurred because we * cannot make a decision based solely on its value: * * - If Overlay is set, a fault did occur due to POE, but it may be * spurious in those cases where we update POR_EL0 without ISB (e.g. * on context-switch). We would then need to manually check POR_EL0 * against vma_pkey(vma), which is exactly what * arch_vma_access_permitted() does. * * - If Overlay is not set, we may still need to report a pkey fault. * This is the case if an access was made within a mapping but with no * page mapped, and POR_EL0 forbids the access (according to * vma_pkey()). Such access will result in a SIGSEGV regardless * because core code checks arch_vma_access_permitted(), but in order * to report the correct error code - SEGV_PKUERR - we must handle * that case here. */ return !arch_vma_access_permitted(vma, mm_flags & FAULT_FLAG_WRITE, mm_flags & FAULT_FLAG_INSTRUCTION, false); } static bool is_gcs_fault(unsigned long esr) { if (!esr_is_data_abort(esr)) return false; return ESR_ELx_ISS2(esr) & ESR_ELx_GCS; } static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } /* * Note: not valid for EL1 DC IVAC, but we never use that such that it * should fault. EL0 cannot issue DC IVAC (undef). */ static bool is_write_abort(unsigned long esr) { return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } static bool is_invalid_gcs_access(struct vm_area_struct *vma, u64 esr) { if (!system_supports_gcs()) return false; if (unlikely(is_gcs_fault(esr))) { /* GCS accesses must be performed on a GCS page */ if (!(vma->vm_flags & VM_SHADOW_STACK)) return true; } else if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) { /* Only GCS operations can write to a GCS page */ return esr_is_data_abort(esr) && is_write_abort(esr); } return false; } static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault; vm_flags_t vm_flags; unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; int si_code; int pkey = -1; if (kprobe_page_fault(regs, esr)) return 0; /* * If we're in an interrupt or have no user context, we must not take * the fault. */ if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) mm_flags |= FAULT_FLAG_USER; /* * vm_flags tells us what bits we must have in vma->vm_flags * for the fault to be benign, __do_page_fault() would check * vma->vm_flags & vm_flags and returns an error if the * intersection is empty */ if (is_el0_instruction_abort(esr)) { /* It was exec fault */ vm_flags = VM_EXEC; mm_flags |= FAULT_FLAG_INSTRUCTION; } else if (is_gcs_fault(esr)) { /* * The GCS permission on a page implies both read and * write so always handle any GCS fault as a write fault, * we need to trigger CoW even for GCS reads. */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else if (is_write_abort(esr)) { /* It was write fault */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else { /* It was read fault */ vm_flags = VM_READ; /* Write implies read */ vm_flags |= VM_WRITE; /* If EPAN is absent then exec implies read */ if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; } if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { if (is_el1_instruction_abort(esr)) die_kernel_fault("execution of user memory", addr, esr, regs); if (!insn_may_access_user(regs->pc, esr)) die_kernel_fault("access to user memory outside uaccess routines", addr, esr, regs); } if (is_pkvm_stage2_abort(esr)) { if (!user_mode(regs)) goto no_context; arm64_force_sig_fault(SIGSEGV, SEGV_ACCERR, far, "stage-2 fault"); return 0; } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, addr); if (!vma) goto lock_mmap; if (is_invalid_gcs_access(vma, esr)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); vma_end_read(vma); fault = 0; si_code = SEGV_PKUERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { fault = 0; si_code = SEGV_MAPERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { mmap_read_unlock(mm); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); mmap_read_unlock(mm); fault = 0; si_code = SEGV_PKUERR; goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return 0; if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: /* Handle the "normal" (no error) case first. */ if (likely(!(fault & VM_FAULT_ERROR))) return 0; si_code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (!user_mode(regs)) goto no_context; if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to * userspace (which will retry the fault, or kill us if we got * oom-killed). */ pagefault_out_of_memory(); return 0; } inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up * this page fault. */ arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name); } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) { unsigned int lsb; lsb = PAGE_SHIFT; if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { /* * The pkey value that we return to userspace can be different * from the pkey that caused the fault. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set POR_EL0 to deny access to pkey=4, touches, page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ /* Something tried to access memory that out of memory map */ if (si_code == SEGV_PKUERR) arm64_force_sig_fault_pkey(far, inf->name, pkey); else arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; no_context: __do_kernel_fault(addr, esr, regs); return 0; } static int __kprobes do_translation_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); if (is_ttbr0_addr(addr)) return do_page_fault(far, esr, regs); do_bad_area(far, esr, regs); return 0; } static int do_alignment_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) && compat_user_mode(regs)) return do_compat_alignment_fixup(far, regs); do_bad_area(far, esr, regs); return 0; } static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs) { return 1; /* "fault" */ } static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; unsigned long siaddr; inf = esr_to_fault_info(esr); if (user_mode(regs) && apei_claim_sea(regs) == 0) { /* * APEI claimed this as a firmware-first notification. * Some processing deferred to task_work before ret_to_user(). */ return 0; } if (esr & ESR_ELx_FnV) { siaddr = 0; } else { /* * The architecture specifies that the tag bits of FAR_EL1 are * UNKNOWN for synchronous external aborts. Mask them out now * so that userspace doesn't see them. */ siaddr = untagged_addr(far); } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; } static int do_tag_check_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { /* * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN * for tag check faults. Set them to corresponding bits in the untagged * address if ARM64_MTE_FAR isn't supported. * Otherwise, bits 63:60 of FAR_EL1 are not UNKNOWN. */ if (!cpus_have_cap(ARM64_MTE_FAR)) far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 2 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 3 address size fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 3 (translation table walk)" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 32" }, { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 34" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 35" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 36" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 37" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 47" }, { do_bad, SIGKILL, SI_KERNEL, "TLB conflict abort" }, { do_bad, SIGKILL, SI_KERNEL, "Unsupported atomic hardware update fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 50" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 51" }, { do_bad, SIGKILL, SI_KERNEL, "implementation fault (lockdown abort)" }, { do_bad, SIGBUS, BUS_OBJERR, "implementation fault (unsupported exclusive)" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 54" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 55" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 56" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 57" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 58" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 59" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 60" }, { do_bad, SIGKILL, SI_KERNEL, "section domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "page domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); unsigned long addr = untagged_addr(far); if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) die_kernel_fault(inf->name, addr, esr, regs); /* * At this point we have an unrecognized fault type whose tag bits may * have been defined as UNKNOWN. Therefore we only expose the untagged * address to the signal handler. */ arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr); } NOKPROBE_SYMBOL(do_mem_abort); void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs) { arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); /* * Used during anonymous page fault handling. */ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO; /* * If the page is mapped with PROT_MTE, initialise the tags at the * point of allocation and page zeroing as this is usually faster than * separate DC ZVA and STGM. */ if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; return vma_alloc_folio(flags, 0, vma, vaddr); } bool tag_clear_highpages(struct page *page, int numpages) { /* * Check if MTE is supported and fall back to clear_highpage(). * get_huge_zero_folio() unconditionally passes __GFP_ZEROTAGS and * post_alloc_hook() will invoke tag_clear_highpages(). */ if (!system_supports_mte()) return false; /* Newly allocated pages, shouldn't have been tagged yet */ for (int i = 0; i < numpages; i++, page++) { WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } return true; } |
| 12 995 991 994 995 995 991 12 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. * * A context holding the printk_cpu_sync must not spin waiting for * another CPU. For legacy printing, it could be the console_lock * or the port lock. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi() || is_printk_cpu_sync_owner()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/cacheflush.h * * Copyright (C) 1999-2002 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_CACHEFLUSH_H #define __ASM_CACHEFLUSH_H #include <linux/kgdb.h> #include <linux/mm.h> /* * This flag is used to indicate that the page pointed to by a pte is clean * and does not require cleaning before returning it to the user. */ #define PG_dcache_clean PG_arch_1 /* * MM Cache Management * =================== * * The arch/arm64/mm/cache.S implements these methods. * * Start addresses are inclusive and end addresses are exclusive; start * addresses should be rounded down, end addresses up. * * See Documentation/core-api/cachetlb.rst for more information. Please note that * the implementation assumes non-aliasing VIPT D-cache and (aliasing) * VIPT I-cache. * * All functions below apply to the interval [start, end) * - start - virtual start address (inclusive) * - end - virtual end address (exclusive) * * caches_clean_inval_pou(start, end) * * Ensure coherency between the I-cache and the D-cache region to * the Point of Unification. * * caches_clean_inval_user_pou(start, end) * * Ensure coherency between the I-cache and the D-cache region to * the Point of Unification. * Use only if the region might access user memory. * * icache_inval_pou(start, end) * * Invalidate I-cache region to the Point of Unification. * * dcache_clean_inval_poc(start, end) * * Clean and invalidate D-cache region to the Point of Coherency. * * dcache_inval_poc(start, end) * * Invalidate D-cache region to the Point of Coherency. * * dcache_clean_poc(start, end) * * Clean D-cache region to the Point of Coherency. * * dcache_clean_pop(start, end) * * Clean D-cache region to the Point of Persistence. * * dcache_clean_pou(start, end) * * Clean D-cache region to the Point of Unification. */ extern void caches_clean_inval_pou(unsigned long start, unsigned long end); extern void icache_inval_pou(unsigned long start, unsigned long end); extern void dcache_clean_inval_poc(unsigned long start, unsigned long end); extern void dcache_inval_poc(unsigned long start, unsigned long end); extern void dcache_clean_poc(unsigned long start, unsigned long end); extern void dcache_clean_pop(unsigned long start, unsigned long end); extern void dcache_clean_pou(unsigned long start, unsigned long end); extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end); extern void sync_icache_aliases(unsigned long start, unsigned long end); static inline void flush_icache_range(unsigned long start, unsigned long end) { caches_clean_inval_pou(start, end); /* * IPI all online CPUs so that they undergo a context synchronization * event and are forced to refetch the new instructions. */ /* * KGDB performs cache maintenance with interrupts disabled, so we * will deadlock trying to IPI the secondary CPUs. In theory, we can * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that * just means that KGDB will elide the maintenance altogether! As it * turns out, KGDB uses IPIs to round-up the secondary CPUs during * the patching operation, so we don't need extra IPIs here anyway. * In which case, add a KGDB-specific bodge and return early. */ if (in_dbg_master()) return; kick_all_cpus_sync(); } #define flush_icache_range flush_icache_range /* * Copy user data from/to a page which is mapped into a different * processes address space. Really, we want to allow our "user * space" model to handle this. */ extern void copy_to_user_page(struct vm_area_struct *, struct page *, unsigned long, void *, const void *, unsigned long); #define copy_to_user_page copy_to_user_page /* * flush_dcache_folio is used when the kernel has written to the page * cache page at virtual address page->virtual. * * If this page isn't mapped (ie, folio_mapping == NULL), or it might * have userspace mappings, then we _must_ always clean + invalidate * the dcache entries associated with the kernel mapping. * * Otherwise we can defer the operation, and clean the cache when we are * about to change to user space. This is the same method as used on SPARC64. * See update_mmu_cache for the user space part. */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); void flush_dcache_folio(struct folio *); #define flush_dcache_folio flush_dcache_folio static __always_inline void icache_inval_all_pou(void) { if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC)) return; asm("ic ialluis"); dsb(ish); } #include <asm-generic/cacheflush.h> #endif /* __ASM_CACHEFLUSH_H */ |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/if.h> #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/sch_generic.h> #include <linux/netfilter.h> #include <rdma/ib_addr.h> #include "rxe.h" #include "rxe_net.h" #include "rxe_loc.h" static struct rxe_recv_sockets recv_sockets; #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * lockdep can detect false positive circular dependencies * when there are user-space socket API users or in kernel * users switching between a tcp and rdma transport. * Maybe also switching between siw and rxe may cause * problems as per default sockets are only classified * by family and not by ip protocol. And there might * be different locks used between the application * and the low level sockets. * * Problems were seen with ksmbd.ko and cifs.ko, * switching transports, use git blame to find * more details. */ static struct lock_class_key rxe_recv_sk_key[2]; static struct lock_class_key rxe_recv_slock_key[2]; #endif /* CONFIG_DEBUG_LOCK_ALLOC */ static inline void rxe_reclassify_recv_socket(struct socket *sock) { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct sock *sk = sock->sk; if (WARN_ON_ONCE(!sock_allow_reclassification(sk))) return; switch (sk->sk_family) { case AF_INET: sock_lock_init_class_and_name(sk, "slock-AF_INET-RDMA-RXE-RECV", &rxe_recv_slock_key[0], "sk_lock-AF_INET-RDMA-RXE-RECV", &rxe_recv_sk_key[0]); break; case AF_INET6: sock_lock_init_class_and_name(sk, "slock-AF_INET6-RDMA-RXE-RECV", &rxe_recv_slock_key[1], "sk_lock-AF_INET6-RDMA-RXE-RECV", &rxe_recv_sk_key[1]); break; default: WARN_ON_ONCE(1); return; } /* * sock_lock_init_class_and_name() calls * sk_owner_set(sk, THIS_MODULE); in order * to make sure the referenced global * variables rxe_recv_slock_key and * rxe_recv_sk_key are not removed * before the socket is closed. * * However this prevents rxe_net_exit() * from being called and 'rmmod rdma_rxe' * is refused because of the references. * * For the global sockets in recv_sockets, * we are sure that rxe_net_exit() will call * rxe_release_udp_tunnel -> udp_tunnel_sock_release. * * So we don't need the additional reference to * our own (THIS_MODULE). */ sk_owner_put(sk); /* * We also call sk_owner_clear() otherwise * sk_owner_put(sk) in sk_prot_free will * fail, which is called via * sk_free -> __sk_free -> sk_destruct * and sk_destruct calls __sk_destruct * directly or via call_rcu() * so sk_prot_free() might be called * after rxe_net_exit(). */ sk_owner_clear(sk); #endif /* CONFIG_DEBUG_LOCK_ALLOC */ } static struct dst_entry *rxe_find_route4(struct rxe_qp *qp, struct net_device *ndev, struct in_addr *saddr, struct in_addr *daddr) { struct rtable *rt; struct flowi4 fl = { { 0 } }; memset(&fl, 0, sizeof(fl)); fl.flowi4_oif = ndev->ifindex; memcpy(&fl.saddr, saddr, sizeof(*saddr)); memcpy(&fl.daddr, daddr, sizeof(*daddr)); fl.flowi4_proto = IPPROTO_UDP; rt = ip_route_output_key(&init_net, &fl); if (IS_ERR(rt)) { rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr); return NULL; } return &rt->dst; } #if IS_ENABLED(CONFIG_IPV6) static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { struct dst_entry *ndst; struct flowi6 fl6 = { { 0 } }; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = ndev->ifindex; memcpy(&fl6.saddr, saddr, sizeof(*saddr)); memcpy(&fl6.daddr, daddr, sizeof(*daddr)); fl6.flowi6_proto = IPPROTO_UDP; ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), recv_sockets.sk6->sk, &fl6, NULL); if (IS_ERR(ndst)) { rxe_dbg_qp(qp, "no route to %pI6\n", daddr); return NULL; } if (unlikely(ndst->error)) { rxe_dbg_qp(qp, "no route to %pI6\n", daddr); goto put; } return ndst; put: dst_release(ndst); return NULL; } #else static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { return NULL; } #endif static struct dst_entry *rxe_find_route(struct net_device *ndev, struct rxe_qp *qp, struct rxe_av *av) { struct dst_entry *dst = NULL; if (qp_type(qp) == IB_QPT_RC) dst = sk_dst_get(qp->sk->sk); if (!dst || !dst_check(dst, qp->dst_cookie)) { if (dst) dst_release(dst); if (av->network_type == RXE_NETWORK_TYPE_IPV4) { struct in_addr *saddr; struct in_addr *daddr; saddr = &av->sgid_addr._sockaddr_in.sin_addr; daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route4(qp, ndev, saddr, daddr); } else if (av->network_type == RXE_NETWORK_TYPE_IPV6) { struct in6_addr *saddr6; struct in6_addr *daddr6; saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr; daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route6(qp, ndev, saddr6, daddr6); #if IS_ENABLED(CONFIG_IPV6) if (dst) qp->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); #endif } if (dst && (qp_type(qp) == IB_QPT_RC)) { dst_hold(dst); sk_dst_set(qp->sk->sk, dst); } } return dst; } static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct udphdr *udph; struct rxe_dev *rxe; struct net_device *ndev = skb->dev; struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); /* takes a reference on rxe->ib_dev * drop when skb is freed */ rxe = rxe_get_dev_from_net(ndev); if (!rxe && is_vlan_dev(ndev)) rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); if (!rxe) goto drop; if (skb_linearize(skb)) { ib_device_put(&rxe->ib_dev); goto drop; } udph = udp_hdr(skb); pkt->rxe = rxe; pkt->port_num = 1; pkt->hdr = (u8 *)(udph + 1); pkt->mask = RXE_GRH_MASK; pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph); /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; drop: kfree_skb(skb); return 0; } static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, bool ipv6) { int err; struct socket *sock; struct udp_port_cfg udp_cfg = { }; struct udp_tunnel_sock_cfg tnl_cfg = { }; if (ipv6) { udp_cfg.family = AF_INET6; udp_cfg.ipv6_v6only = 1; } else { udp_cfg.family = AF_INET; } udp_cfg.local_udp_port = port; /* Create UDP socket */ err = udp_sock_create(net, &udp_cfg, &sock); if (err < 0) return ERR_PTR(err); rxe_reclassify_recv_socket(sock); tnl_cfg.encap_type = 1; tnl_cfg.encap_rcv = rxe_udp_encap_recv; /* Setup UDP tunnel */ setup_udp_tunnel_sock(net, sock, &tnl_cfg); return sock; } static void rxe_release_udp_tunnel(struct socket *sk) { if (sk) udp_tunnel_sock_release(sk); } static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port, __be16 dst_port) { struct udphdr *udph; __skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); udph = udp_hdr(skb); udph->dest = dst_port; udph->source = src_port; udph->len = htons(skb->len); udph->check = 0; } static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb, __be32 saddr, __be32 daddr, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { struct iphdr *iph; skb_scrub_packet(skb, xnet); skb_clear_hash(skb); skb_dst_set(skb, dst_clone(dst)); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = IPVERSION; iph->ihl = sizeof(struct iphdr) >> 2; iph->tot_len = htons(skb->len); iph->frag_off = df; iph->protocol = proto; iph->tos = tos; iph->daddr = daddr; iph->saddr = saddr; iph->ttl = ttl; __ip_select_ident(dev_net(dst->dev), iph, skb_shinfo(skb)->gso_segs ?: 1); } static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, __u8 proto, __u8 prio, __u8 ttl) { struct ipv6hdr *ip6h; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst_clone(dst)); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, htonl(0)); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = proto; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); } static int prepare4(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; bool xnet = false; __be16 df = htons(IP_DF); struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr; struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { rxe_dbg_qp(qp, "Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit, df, xnet); dst_release(dst); return 0; } static int prepare6(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr; struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { rxe_dbg_qp(qp, "Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit); dst_release(dst); return 0; } int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err = 0; if (skb->protocol == htons(ETH_P_IP)) err = prepare4(av, pkt, skb); else if (skb->protocol == htons(ETH_P_IPV6)) err = prepare6(av, pkt, skb); if (ether_addr_equal(skb->dev->dev_addr, av->dmac)) pkt->mask |= RXE_LOOPBACK_MASK; return err; } static void rxe_skb_tx_dtor(struct sk_buff *skb) { struct rxe_qp *qp = skb->sk->sk_user_data; int skb_out; skb_out = atomic_dec_return(&qp->skb_out); if (unlikely(qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)) rxe_sched_task(&qp->send_task); rxe_put(qp); sock_put(skb->sk); } static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) { int err; struct sock *sk = pkt->qp->sk->sk; sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; rxe_get(pkt->qp); atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); else err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); return err; } /* fix up a send packet to match the packets * received from UDP before looping them back */ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) { struct sock *sk = pkt->qp->sk->sk; memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; rxe_get(pkt->qp); atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) skb_pull(skb, sizeof(struct iphdr)); else skb_pull(skb, sizeof(struct ipv6hdr)); if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) { kfree_skb(skb); return -EIO; } /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; } int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); if (pkt->mask & RXE_LOOPBACK_MASK) err = rxe_loopback(skb, pkt); else err = rxe_send(skb, pkt); if (err) { rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); return err; } rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); goto done; drop: kfree_skb(skb); err = 0; done: return err; } struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, int paylen, struct rxe_pkt_info *pkt) { unsigned int hdr_len; struct sk_buff *skb = NULL; struct net_device *ndev; const struct ib_gid_attr *attr; const int port_num = 1; attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index); if (IS_ERR(attr)) return NULL; if (av->network_type == RXE_NETWORK_TYPE_IPV4) hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct iphdr); else hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct ipv6hdr); rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (IS_ERR(ndev)) { rcu_read_unlock(); goto out; } skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev), GFP_ATOMIC); if (unlikely(!skb)) { rcu_read_unlock(); goto out; } /* Add time stamp to skb. */ skb->tstamp = ktime_get(); skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev)); /* FIXME: hold reference to this netdev until life of this skb. */ skb->dev = ndev; rcu_read_unlock(); if (av->network_type == RXE_NETWORK_TYPE_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); pkt->rxe = rxe; pkt->port_num = port_num; pkt->hdr = skb_put(skb, paylen); pkt->mask |= RXE_GRH_MASK; out: rdma_put_gid_attr(attr); return skb; } /* * this is required by rxe_cfg to match rxe devices in * /sys/class/infiniband up with their underlying ethernet devices */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { struct net_device *ndev; char *ndev_name; ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); if (!ndev) return NULL; ndev_name = ndev->name; dev_put(ndev); return ndev_name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) { int err; struct rxe_dev *rxe = NULL; rxe = ib_alloc_device(rxe_dev, ib_dev); if (!rxe) return -ENOMEM; ib_mark_name_assigned_by_user(&rxe->ib_dev); err = rxe_add(rxe, ndev->mtu, ibdev_name, ndev); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; } return 0; } static void rxe_port_event(struct rxe_dev *rxe, enum ib_event_type event) { struct ib_event ev; ev.device = &rxe->ib_dev; ev.element.port_num = 1; ev.event = event; ib_dispatch_event(&ev); } /* Caller must hold net_info_lock */ void rxe_port_up(struct rxe_dev *rxe) { rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE); dev_info(&rxe->ib_dev.dev, "set active\n"); } /* Caller must hold net_info_lock */ void rxe_port_down(struct rxe_dev *rxe) { rxe_port_event(rxe, IB_EVENT_PORT_ERR); rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); dev_info(&rxe->ib_dev.dev, "set down\n"); } void rxe_set_port_state(struct rxe_dev *rxe) { struct net_device *ndev; ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); if (!ndev) return; if (ib_get_curr_port_state(ndev) == IB_PORT_ACTIVE) rxe_port_up(rxe); else rxe_port_down(rxe); dev_put(ndev); } static int rxe_notify(struct notifier_block *not_blk, unsigned long event, void *arg) { struct net_device *ndev = netdev_notifier_info_to_dev(arg); struct rxe_dev *rxe = rxe_get_dev_from_net(ndev); if (!rxe) return NOTIFY_OK; switch (event) { case NETDEV_UNREGISTER: ib_unregister_device_queued(&rxe->ib_dev); break; case NETDEV_CHANGEMTU: rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); rxe_set_mtu(rxe, ndev->mtu); break; case NETDEV_DOWN: case NETDEV_CHANGE: if (ib_get_curr_port_state(ndev) == IB_PORT_DOWN) rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); break; case NETDEV_REBOOT: case NETDEV_GOING_DOWN: case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: default: rxe_dbg_dev(rxe, "ignoring netdev event = %ld for %s\n", event, ndev->name); break; } ib_device_put(&rxe->ib_dev); return NOTIFY_OK; } static struct notifier_block rxe_net_notifier = { .notifier_call = rxe_notify, }; static int rxe_net_ipv4_init(void) { recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false); if (IS_ERR(recv_sockets.sk4)) { recv_sockets.sk4 = NULL; pr_err("Failed to create IPv4 UDP tunnel\n"); return -1; } return 0; } static int rxe_net_ipv6_init(void) { #if IS_ENABLED(CONFIG_IPV6) recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true); if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) { recv_sockets.sk6 = NULL; pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n"); return 0; } if (IS_ERR(recv_sockets.sk6)) { recv_sockets.sk6 = NULL; pr_err("Failed to create IPv6 UDP tunnel\n"); return -1; } #endif return 0; } void rxe_net_exit(void) { rxe_release_udp_tunnel(recv_sockets.sk6); rxe_release_udp_tunnel(recv_sockets.sk4); unregister_netdevice_notifier(&rxe_net_notifier); } int rxe_net_init(void) { int err; recv_sockets.sk6 = NULL; err = rxe_net_ipv4_init(); if (err) return err; err = rxe_net_ipv6_init(); if (err) goto err_out; err = register_netdevice_notifier(&rxe_net_notifier); if (err) { pr_err("Failed to register netdev notifier\n"); goto err_out; } return 0; err_out: rxe_net_exit(); return err; } |
| 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #ifndef __LINUX_NEXTHOP_H #define __LINUX_NEXTHOP_H #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/route.h> #include <linux/types.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/netlink.h> #define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK struct nexthop; struct nh_config { u32 nh_id; u8 nh_family; u8 nh_protocol; u8 nh_blackhole; u8 nh_fdb; u32 nh_flags; int nh_ifindex; struct net_device *dev; union { __be32 ipv4; struct in6_addr ipv6; } gw; struct nlattr *nh_grp; u16 nh_grp_type; u16 nh_grp_res_num_buckets; unsigned long nh_grp_res_idle_timer; unsigned long nh_grp_res_unbalanced_timer; bool nh_grp_res_has_num_buckets; bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; bool nh_hw_stats; struct nlattr *nh_encap; u16 nh_encap_type; u32 nlflags; struct nl_info nlinfo; }; struct nh_info { struct hlist_node dev_hash; /* entry on netns devhash */ struct nexthop *nh_parent; u8 family; bool reject_nh; bool fdb_nh; union { struct fib_nh_common fib_nhc; struct fib_nh fib_nh; struct fib6_nh fib6_nh; }; }; struct nh_res_bucket { struct nh_grp_entry __rcu *nh_entry; atomic_long_t used_time; unsigned long migrated_time; bool occupied; u8 nh_flags; }; struct nh_res_table { struct net *net; u32 nhg_id; struct delayed_work upkeep_dw; /* List of NHGEs that have too few buckets ("uw" for underweight). * Reclaimed buckets will be given to entries in this list. */ struct list_head uw_nh_entries; unsigned long unbalanced_since; u32 idle_timer; u32 unbalanced_timer; u16 num_nh_buckets; struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; struct nh_grp_entry_stats { u64_stats_t packets; struct u64_stats_sync syncp; }; struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; u16 weight; union { struct { atomic_t upper_bound; } hthr; struct { /* Member on uw_nh_entries. */ struct list_head uw_nh_entry; u16 count_buckets; u16 wants_buckets; } res; }; struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ u64 packets_hw; }; struct nh_group { struct nh_group *spare; /* spare group for removals */ u16 num_nh; bool is_multipath; bool hash_threshold; bool resilient; bool fdb_nh; bool has_v4; bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); }; struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ struct list_head f6i_list; /* v6 entries using nh */ struct list_head fdb_list; /* fdb entries using this nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; u32 id; u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; bool dead; spinlock_t lock; /* protect dead and f6i_list */ refcount_t refcnt; struct rcu_head rcu; union { struct nh_info __rcu *nh_info; struct nh_group __rcu *nh_grp; }; }; enum nexthop_event_type { NEXTHOP_EVENT_DEL, NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_SINGLE, NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { struct net_device *dev; u8 gw_family; union { __be32 ipv4; struct in6_addr ipv6; }; u32 id; u8 is_reject:1, is_fdb:1, has_encap:1; }; struct nh_notifier_grp_entry_info { u16 weight; struct nh_notifier_single_info nh; }; struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; struct nh_notifier_res_bucket_info { u16 bucket_index; unsigned int idle_timer_ms; bool force; struct nh_notifier_single_info old_nh; struct nh_notifier_single_info new_nh; }; struct nh_notifier_res_table_info { u16 num_nh_buckets; bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; struct nh_notifier_grp_hw_stats_entry_info { u32 id; u64 packets; }; struct nh_notifier_grp_hw_stats_info { u16 num_nh; bool hw_stats_used; struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); }; struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; u32 id; enum nh_notifier_info_type type; union { struct nh_notifier_single_info *nh; struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); void nexthop_free_rcu(struct rcu_head *head); static inline bool nexthop_get(struct nexthop *nh) { return refcount_inc_not_zero(&nh->refcnt); } static inline void nexthop_put(struct nexthop *nh) { if (refcount_dec_and_test(&nh->refcnt)) call_rcu_hurry(&nh->rcu, nexthop_free_rcu); } static inline bool nexthop_cmp(const struct nexthop *nh1, const struct nexthop *nh2) { return nh1 == nh2; } static inline bool nexthop_is_fdb(const struct nexthop *nh) { if (nh->is_group) { const struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->fdb_nh; } else { const struct nh_info *nhi; nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->fdb_nh; } } static inline bool nexthop_has_v4(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->has_v4; } return false; } static inline bool nexthop_is_multipath(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->is_multipath; } return false; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); static inline unsigned int nexthop_num_path(const struct nexthop *nh) { unsigned int rc = 1; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) rc = nh_grp->num_nh; } return rc; } static inline struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel) { /* for_nexthops macros in fib_semantics.c grabs a pointer to * the nexthop before checking nhsel */ if (nhsel >= nhg->num_nh) return NULL; return nhg->nh_entries[nhsel].nh; } static inline int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, u8 rt_family) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } return 0; } /* called with rcu lock */ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->num_nh > 1) return false; nh = nh_grp->nh_entries[0].nh; } nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } static inline void nexthop_path_fib_result(struct fib_result *res, int hash) { struct nh_info *nhi; struct nexthop *nh; nh = nexthop_select_path(res->fi->nh, hash); nhi = rcu_dereference(nh->nh_info); res->nhc = &nhi->fib_nhc; } /* called with rcu read lock or rtnl held */ static inline struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) { struct nh_info *nhi; BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) { nh = nexthop_mpath_select(nh_grp, nhsel); if (!nh) return NULL; } } nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } /* called from fib_table_lookup with rcu_lock */ static inline struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh, int fib_flags, const struct flowi4 *flp, int *nhsel) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = i; return &nhi->fib_nhc; } } } else { nhi = rcu_dereference(nh->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = 0; return &nhi->fib_nhc; } } return NULL; } static inline bool nexthop_uses_dev(const struct nexthop *nh, const struct net_device *dev) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } } else { nhi = rcu_dereference(nh->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } return false; } static inline unsigned int fib_info_num_path(const struct fib_info *fi) { if (unlikely(fi->nh)) return nexthop_num_path(fi->nh); return fi->fib_nhs; } int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack); static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) { if (unlikely(fi->nh)) return nexthop_fib_nhc(fi->nh, nhsel); return &fi->fib_nh[nhsel].nh_common; } /* only used when fib_nh is built into fib_info */ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) { WARN_ON(fi->nh); return &fi->fib_nh[nhsel]; } /* * IPv6 variants */ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); /* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); nh = nexthop_mpath_select(nh_grp, 0); if (!nh) return NULL; } nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET6) return &nhi->fib6_nh; return NULL; } static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh; return fib6_nh->fib_nh_dev; } static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) { struct nexthop *nh = res->f6i->nh; struct nh_info *nhi; nh = nexthop_select_path(nh, hash); nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->reject_nh) { res->fib6_type = RTN_BLACKHOLE; res->fib6_flags |= RTF_REJECT; res->nh = nexthop_fib6_nh(nh); } else { res->nh = &nhi->fib6_nh; } } int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg); static inline int nexthop_get_family(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->family; } static inline struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh, int hash) { struct nh_info *nhi; struct nexthop *nhp; nhp = nexthop_select_path(nh, hash); if (unlikely(!nhp)) return NULL; nhi = rcu_dereference(nhp->nh_info); return &nhi->fib_nhc; } #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <net/netdev_lock.h> #include "netlink.h" #include "common.h" #include "bitset.h" struct features_req_info { struct ethnl_req_info base; }; struct features_reply_data { struct ethnl_reply_data base; u32 hw[ETHTOOL_DEV_FEATURE_WORDS]; u32 wanted[ETHTOOL_DEV_FEATURE_WORDS]; u32 active[ETHTOOL_DEV_FEATURE_WORDS]; u32 nochange[ETHTOOL_DEV_FEATURE_WORDS]; u32 all[ETHTOOL_DEV_FEATURE_WORDS]; }; #define FEATURES_REPDATA(__reply_base) \ container_of(__reply_base, struct features_reply_data, base) const struct nla_policy ethnl_features_get_policy[] = { [ETHTOOL_A_FEATURES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static void ethnl_features_to_bitmap32(u32 *dest, netdev_features_t src) { unsigned int i; for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; i++) dest[i] = src >> (32 * i); } static int features_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct features_reply_data *data = FEATURES_REPDATA(reply_base); struct net_device *dev = reply_base->dev; netdev_features_t all_features; ethnl_features_to_bitmap32(data->hw, dev->hw_features); ethnl_features_to_bitmap32(data->wanted, dev->wanted_features); ethnl_features_to_bitmap32(data->active, dev->features); ethnl_features_to_bitmap32(data->nochange, NETIF_F_NEVER_CHANGE); all_features = GENMASK_ULL(NETDEV_FEATURE_COUNT - 1, 0); ethnl_features_to_bitmap32(data->all, all_features); return 0; } static int features_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct features_reply_data *data = FEATURES_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; unsigned int len = 0; int ret; ret = ethnl_bitset32_size(data->hw, data->all, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; len += ret; ret = ethnl_bitset32_size(data->wanted, NULL, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; len += ret; ret = ethnl_bitset32_size(data->active, NULL, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; len += ret; ret = ethnl_bitset32_size(data->nochange, NULL, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; len += ret; return len; } static int features_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct features_reply_data *data = FEATURES_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_HW, data->hw, data->all, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_WANTED, data->wanted, NULL, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; ret = ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_ACTIVE, data->active, NULL, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) return ret; return ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_NOCHANGE, data->nochange, NULL, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); } const struct ethnl_request_ops ethnl_features_request_ops = { .request_cmd = ETHTOOL_MSG_FEATURES_GET, .reply_cmd = ETHTOOL_MSG_FEATURES_GET_REPLY, .hdr_attr = ETHTOOL_A_FEATURES_HEADER, .req_info_size = sizeof(struct features_req_info), .reply_data_size = sizeof(struct features_reply_data), .prepare_data = features_prepare_data, .reply_size = features_reply_size, .fill_reply = features_fill_reply, }; /* FEATURES_SET */ const struct nla_policy ethnl_features_set_policy[] = { [ETHTOOL_A_FEATURES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_FEATURES_WANTED] = { .type = NLA_NESTED }, }; static void ethnl_features_to_bitmap(unsigned long *dest, netdev_features_t val) { const unsigned int words = BITS_TO_LONGS(NETDEV_FEATURE_COUNT); unsigned int i; for (i = 0; i < words; i++) dest[i] = (unsigned long)(val >> (i * BITS_PER_LONG)); } static netdev_features_t ethnl_bitmap_to_features(unsigned long *src) { const unsigned int nft_bits = sizeof(netdev_features_t) * BITS_PER_BYTE; const unsigned int words = BITS_TO_LONGS(NETDEV_FEATURE_COUNT); netdev_features_t ret = 0; unsigned int i; for (i = 0; i < words; i++) ret |= (netdev_features_t)(src[i]) << (i * BITS_PER_LONG); ret &= ~(netdev_features_t)0 >> (nft_bits - NETDEV_FEATURE_COUNT); return ret; } static int features_send_reply(struct net_device *dev, struct genl_info *info, const unsigned long *wanted, const unsigned long *wanted_mask, const unsigned long *active, const unsigned long *active_mask, bool compact) { struct sk_buff *rskb; void *reply_payload; int reply_len = 0; int ret; reply_len = ethnl_reply_header_size(); ret = ethnl_bitset_size(wanted, wanted_mask, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) goto err; reply_len += ret; ret = ethnl_bitset_size(active, active_mask, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) goto err; reply_len += ret; ret = -ENOMEM; rskb = ethnl_reply_init(reply_len, dev, ETHTOOL_MSG_FEATURES_SET_REPLY, ETHTOOL_A_FEATURES_HEADER, info, &reply_payload); if (!rskb) goto err; ret = ethnl_put_bitset(rskb, ETHTOOL_A_FEATURES_WANTED, wanted, wanted_mask, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) goto nla_put_failure; ret = ethnl_put_bitset(rskb, ETHTOOL_A_FEATURES_ACTIVE, active, active_mask, NETDEV_FEATURE_COUNT, netdev_features_strings, compact); if (ret < 0) goto nla_put_failure; genlmsg_end(rskb, reply_payload); ret = genlmsg_reply(rskb, info); return ret; nla_put_failure: nlmsg_free(rskb); WARN_ONCE(1, "calculated message payload length (%d) not sufficient\n", reply_len); err: GENL_SET_ERR_MSG(info, "failed to send reply message"); return ret; } int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) { DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT); struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; struct net_device *dev; bool mod; int ret; if (!tb[ETHTOOL_A_FEATURES_WANTED]) return -EINVAL; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_FEATURES_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; rtnl_lock(); netdev_lock_ops(dev); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_unlock; ethnl_features_to_bitmap(old_active, dev->features); ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); if (ret < 0) goto out_ops; if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) { GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features"); ret = -EINVAL; goto out_ops; } /* set req_wanted bits not in req_mask from old_wanted */ bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT); bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT); bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT); if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) { dev->wanted_features &= ~dev->hw_features; dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features; __netdev_update_features(dev); } ethnl_features_to_bitmap(new_active, dev->features); mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT); ret = 0; if (!(req_info.flags & ETHTOOL_FLAG_OMIT_REPLY)) { bool compact = req_info.flags & ETHTOOL_FLAG_COMPACT_BITSETS; bitmap_xor(wanted_diff_mask, req_wanted, new_active, NETDEV_FEATURE_COUNT); bitmap_xor(active_diff_mask, old_active, new_active, NETDEV_FEATURE_COUNT); bitmap_and(wanted_diff_mask, wanted_diff_mask, req_mask, NETDEV_FEATURE_COUNT); bitmap_and(req_wanted, req_wanted, wanted_diff_mask, NETDEV_FEATURE_COUNT); bitmap_and(new_active, new_active, active_diff_mask, NETDEV_FEATURE_COUNT); ret = features_send_reply(dev, info, req_wanted, wanted_diff_mask, new_active, active_diff_mask, compact); } if (mod) netdev_features_change(dev); out_ops: ethnl_ops_complete(dev); out_unlock: netdev_unlock_ops(dev); rtnl_unlock(); ethnl_parse_header_dev_put(&req_info); return ret; } |
| 137 142 142 142 141 141 4 2 1 1 1 2 2 1 1 1 37 84 84 49 49 49 50 50 50 50 1 49 90 89 90 87 89 39 50 1 49 38 1 37 38 85 84 85 85 85 84 83 85 85 84 85 85 2 2 2 4 88 90 90 5 5 5 5 5 87 87 1 1 6 2 1 2 2 2 4 2 4 4 1 3 3 3 1 1 1 1 4 2 2 62 3 3 6 56 2 1 3 1 1 51 1 1 1 1 1 2 1 2 1 1 6 4 1 1 1 1 1 1 2 3 1 1 3 1 2 2 1 13 2 53 62 2 1 1 4 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TUN - Universal TUN/TAP device driver. * Copyright (C) 1999-2002 Maxim Krasnyansky <maxk@qualcomm.com> * * $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $ */ /* * Changes: * * Mike Kershaw <dragorn@kismetwireless.net> 2005/08/14 * Add TUNSETLINK ioctl to set the link encapsulation * * Mark Smith <markzzzsmith@yahoo.com.au> * Use eth_random_addr() for tap MAC address. * * Harald Roelle <harald.roelle@ifi.lmu.de> 2004/04/20 * Fixes in packet dropping, queue length setting and queue wakeup. * Increased default tx queue length. * Added ethtool API. * Minor cleanups * * Daniel Podlejski <underley@underley.eu.org> * Modifications for 2.3.99-pre5 kernel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "tun" #define DRV_VERSION "1.6" #define DRV_DESCRIPTION "Universal TUN/TAP device driver" #define DRV_COPYRIGHT "(C) 1999-2004 Max Krasnyansky <maxk@qualcomm.com>" #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/miscdevice.h> #include <linux/ethtool.h> #include <linux/rtnetlink.h> #include <linux/compat.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_tun.h> #include <linux/if_vlan.h> #include <linux/crc32.h> #include <linux/math.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <net/xdp.h> #include <net/ip_tunnels.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/skb_array.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> #include <linux/ieee802154.h> #include <uapi/linux/if_ltalk.h> #include <uapi/linux/if_fddi.h> #include <uapi/linux/if_hippi.h> #include <uapi/linux/if_fc.h> #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> #include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> #include "tun_vnet.h" static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd); #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ /* IFF_ATTACH_QUEUE is never stored in device flags, * overload it to mean fasync when stored there. */ #define TUN_FASYNC IFF_ATTACH_QUEUE #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 struct tap_filter { unsigned int count; /* Number of addrs. Zero means disabled */ u32 mask[2]; /* Mask of the hashed addrs */ unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; }; /* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal * to max number of VCPUs in guest. */ #define MAX_TAP_QUEUES 256 #define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) /* A tun_file connects an open character device to a tuntap netdevice. It * also contains all socket related structures (except sock_fprog and tap_filter) * to serve as one transmit queue for tuntap device. The sock_fprog and * tap_filter were kept in tun_struct since they were used for filtering for the * netdevice not for a specific queue (at least I didn't see the requirement for * this). * * RCU usage: * The tun_file and tun_struct are loosely coupled, the pointer from one to the * other can only be read while rcu_read_lock or rtnl_lock is held. */ struct tun_file { struct sock sk; struct socket socket; struct tun_struct __rcu *tun; struct fasync_struct *fasync; /* only used for fasnyc */ unsigned int flags; union { u16 queue_index; unsigned int ifindex; }; struct napi_struct napi; bool napi_enabled; bool napi_frags_enabled; struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; }; struct tun_page { struct page *page; int count; }; struct tun_flow_entry { struct hlist_node hash_link; struct rcu_head rcu; struct tun_struct *tun; u32 rxhash; u32 rps_rxhash; int queue_index; unsigned long updated ____cacheline_aligned_in_smp; }; #define TUN_NUM_FLOW_ENTRIES 1024 #define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1) struct tun_prog { struct rcu_head rcu; struct bpf_prog *prog; }; /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the * file were attached to a persist device. */ struct tun_struct { struct tun_file __rcu *tfiles[MAX_TAP_QUEUES]; unsigned int numqueues; unsigned int flags; kuid_t owner; kgid_t group; struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4 | \ NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM) int align; int vnet_hdr_sz; int sndbuf; struct tap_filter txflt; struct sock_fprog fprog; /* protected by rtnl lock */ bool filter_attached; u32 msg_enable; spinlock_t lock; struct hlist_head flows[TUN_NUM_FLOW_ENTRIES]; struct timer_list flow_gc_timer; unsigned long ageing_time; unsigned int numdisabled; struct list_head disabled; void *security; u32 flow_count; u32 rx_batched; atomic_long_t rx_frame_errors; struct bpf_prog __rcu *xdp_prog; struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; /* init args */ struct file *file; struct ifreq *ifr; }; struct veth { __be16 h_vlan_proto; __be16 h_vlan_TCI; }; static void tun_flow_init(struct tun_struct *tun); static void tun_flow_uninit(struct tun_struct *tun); static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; struct sk_buff *skb; int received = 0; __skb_queue_head_init(&process_queue); spin_lock(&queue->lock); skb_queue_splice_tail_init(queue, &process_queue); spin_unlock(&queue->lock); while (received < budget && (skb = __skb_dequeue(&process_queue))) { napi_gro_receive(napi, skb); ++received; } if (!skb_queue_empty(&process_queue)) { spin_lock(&queue->lock); skb_queue_splice(&process_queue, queue); spin_unlock(&queue->lock); } return received; } static int tun_napi_poll(struct napi_struct *napi, int budget) { unsigned int received; received = tun_napi_receive(napi, budget); if (received < budget) napi_complete_done(napi, received); return received; } static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, bool napi_en, bool napi_frags) { tfile->napi_enabled = napi_en; tfile->napi_frags_enabled = napi_en && napi_frags; if (napi_en) { netif_napi_add_tx(tun->dev, &tfile->napi, tun_napi_poll); napi_enable(&tfile->napi); } } static void tun_napi_enable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_enable(&tfile->napi); } static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) napi_disable(&tfile->napi); } static void tun_napi_del(struct tun_file *tfile) { if (tfile->napi_enabled) netif_napi_del(&tfile->napi); } static bool tun_napi_frags_enabled(const struct tun_file *tfile) { return tfile->napi_frags_enabled; } static inline u32 tun_hashfn(u32 rxhash) { return rxhash & TUN_MASK_FLOW_ENTRIES; } static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) { struct tun_flow_entry *e; hlist_for_each_entry_rcu(e, head, hash_link) { if (e->rxhash == rxhash) return e; } return NULL; } static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, struct hlist_head *head, u32 rxhash, u16 queue_index) { struct tun_flow_entry *e = kmalloc_obj(*e, GFP_ATOMIC); if (e) { netif_info(tun, tx_queued, tun->dev, "create flow: hash %u index %u\n", rxhash, queue_index); e->updated = jiffies; e->rxhash = rxhash; e->rps_rxhash = 0; e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); ++tun->flow_count; } return e; } static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) { netif_info(tun, tx_queued, tun->dev, "delete flow: hash %u index %u\n", e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); --tun->flow_count; } static void tun_flow_flush(struct tun_struct *tun) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) tun_flow_delete(tun, e); } spin_unlock_bh(&tun->lock); } static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) { int i; spin_lock_bh(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { if (e->queue_index == queue_index) tun_flow_delete(tun, e); } } spin_unlock_bh(&tun->lock); } static void tun_flow_cleanup(struct timer_list *t) { struct tun_struct *tun = timer_container_of(tun, t, flow_gc_timer); unsigned long delay = tun->ageing_time; unsigned long next_timer = jiffies + delay; unsigned long count = 0; int i; spin_lock(&tun->lock); for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { struct tun_flow_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { unsigned long this_timer; this_timer = e->updated + delay; if (time_before_eq(this_timer, jiffies)) { tun_flow_delete(tun, e); continue; } count++; if (time_before(this_timer, next_timer)) next_timer = this_timer; } } if (count) mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); spin_unlock(&tun->lock); } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; u16 queue_index = tfile->queue_index; head = &tun->flows[tun_hashfn(rxhash)]; rcu_read_lock(); e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ if (READ_ONCE(e->queue_index) != queue_index) WRITE_ONCE(e->queue_index, queue_index); if (e->updated != jiffies) e->updated = jiffies; sock_rps_record_flow_hash(e->rps_rxhash); } else { spin_lock_bh(&tun->lock); if (!tun_flow_find(head, rxhash) && tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index); if (!timer_pending(&tun->flow_gc_timer)) mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + delay)); spin_unlock_bh(&tun->lock); } rcu_read_unlock(); } /* Save the hash received in the stack receive path and update the * flow_hash table accordingly. */ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) { if (unlikely(e->rps_rxhash != hash)) e->rps_rxhash = hash; } /* We try to identify a flow through its rxhash. The reason that * we do not check rxq no. is because some cards(e.g 82599), chooses * the rxq based on the txq where the last packet of the flow comes. As * the userspace application move between processors, we may get a * different rxq no. here. */ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_flow_entry *e; u32 txq, numqueues; numqueues = READ_ONCE(tun->numqueues); txq = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); if (e) { tun_flow_save_rps_rxhash(e, txq); txq = e->queue_index; } else { txq = reciprocal_scale(txq, numqueues); } return txq; } static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) { struct tun_prog *prog; u32 numqueues; u16 ret = 0; numqueues = READ_ONCE(tun->numqueues); if (!numqueues) return 0; prog = rcu_dereference(tun->steering_prog); if (prog) ret = bpf_prog_run_clear_cb(prog->prog, skb); return ret % numqueues; } static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct tun_struct *tun = netdev_priv(dev); u16 ret; rcu_read_lock(); if (rcu_dereference(tun->steering_prog)) ret = tun_ebpf_select_queue(tun, skb); else ret = tun_automq_select_queue(tun, skb); rcu_read_unlock(); return ret; } static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || (gid_valid(tun->group) && !in_egroup_p(tun->group))) && !ns_capable(net->user_ns, CAP_NET_ADMIN); } static void tun_set_real_num_queues(struct tun_struct *tun) { netif_set_real_num_tx_queues(tun->dev, tun->numqueues); netif_set_real_num_rx_queues(tun->dev, tun->numqueues); } static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile) { tfile->detached = tun; list_add_tail(&tfile->next, &tun->disabled); ++tun->numdisabled; } static struct tun_struct *tun_enable_queue(struct tun_file *tfile) { struct tun_struct *tun = tfile->detached; tfile->detached = NULL; list_del_init(&tfile->next); --tun->numdisabled; return tun; } void tun_ptr_free(void *ptr) { if (!ptr) return; if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); xdp_return_frame(xdpf); } else { __skb_array_destroy_skb(ptr); } } EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { void *ptr; while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL) tun_ptr_free(ptr); skb_queue_purge(&tfile->sk.sk_write_queue); skb_queue_purge(&tfile->sk.sk_error_queue); } static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; struct tun_struct *tun; tun = rtnl_dereference(tfile->tun); if (tun && clean) { if (!tfile->detached) tun_napi_disable(tfile); tun_napi_del(tfile); } if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); --tun->numqueues; if (clean) { RCU_INIT_POINTER(tfile->tun, NULL); sock_put(&tfile->sk); } else { tun_disable_queue(tun, tfile); tun_napi_disable(tfile); } synchronize_net(); tun_flow_delete_by_queue(tun, tun->numqueues + 1); /* Drop read queue */ tun_queue_purge(tfile); tun_set_real_num_queues(tun); } else if (tfile->detached && clean) { tun = tun_enable_queue(tfile); sock_put(&tfile->sk); } if (clean) { if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { netif_carrier_off(tun->dev); if (!(tun->flags & IFF_PERSIST) && tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); } } static void tun_detach(struct tun_file *tfile, bool clean) { struct tun_struct *tun; struct net_device *dev; rtnl_lock(); tun = rtnl_dereference(tfile->tun); dev = tun ? tun->dev : NULL; __tun_detach(tfile, clean); if (dev) netdev_state_change(dev); rtnl_unlock(); if (clean) sock_put(&tfile->sk); } static void tun_detach_all(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile, *tmp; int i, n = tun->numqueues; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); tun_napi_disable(tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); --tun->numqueues; } list_for_each_entry(tfile, &tun->disabled, next) { tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); } BUG_ON(tun->numqueues != 0); synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tun_napi_del(tfile); /* Drop read queue */ tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_napi_del(tfile); tun_enable_queue(tfile); tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } BUG_ON(tun->numdisabled != 0); if (tun->flags & IFF_PERSIST) module_put(THIS_MODULE); } static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter, bool napi, bool napi_frags, bool publish_tun) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); if (err < 0) goto out; err = -EINVAL; if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; if (!(tun->flags & IFF_MULTI_QUEUE) && tun->numqueues == 1) goto out; err = -E2BIG; if (!tfile->detached && tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) goto out; err = 0; /* Re-attach the filter to persist device */ if (!skip_filter && (tun->filter_attached == true)) { lock_sock(tfile->socket.sk); err = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (!err) goto out; } if (!tfile->detached && ptr_ring_resize(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free)) { err = -ENOMEM; goto out; } tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; if (tfile->detached) { /* Re-attach detached tfile, updating XDP queue_index */ WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); if (tfile->xdp_rxq.queue_index != tfile->queue_index) tfile->xdp_rxq.queue_index = tfile->queue_index; } else { /* Setup XDP RX-queue info, for new tfile getting attached */ err = xdp_rxq_info_reg(&tfile->xdp_rxq, tun->dev, tfile->queue_index, 0); if (err < 0) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) { xdp_rxq_info_unreg(&tfile->xdp_rxq); goto out; } err = 0; } if (tfile->detached) { tun_enable_queue(tfile); tun_napi_enable(tfile); } else { sock_hold(&tfile->sk); tun_napi_init(tun, tfile, napi, napi_frags); } if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); /* device is allowed to go away first, so no need to hold extra * refcnt. */ /* Publish tfile->tun and tun->tfiles only after we've fully * initialized tfile; otherwise we risk using half-initialized * object. */ if (publish_tun) rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; tun_set_real_num_queues(tun); out: return err; } static struct tun_struct *tun_get(struct tun_file *tfile) { struct tun_struct *tun; rcu_read_lock(); tun = rcu_dereference(tfile->tun); if (tun) dev_hold(tun->dev); rcu_read_unlock(); return tun; } static void tun_put(struct tun_struct *tun) { dev_put(tun->dev); } /* TAP filtering */ static void addr_hash_set(u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; mask[n >> 5] |= (1 << (n & 31)); } static unsigned int addr_hash_test(const u32 *mask, const u8 *addr) { int n = ether_crc(ETH_ALEN, addr) >> 26; return mask[n >> 5] & (1 << (n & 31)); } static int update_filter(struct tap_filter *filter, void __user *arg) { struct { u8 u[ETH_ALEN]; } *addr; struct tun_filter uf; int err, alen, n, nexact; if (copy_from_user(&uf, arg, sizeof(uf))) return -EFAULT; if (!uf.count) { /* Disabled */ filter->count = 0; return 0; } alen = ETH_ALEN * uf.count; addr = memdup_user(arg + sizeof(uf), alen); if (IS_ERR(addr)) return PTR_ERR(addr); /* The filter is updated without holding any locks. Which is * perfectly safe. We disable it first and in the worst * case we'll accept a few undesired packets. */ filter->count = 0; wmb(); /* Use first set of addresses as an exact filter */ for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++) memcpy(filter->addr[n], addr[n].u, ETH_ALEN); nexact = n; /* Remaining multicast addresses are hashed, * unicast will leave the filter disabled. */ memset(filter->mask, 0, sizeof(filter->mask)); for (; n < uf.count; n++) { if (!is_multicast_ether_addr(addr[n].u)) { err = 0; /* no filter */ goto free_addr; } addr_hash_set(filter->mask, addr[n].u); } /* For ALLMULTI just set the mask to all ones. * This overrides the mask populated above. */ if ((uf.flags & TUN_FLT_ALLMULTI)) memset(filter->mask, ~0, sizeof(filter->mask)); /* Now enable the filter */ wmb(); filter->count = nexact; /* Return the number of exact filters */ err = nexact; free_addr: kfree(addr); return err; } /* Returns: 0 - drop, !=0 - accept */ static int run_filter(struct tap_filter *filter, const struct sk_buff *skb) { /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect * at this point. */ struct ethhdr *eh = (struct ethhdr *) skb->data; int i; /* Exact match */ for (i = 0; i < filter->count; i++) if (ether_addr_equal(eh->h_dest, filter->addr[i])) return 1; /* Inexact match (multicast only) */ if (is_multicast_ether_addr(eh->h_dest)) return addr_hash_test(filter->mask, eh->h_dest); return 0; } /* * Checks whether the packet is accepted or not. * Returns: 0 - drop, !=0 - accept */ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) { if (!filter->count) return 1; return run_filter(filter, skb); } /* Network device part of the driver */ static const struct ethtool_ops tun_ethtool_ops; static int tun_net_init(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); struct ifreq *ifr = tun->ifr; int err; spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); if (err < 0) return err; tun_flow_init(tun); dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->hw_enc_features = dev->hw_features; dev->features = dev->hw_features; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->lltx = true; tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, false); if (err < 0) { tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); return err; } return 0; } /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { tun_detach_all(dev); } /* Net device open. */ static int tun_net_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } /* Net device close. */ static int tun_net_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } /* Net device start xmit */ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { #ifdef CONFIG_RPS if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ struct tun_flow_entry *e; __u32 rxhash; rxhash = __skb_get_hash_symmetric(skb); e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], rxhash); if (e) tun_flow_save_rps_rxhash(e, rxhash); } #endif } static unsigned int run_ebpf_filter(struct tun_struct *tun, struct sk_buff *skb, int len) { struct tun_prog *prog = rcu_dereference(tun->filter_prog); if (prog) len = bpf_prog_run_clear_cb(prog->prog, skb); return len; } /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); /* Drop packet if interface is not attached */ if (!tfile) { drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (!rcu_dereference(tun->steering_prog)) tun_automq_xmit(tun, skb); netif_info(tun, tx_queued, tun->dev, "%s %d\n", __func__, skb->len); /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ if (!check_filter(&tun->txflt, skb)) { drop_reason = SKB_DROP_REASON_TAP_TXFILTER; goto drop; } if (tfile->socket.sk->sk_filter && sk_filter_reason(tfile->socket.sk, skb, &drop_reason)) goto drop; len = run_ebpf_filter(tun, skb, len); if (len == 0) { drop_reason = SKB_DROP_REASON_TAP_FILTER; goto drop; } if (pskb_trim(skb, len)) { drop_reason = SKB_DROP_REASON_NOMEM; goto drop; } if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) { drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. */ skb_orphan(skb); nf_reset_ct(skb); if (ptr_ring_produce(&tfile->tx_ring, skb)) { drop_reason = SKB_DROP_REASON_FULL_RING; goto drop; } /* dev->lltx requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); rcu_read_unlock(); return NETDEV_TX_OK; drop: dev_core_stats_tx_dropped_inc(dev); skb_tx_error(skb); kfree_skb_reason(skb, drop_reason); rcu_read_unlock(); return NET_XMIT_DROP; } static void tun_net_mclist(struct net_device *dev) { /* * This callback is supposed to deal with mc filter in * _rx_ path and has nothing to do with the _tx_ path. * In rx path we always accept everything userspace gives us. */ } static netdev_features_t tun_net_fix_features(struct net_device *dev, netdev_features_t features) { struct tun_struct *tun = netdev_priv(dev); return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } static void tun_set_headroom(struct net_device *dev, int new_hr) { struct tun_struct *tun = netdev_priv(dev); if (new_hr < NET_SKB_PAD) new_hr = NET_SKB_PAD; tun->align = new_hr; } static void tun_net_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct tun_struct *tun = netdev_priv(dev); dev_get_tstats64(dev, stats); stats->rx_frame_errors += (unsigned long)atomic_long_read(&tun->rx_frame_errors); } static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; struct bpf_prog *old_prog; int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } list_for_each_entry(tfile, &tun->disabled, next) { if (prog) sock_set_flag(&tfile->sk, SOCK_XDP); else sock_reset_flag(&tfile->sk, SOCK_XDP); } return 0; } static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return tun_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) { if (new_carrier) { struct tun_struct *tun = netdev_priv(dev); if (!tun->numqueues) return -EPERM; netif_carrier_on(dev); } else { netif_carrier_off(dev); } return 0; } static const struct net_device_ops tun_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_select_queue = tun_select_queue, .ndo_set_rx_headroom = tun_set_headroom, .ndo_get_stats64 = tun_net_get_stats64, .ndo_change_carrier = tun_net_change_carrier, }; static void __tun_xdp_flush_tfile(struct tun_file *tfile) { /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); tfile->socket.sk->sk_data_ready(tfile->socket.sk); } static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; u32 numqueues; int nxmit = 0; int i; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); resample: numqueues = READ_ONCE(tun->numqueues); if (!numqueues) { rcu_read_unlock(); return -ENXIO; /* Caller will free/return all frames */ } tfile = rcu_dereference(tun->tfiles[smp_processor_id() % numqueues]); if (unlikely(!tfile)) goto resample; spin_lock(&tfile->tx_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *xdp = frames[i]; /* Encode the XDP flag into lowest bit for consumer to differ * XDP buffer from sk_buff. */ void *frame = tun_xdp_to_ptr(xdp); if (__ptr_ring_produce(&tfile->tx_ring, frame)) { dev_core_stats_tx_dropped_inc(dev); break; } nxmit++; } spin_unlock(&tfile->tx_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __tun_xdp_flush_tfile(tfile); rcu_read_unlock(); return nxmit; } static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); int nxmit; if (unlikely(!frame)) return -EOVERFLOW; nxmit = tun_xdp_xmit(dev, 1, &frame, XDP_XMIT_FLUSH); if (!nxmit) xdp_return_frame_rx_napi(frame); return nxmit; } static const struct net_device_ops tap_netdev_ops = { .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, .ndo_start_xmit = tun_net_xmit, .ndo_fix_features = tun_net_fix_features, .ndo_set_rx_mode = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, }; static void tun_flow_init(struct tun_struct *tun) { int i; for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) INIT_HLIST_HEAD(&tun->flows[i]); tun->ageing_time = TUN_FLOW_EXPIRE; timer_setup(&tun->flow_gc_timer, tun_flow_cleanup, 0); mod_timer(&tun->flow_gc_timer, round_jiffies_up(jiffies + tun->ageing_time)); } static void tun_flow_uninit(struct tun_struct *tun) { timer_delete_sync(&tun->flow_gc_timer); tun_flow_flush(tun); } #define MIN_MTU 68 #define MAX_MTU 65535 /* Initialize net device. */ static void tun_net_initialize(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: dev->netdev_ops = &tun_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; /* Point-to-Point TUN Device */ dev->hard_header_len = 0; dev->addr_len = 0; dev->mtu = 1500; /* Zero header length */ dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; break; case IFF_TAP: dev->netdev_ops = &tap_netdev_ops; /* Ethernet TAP Device */ ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; eth_hw_addr_random(dev); /* Currently tun does not support XDP, only tap does. */ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT; break; } dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU - dev->hard_header_len; } static bool tun_sock_writeable(struct tun_struct *tun, struct tun_file *tfile) { struct sock *sk = tfile->socket.sk; return (tun->dev->flags & IFF_UP) && sock_writeable(sk); } /* Character device part */ /* Poll */ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); struct sock *sk; __poll_t mask = 0; if (!tun) return EPOLLERR; sk = tfile->socket.sk; poll_wait(file, sk_sleep(sk), wait); if (!ptr_ring_empty(&tfile->tx_ring)) mask |= EPOLLIN | EPOLLRDNORM; /* Make sure SOCKWQ_ASYNC_NOSPACE is set if not writable to * guarantee EPOLLOUT to be raised by either here or * tun_sock_write_space(). Then process could get notification * after it writes to a down device and meets -EIO. */ if (tun_sock_writeable(tun, tfile) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && tun_sock_writeable(tun, tfile))) mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) mask = EPOLLERR; tun_put(tun); return mask; } static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, size_t len, const struct iov_iter *it) { struct sk_buff *skb; size_t linear; int err; int i; if (it->nr_segs > MAX_SKB_FRAGS + 1 || len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); skb = napi_get_frags(&tfile->napi); local_bh_enable(); if (!skb) return ERR_PTR(-ENOMEM); linear = iov_iter_single_seg_count(it); err = __skb_grow(skb, linear); if (err) goto free; skb->len = len; skb->data_len = len - linear; skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; if (fragsz == 0 || fragsz > PAGE_SIZE) { err = -EINVAL; goto free; } frag = netdev_alloc_frag(fragsz); if (!frag) { err = -ENOMEM; goto free; } page = virt_to_head_page(frag); skb_fill_page_desc(skb, i - 1, page, frag - page_address(page), fragsz); } return skb; free: /* frees skb and all frags allocated with napi_alloc_frag() */ napi_free_frags(&tfile->napi); return ERR_PTR(err); } /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, size_t prepad, size_t len, size_t linear, int noblock) { struct sock *sk = tfile->socket.sk; struct sk_buff *skb; int err; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, &err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return ERR_PTR(err); skb_reserve(skb, prepad); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static void tun_rx_batched(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, int more) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; struct sk_buff_head process_queue; u32 rx_batched = tun->rx_batched; bool rcv = false; if (!rx_batched || (!more && skb_queue_empty(queue))) { local_bh_disable(); skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); return; } spin_lock(&queue->lock); if (!more || skb_queue_len(queue) == rx_batched) { __skb_queue_head_init(&process_queue); skb_queue_splice_tail_init(queue, &process_queue); rcv = true; } else { __skb_queue_tail(queue, skb); } spin_unlock(&queue->lock); if (rcv) { struct sk_buff *nskb; local_bh_disable(); while ((nskb = __skb_dequeue(&process_queue))) { skb_record_rx_queue(nskb, tfile->queue_index); netif_receive_skb(nskb); } skb_record_rx_queue(skb, tfile->queue_index); netif_receive_skb(skb); local_bh_enable(); } } static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, int len, int noblock, bool zerocopy) { if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) return false; if (tfile->socket.sk->sk_sndbuf != INT_MAX) return false; if (!noblock) return false; if (zerocopy) return false; if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; return true; } static struct sk_buff *__tun_build_skb(struct tun_file *tfile, struct page_frag *alloc_frag, char *buf, int buflen, int len, int pad, int metasize) { struct sk_buff *skb = build_skb(buf, buflen); if (!skb) return ERR_PTR(-ENOMEM); skb_reserve(skb, pad); skb_put(skb, len); if (metasize) skb_metadata_set(skb, metasize); skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen; return skb; } static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, struct xdp_buff *xdp, u32 act) { int err; switch (act) { case XDP_REDIRECT: err = xdp_do_redirect(tun->dev, xdp, xdp_prog); if (err) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_TX: err = tun_xdp_tx(tun->dev, xdp); if (err < 0) { dev_core_stats_rx_dropped_inc(tun->dev); return err; } dev_sw_netstats_rx_add(tun->dev, xdp->data_end - xdp->data); break; case XDP_PASS: break; default: bpf_warn_invalid_xdp_action(tun->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); fallthrough; case XDP_DROP: dev_core_stats_rx_dropped_inc(tun->dev); break; } return act; } static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, struct virtio_net_hdr *hdr, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); char *buf; size_t copied; int pad = TUN_RX_PAD; int metasize = 0; int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) return ERR_PTR(-ENOMEM); buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; copied = copy_page_from_iter(alloc_frag->page, alloc_frag->offset + pad, len, from); if (copied != len) return ERR_PTR(-EFAULT); /* There's a small window that XDP may be set after the check * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); } *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { struct xdp_buff xdp; u32 act; xdp_init_buff(&xdp, buflen, &tfile->xdp_rxq); xdp_prepare_buff(&xdp, buf, pad, len, true); act = bpf_prog_run_xdp(xdp_prog, &xdp); if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; } err = tun_xdp_act(tun, xdp_prog, &xdp, act); if (err < 0) { if (act == XDP_REDIRECT || act == XDP_TX) put_page(alloc_frag->page); goto out; } if (err == XDP_REDIRECT) xdp_do_flush(); if (err != XDP_PASS) goto out; pad = xdp.data - xdp.data_hard_start; len = xdp.data_end - xdp.data; /* It is known that the xdp_buff was prepared with metadata * support, so the metasize will never be negative. */ metasize = xdp.data - xdp.data_meta; } bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad, metasize); out: bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); return NULL; } /* Get packet from user space buffer */ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, void *msg_control, struct iov_iter *from, int noblock, bool more) { struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; struct sk_buff *skb; size_t total_len = iov_iter_count(from); size_t len = total_len, align = tun->align, linear; struct virtio_net_hdr_v1_hash_tunnel hdr; struct virtio_net_hdr *gso; int good_linear; int copylen; int hdr_len = 0; bool zerocopy = false; int err; u32 rxhash = 0; int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tfile); enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; netdev_features_t features = 0; /* * Keep it easy and always zero the whole buffer, even if the * tunnel-related field will be touched only when the feature * is enabled and the hdr size id compatible. */ memset(&hdr, 0, sizeof(hdr)); gso = (struct virtio_net_hdr *)&hdr; if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; len -= sizeof(pi); if (!copy_from_iter_full(&pi, sizeof(pi), from)) return -EFAULT; } if (tun->flags & IFF_VNET_HDR) { int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); features = tun_vnet_hdr_guest_features(vnet_hdr_sz); hdr_len = __tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, features, from, gso); if (hdr_len < 0) return hdr_len; len -= vnet_hdr_sz; } if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) { align += NET_IP_ALIGN; if (unlikely(len < ETH_HLEN || (hdr_len && hdr_len < ETH_HLEN))) return -EINVAL; } good_linear = SKB_MAX_HEAD(align); if (msg_control) { struct iov_iter i = *from; /* There are 256 bytes to be copied in skb, so there is * enough room for skb expand head in case it is used. * The rest of the buffer is mapped from userspace. */ copylen = min(hdr_len ? hdr_len : GOODCOPY_LEN, good_linear); linear = copylen; iov_iter_advance(&i, copylen); if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS) zerocopy = true; } if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { /* For the packet that is not easy to be processed * (e.g gso or jumbo packet), we will do it at after * skb was created with generic XDP routine. */ skb = tun_build_skb(tun, tfile, from, gso, len, &skb_xdp); err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (!skb) return total_len; } else { if (!zerocopy) { copylen = len; linear = min(hdr_len, good_linear); } if (frags) { mutex_lock(&tfile->napi_mutex); skb = tun_napi_alloc_frags(tfile, copylen, from); /* tun_napi_alloc_frags() enforces a layout for the skb. * If zerocopy is enabled, then this layout will be * overwritten by zerocopy_sg_from_iter(). */ zerocopy = false; } else { if (!linear) linear = min_t(size_t, good_linear, copylen); skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); } err = PTR_ERR_OR_ZERO(skb); if (err) goto drop; if (zerocopy) err = zerocopy_sg_from_iter(skb, from); else err = skb_copy_datagram_from_iter(skb, 0, from, len); if (err) { err = -EFAULT; drop_reason = SKB_DROP_REASON_SKB_UCOPY_FAULT; goto drop; } } if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) { atomic_long_inc(&tun->rx_frame_errors); err = -EINVAL; goto free_skb; } switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; switch (ip_version) { case 4: pi.proto = htons(ETH_P_IP); break; case 6: pi.proto = htons(ETH_P_IPV6); break; default: err = -EINVAL; goto drop; } } skb_reset_mac_header(skb); skb->protocol = pi.proto; skb->dev = tun->dev; break; case IFF_TAP: if (frags && !pskb_may_pull(skb, ETH_HLEN)) { err = -ENOMEM; drop_reason = SKB_DROP_REASON_HDR_TRUNC; goto drop; } skb->protocol = eth_type_trans(skb, tun->dev); break; } /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { skb_zcopy_init(skb, msg_control); } else if (msg_control) { struct ubuf_info *uarg = msg_control; uarg->ops->complete(NULL, uarg, false); } skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { struct bpf_prog *xdp_prog; int ret; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { rcu_read_unlock(); local_bh_enable(); goto unlock_frags; } if (frags && skb != tfile->napi.skb) tfile->napi.skb = skb; } rcu_read_unlock(); local_bh_enable(); } /* Compute the costly rx hash only if needed for flow updates. * We may get a very small possibility of OOO during switching, not * worth to optimize. */ if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); rcu_read_lock(); if (unlikely(!(tun->dev->flags & IFF_UP))) { err = -EIO; rcu_read_unlock(); drop_reason = SKB_DROP_REASON_DEV_READY; goto drop; } if (frags) { u32 headlen; /* Exercise flow dissector code path. */ skb_push(skb, ETH_HLEN); headlen = eth_get_headlen(tun->dev, skb->data, skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { WARN_ON_ONCE(1); err = -ENOMEM; dev_core_stats_rx_dropped_inc(tun->dev); napi_busy: napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); return err; } if (likely(napi_schedule_prep(&tfile->napi))) { local_bh_disable(); napi_gro_frags(&tfile->napi); napi_complete(&tfile->napi); local_bh_enable(); } else { err = -EBUSY; goto napi_busy; } mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; spin_lock_bh(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock_bh(&queue->lock); rcu_read_unlock(); err = -EBUSY; goto free_skb; } __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); if (!more || queue_len > NAPI_POLL_WEIGHT) napi_schedule(&tfile->napi); local_bh_enable(); } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { tun_rx_batched(tun, tfile, skb, more); } else { netif_rx(skb); } rcu_read_unlock(); preempt_disable(); dev_sw_netstats_rx_add(tun->dev, len); preempt_enable(); if (rxhash) tun_flow_update(tun, rxhash, tfile); return total_len; drop: if (err != -EAGAIN) dev_core_stats_rx_dropped_inc(tun->dev); free_skb: if (!IS_ERR_OR_NULL(skb)) kfree_skb_reason(skb, drop_reason); unlock_frags: if (frags) { tfile->napi.skb = NULL; mutex_unlock(&tfile->napi_mutex); } return err ?: total_len; } static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t result; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; result = tun_get_user(tun, tfile, NULL, from, noblock, false); tun_put(tun); return result; } static ssize_t tun_put_user_xdp(struct tun_struct *tun, struct tun_file *tfile, struct xdp_frame *xdp_frame, struct iov_iter *iter) { int vnet_hdr_sz = 0; size_t size = xdp_frame->len; ssize_t ret; if (tun->flags & IFF_VNET_HDR) { struct virtio_net_hdr gso = { 0 }; vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso); if (ret) return ret; } ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, ret); preempt_enable(); return ret; } /* Put packet to the user space buffer */ static ssize_t tun_put_user(struct tun_struct *tun, struct tun_file *tfile, struct sk_buff *skb, struct iov_iter *iter) { struct tun_pi pi = { 0, skb->protocol }; ssize_t total; int vlan_offset = 0; int vlan_hlen = 0; int vnet_hdr_sz = 0; int ret; if (skb_vlan_tag_present(skb)) vlan_hlen = VLAN_HLEN; if (tun->flags & IFF_VNET_HDR) vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz); total = skb->len + vlan_hlen + vnet_hdr_sz; if (!(tun->flags & IFF_NO_PI)) { if (iov_iter_count(iter) < sizeof(pi)) return -EINVAL; total += sizeof(pi); if (iov_iter_count(iter) < total) { /* Packet will be striped */ pi.flags |= TUN_PKT_STRIP; } if (copy_to_iter(&pi, sizeof(pi), iter) != sizeof(pi)) return -EFAULT; } if (vnet_hdr_sz) { struct virtio_net_hdr_v1_hash_tunnel hdr; struct virtio_net_hdr *gso; ret = tun_vnet_hdr_tnl_from_skb(tun->flags, tun->dev, skb, &hdr); if (ret) return ret; /* * Drop the packet if the configured header size is too small * WRT the enabled offloads. */ gso = (struct virtio_net_hdr *)&hdr; ret = __tun_vnet_hdr_put(vnet_hdr_sz, tun->dev->features, iter, gso); if (ret) return ret; } if (vlan_hlen) { int ret; struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset); if (ret || !iov_iter_count(iter)) goto done; ret = copy_to_iter(&veth, sizeof(veth), iter); if (ret != sizeof(veth) || !iov_iter_count(iter)) goto done; } skb_copy_datagram_iter(skb, vlan_offset, iter, skb->len - vlan_offset); done: /* caller is in process context, */ preempt_disable(); dev_sw_netstats_tx_add(tun->dev, 1, skb->len + vlan_hlen); preempt_enable(); return total; } static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) { DECLARE_WAITQUEUE(wait, current); void *ptr = NULL; int error = 0; ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) goto out; if (noblock) { error = -EAGAIN; goto out; } add_wait_queue(&tfile->socket.wq.wait, &wait); while (1) { set_current_state(TASK_INTERRUPTIBLE); ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) break; if (signal_pending(current)) { error = -ERESTARTSYS; break; } if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { error = -EFAULT; break; } schedule(); } __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->socket.wq.wait, &wait); out: *err = error; return ptr; } static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock, void *ptr) { ssize_t ret; int err; if (!iov_iter_count(to)) { tun_ptr_free(ptr); return 0; } if (!ptr) { /* Read frames from ring */ ptr = tun_ring_recv(tfile, noblock, &err); if (!ptr) return err; } if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); ret = tun_put_user_xdp(tun, tfile, xdpf, to); xdp_return_frame(xdpf); } else { struct sk_buff *skb = ptr; ret = tun_put_user(tun, tfile, skb, to); if (unlikely(ret < 0)) kfree_skb(skb); else consume_skb(skb); } return ret; } static ssize_t tun_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); ssize_t len = iov_iter_count(to), ret; int noblock = 0; if (!tun) return -EBADFD; if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) noblock = 1; ret = tun_do_read(tun, tfile, to, noblock, NULL); ret = min_t(ssize_t, ret, len); if (ret > 0) iocb->ki_pos = ret; tun_put(tun); return ret; } static void tun_prog_free(struct rcu_head *rcu) { struct tun_prog *prog = container_of(rcu, struct tun_prog, rcu); bpf_prog_destroy(prog->prog); kfree(prog); } static int __tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, struct bpf_prog *prog) { struct tun_prog *old, *new = NULL; if (prog) { new = kmalloc_obj(*new); if (!new) return -ENOMEM; new->prog = prog; } spin_lock_bh(&tun->lock); old = rcu_dereference_protected(*prog_p, lockdep_is_held(&tun->lock)); rcu_assign_pointer(*prog_p, new); spin_unlock_bh(&tun->lock); if (old) call_rcu(&old->rcu, tun_prog_free); return 0; } static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); BUG_ON(!(list_empty(&tun->disabled))); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); tun->owner = INVALID_UID; tun->group = INVALID_GID; tun_default_link_ksettings(dev, &tun->link_ksettings); dev->ethtool_ops = &tun_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = tun_free_netdev; /* We prefer our own queue length */ dev->tx_queue_len = TUN_READQ_SIZE; } /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ static int tun_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "tun/tap creation via rtnetlink is not supported."); return -EOPNOTSUPP; } static size_t tun_get_size(const struct net_device *dev) { BUILD_BUG_ON(sizeof(u32) != sizeof(uid_t)); BUILD_BUG_ON(sizeof(u32) != sizeof(gid_t)); return nla_total_size(sizeof(uid_t)) + /* OWNER */ nla_total_size(sizeof(gid_t)) + /* GROUP */ nla_total_size(sizeof(u8)) + /* TYPE */ nla_total_size(sizeof(u8)) + /* PI */ nla_total_size(sizeof(u8)) + /* VNET_HDR */ nla_total_size(sizeof(u8)) + /* PERSIST */ nla_total_size(sizeof(u8)) + /* MULTI_QUEUE */ nla_total_size(sizeof(u32)) + /* NUM_QUEUES */ nla_total_size(sizeof(u32)) + /* NUM_DISABLED_QUEUES */ 0; } static int tun_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); if (nla_put_u8(skb, IFLA_TUN_TYPE, tun->flags & TUN_TYPE_MASK)) goto nla_put_failure; if (uid_valid(tun->owner) && nla_put_u32(skb, IFLA_TUN_OWNER, from_kuid_munged(current_user_ns(), tun->owner))) goto nla_put_failure; if (gid_valid(tun->group) && nla_put_u32(skb, IFLA_TUN_GROUP, from_kgid_munged(current_user_ns(), tun->group))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PI, !(tun->flags & IFF_NO_PI))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_VNET_HDR, !!(tun->flags & IFF_VNET_HDR))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_PERSIST, !!(tun->flags & IFF_PERSIST))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_TUN_MULTI_QUEUE, !!(tun->flags & IFF_MULTI_QUEUE))) goto nla_put_failure; if (tun->flags & IFF_MULTI_QUEUE) { if (nla_put_u32(skb, IFLA_TUN_NUM_QUEUES, tun->numqueues)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_TUN_NUM_DISABLED_QUEUES, tun->numdisabled)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops tun_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct tun_struct), .setup = tun_setup, .validate = tun_validate, .get_size = tun_get_size, .fill_info = tun_fill_info, }; static void tun_sock_write_space(struct sock *sk) { struct tun_file *tfile; wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } static void tun_put_page(struct tun_page *tpage) { if (tpage->page) __page_frag_cache_drain(tpage->page, tpage->count); } static int tun_xdp_one(struct tun_struct *tun, struct tun_file *tfile, struct xdp_buff *xdp, int *flush, struct tun_page *tpage) { unsigned int datasize = xdp->data_end - xdp->data; struct virtio_net_hdr *gso = xdp->data_hard_start; struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr; struct bpf_prog *xdp_prog; struct sk_buff *skb = NULL; struct sk_buff_head *queue; netdev_features_t features; u32 rxhash = 0, act; int buflen = xdp->frame_sz; int metasize = 0; int ret = 0; bool skb_xdp = false; struct page *page; if (unlikely(datasize < ETH_HLEN)) return -EINVAL; xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) { if (gso->gso_type) { skb_xdp = true; goto build; } xdp_init_buff(xdp, buflen, &tfile->xdp_rxq); act = bpf_prog_run_xdp(xdp_prog, xdp); ret = tun_xdp_act(tun, xdp_prog, xdp, act); if (ret < 0) { put_page(virt_to_head_page(xdp->data)); return ret; } switch (ret) { case XDP_REDIRECT: *flush = true; fallthrough; case XDP_TX: return 0; case XDP_PASS: break; default: page = virt_to_head_page(xdp->data); if (tpage->page == page) { ++tpage->count; } else { tun_put_page(tpage); tpage->page = page; tpage->count = 1; } return 0; } } build: skb = build_skb(xdp->data_hard_start, buflen); if (!skb) { ret = -ENOMEM; goto out; } skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); /* The externally provided xdp_buff may have no metadata support, which * is marked by xdp->data_meta being xdp->data + 1. This will lead to a * metasize of -1 and is the reason why the condition checks for > 0. */ metasize = xdp->data - xdp->data_meta; if (metasize > 0) skb_metadata_set(skb, metasize); features = tun_vnet_hdr_guest_features(READ_ONCE(tun->vnet_hdr_sz)); tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso; if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) { atomic_long_inc(&tun->rx_frame_errors); kfree_skb(skb); ret = -EINVAL; goto out; } skb->protocol = eth_type_trans(skb, tun->dev); skb_reset_network_header(skb); skb_probe_transport_header(skb); skb_record_rx_queue(skb, tfile->queue_index); if (skb_xdp) { ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { ret = 0; goto out; } } if (!rcu_dereference(tun->steering_prog) && tun->numqueues > 1 && !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); if (unlikely(tfile->detached)) { spin_unlock(&queue->lock); kfree_skb(skb); return -EBUSY; } __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; } else { netif_receive_skb(skb); ret = 0; } /* No need to disable preemption here since this function is * always called with bh disabled */ dev_sw_netstats_rx_add(tun->dev, datasize); if (rxhash) tun_flow_update(tun, rxhash, tfile); out: return ret; } static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); struct tun_msg_ctl *ctl = m->msg_control; struct xdp_buff *xdp; if (!tun) return -EBADFD; if (m->msg_controllen == sizeof(struct tun_msg_ctl) && ctl && ctl->type == TUN_MSG_PTR) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct tun_page tpage; int n = ctl->num; int flush = 0, queued = 0; memset(&tpage, 0, sizeof(tpage)); local_bh_disable(); rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); for (i = 0; i < n; i++) { xdp = &((struct xdp_buff *)ctl->ptr)[i]; ret = tun_xdp_one(tun, tfile, xdp, &flush, &tpage); if (ret > 0) queued += ret; } if (flush) xdp_do_flush(); if (tfile->napi_enabled && queued > 0) napi_schedule(&tfile->napi); bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); local_bh_enable(); tun_put_page(&tpage); ret = total_len; goto out; } ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); out: tun_put(tun); return ret; } static int tun_recvmsg(struct socket *sock, struct msghdr *m, size_t total_len, int flags) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); void *ptr = m->msg_control; int ret; if (!tun) { ret = -EBADFD; goto out_free; } if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; goto out_put_tun; } if (flags & MSG_ERRQUEUE) { ret = sock_recv_errqueue(sock->sk, m, total_len, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr); if (ret > (ssize_t)total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; } out: tun_put(tun); return ret; out_put_tun: tun_put(tun); out_free: tun_ptr_free(ptr); return ret; } static int tun_ptr_peek_len(void *ptr) { if (likely(ptr)) { if (tun_is_xdp_frame(ptr)) { struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); return xdpf->len; } return __skb_array_len_with_tag(ptr); } else { return 0; } } static int tun_peek_len(struct socket *sock) { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun; int ret = 0; tun = tun_get(tfile); if (!tun) return 0; ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len); tun_put(tun); return ret; } /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; static struct proto tun_proto = { .name = "tun", .owner = THIS_MODULE, .obj_size = sizeof(struct tun_file), }; static int tun_flags(struct tun_struct *tun) { return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP); } static ssize_t tun_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return sysfs_emit(buf, "0x%x\n", tun_flags(tun)); } static ssize_t owner_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return uid_valid(tun->owner)? sysfs_emit(buf, "%u\n", from_kuid_munged(current_user_ns(), tun->owner)) : sysfs_emit(buf, "-1\n"); } static ssize_t group_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return gid_valid(tun->group) ? sysfs_emit(buf, "%u\n", from_kgid_munged(current_user_ns(), tun->group)) : sysfs_emit(buf, "-1\n"); } static DEVICE_ATTR_RO(tun_flags); static DEVICE_ATTR_RO(owner); static DEVICE_ATTR_RO(group); static struct attribute *tun_dev_attrs[] = { &dev_attr_tun_flags.attr, &dev_attr_owner.attr, &dev_attr_group.attr, NULL }; static const struct attribute_group tun_attr_group = { .attrs = tun_dev_attrs }; static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) { struct tun_struct *tun; struct tun_file *tfile = file->private_data; struct net_device *dev; int err; if (tfile->detached) return -EINVAL; if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!(ifr->ifr_flags & IFF_NAPI) || (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) return -EINVAL; } dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) return -EBUSY; if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops) tun = netdev_priv(dev); else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops) tun = netdev_priv(dev); else return -EINVAL; if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; if (tun_not_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) return err; err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, ifr->ifr_flags & IFF_NAPI, ifr->ifr_flags & IFF_NAPI_FRAGS, true); if (err < 0) return err; if (tun->flags & IFF_MULTI_QUEUE && (tun->numqueues + tun->numdisabled > 1)) { /* One or more queue has already been attached, no need * to initialize the device again. */ netdev_state_change(dev); return 0; } tun->flags = (tun->flags & ~TUN_FEATURES) | (ifr->ifr_flags & TUN_FEATURES); netdev_state_change(dev); } else { char *name; unsigned long flags = 0; int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = security_tun_dev_create(); if (err < 0) return err; /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { /* TUN device */ flags |= IFF_TUN; name = "tun%d"; } else if (ifr->ifr_flags & IFF_TAP) { /* TAP device */ flags |= IFF_TAP; name = "tap%d"; } else return -EINVAL; if (*ifr->ifr_name) name = ifr->ifr_name; dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, NET_NAME_UNKNOWN, tun_setup, queues, queues); if (!dev) return -ENOMEM; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; dev->ifindex = tfile->ifindex; dev->sysfs_groups[0] = &tun_attr_group; tun = netdev_priv(dev); tun->dev = dev; tun->flags = flags; tun->txflt.count = 0; tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); tun->align = NET_SKB_PAD; tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); tun->ifr = ifr; tun->file = file; tun_net_initialize(dev); err = register_netdevice(tun->dev); if (err < 0) { free_netdev(dev); return err; } /* free_netdev() won't check refcnt, to avoid race * with dev_put() we need publish tun after registration. */ rcu_assign_pointer(tfile->tun, tun); } if (ifr->ifr_flags & IFF_NO_CARRIER) netif_carrier_off(tun->dev); else netif_carrier_on(tun->dev); /* Make sure persistent devices do not get stuck in * xoff state. */ if (netif_running(tun->dev)) netif_tx_wake_all_queues(tun->dev); strscpy(ifr->ifr_name, tun->dev->name); return 0; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) { strscpy(ifr->ifr_name, tun->dev->name); ifr->ifr_flags = tun_flags(tun); } #define PLAIN_GSO (NETIF_F_GSO_UDP_L4 | NETIF_F_TSO | NETIF_F_TSO6) /* This is like a cut-down ethtool ops, except done via tun fd so no * privs required. */ static int set_offload(struct tun_struct *tun, unsigned long arg) { netdev_features_t features = 0; if (arg & TUN_F_CSUM) { features |= NETIF_F_HW_CSUM; arg &= ~TUN_F_CSUM; if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { if (arg & TUN_F_TSO_ECN) { features |= NETIF_F_TSO_ECN; arg &= ~TUN_F_TSO_ECN; } if (arg & TUN_F_TSO4) features |= NETIF_F_TSO; if (arg & TUN_F_TSO6) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } arg &= ~TUN_F_UFO; /* TODO: for now USO4 and USO6 should work simultaneously */ if (arg & TUN_F_USO4 && arg & TUN_F_USO6) { features |= NETIF_F_GSO_UDP_L4; arg &= ~(TUN_F_USO4 | TUN_F_USO6); } /* * Tunnel offload is allowed only if some plain offload is * available, too. */ if (features & PLAIN_GSO && arg & TUN_F_UDP_TUNNEL_GSO) { features |= NETIF_F_GSO_UDP_TUNNEL; if (arg & TUN_F_UDP_TUNNEL_GSO_CSUM) features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; arg &= ~(TUN_F_UDP_TUNNEL_GSO | TUN_F_UDP_TUNNEL_GSO_CSUM); } } /* This gives the user a way to test for new features in future by * trying to set them. */ if (arg) return -EINVAL; tun->set_features = features; tun->dev->wanted_features &= ~TUN_USER_FEATURES; tun->dev->wanted_features |= features; netdev_update_features(tun->dev); return 0; } static void tun_detach_filter(struct tun_struct *tun, int n) { int i; struct tun_file *tfile; for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); sk_detach_filter(tfile->socket.sk); release_sock(tfile->socket.sk); } tun->filter_attached = false; } static int tun_attach_filter(struct tun_struct *tun) { int i, ret = 0; struct tun_file *tfile; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); lock_sock(tfile->socket.sk); ret = sk_attach_filter(&tun->fprog, tfile->socket.sk); release_sock(tfile->socket.sk); if (ret) { tun_detach_filter(tun, i); return ret; } } tun->filter_attached = true; return ret; } static void tun_set_sndbuf(struct tun_struct *tun) { struct tun_file *tfile; int i; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_sndbuf = tun->sndbuf; } } static int tun_set_queue(struct file *file, struct ifreq *ifr) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; int ret = 0; rtnl_lock(); if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { tun = tfile->detached; if (!tun) { ret = -EINVAL; goto unlock; } ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI, tun->flags & IFF_NAPI_FRAGS, true); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); } else ret = -EINVAL; if (ret >= 0) netdev_state_change(tun->dev); unlock: rtnl_unlock(); return ret; } static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, void __user *data) { struct bpf_prog *prog; int fd; if (copy_from_user(&fd, data, sizeof(fd))) return -EFAULT; if (fd == -1) { prog = NULL; } else { prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) return PTR_ERR(prog); } return __tun_set_ebpf(tun, prog_p, prog); } /* Return correct value for tun->dev->addr_len based on tun->dev->type. */ static unsigned char tun_get_addr_len(unsigned short type) { switch (type) { case ARPHRD_IP6GRE: case ARPHRD_TUNNEL6: return sizeof(struct in6_addr); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: case ARPHRD_SIT: return 4; case ARPHRD_ETHER: return ETH_ALEN; case ARPHRD_IEEE802154: case ARPHRD_IEEE802154_MONITOR: return IEEE802154_EXTENDED_ADDR_LEN; case ARPHRD_PHONET_PIPE: case ARPHRD_PPP: case ARPHRD_NONE: return 0; case ARPHRD_6LOWPAN: return EUI64_ADDR_LEN; case ARPHRD_FDDI: return FDDI_K_ALEN; case ARPHRD_HIPPI: return HIPPI_ALEN; case ARPHRD_IEEE802: return FC_ALEN; case ARPHRD_ROSE: return ROSE_ADDR_LEN; case ARPHRD_NETROM: return AX25_ADDR_LEN; case ARPHRD_LOCALTLK: return LTALK_ALEN; default: return 0; } } static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; unsigned int carrier; struct ifreq ifr; kuid_t owner; kgid_t group; int ifindex; int sndbuf; int ret; bool do_notify = false; if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || (_IOC_TYPE(cmd) == SOCK_IOC_TYPE && cmd != SIOCGSKNS)) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; } else { memset(&ifr, 0, sizeof(ifr)); } if (cmd == TUNGETFEATURES) { /* Currently this just means: "what IFF flags are valid?". * This is needed because we never checked for invalid flags on * TUNSETIFF. */ return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER | TUN_FEATURES, (unsigned int __user*)argp); } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); } else if (cmd == SIOCGSKNS) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; return open_related_ns(&net->ns, get_net_ns); } rtnl_lock(); tun = tun_get(tfile); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) goto unlock; ifr.ifr_name[IFNAMSIZ-1] = '\0'; ret = tun_set_iff(net, file, &ifr); if (ret) goto unlock; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; goto unlock; } if (cmd == TUNSETIFINDEX) { ret = -EPERM; if (tun) goto unlock; ret = -EFAULT; if (copy_from_user(&ifindex, argp, sizeof(ifindex))) goto unlock; ret = -EINVAL; if (ifindex < 0) goto unlock; ret = 0; tfile->ifindex = ifindex; goto unlock; } ret = -EBADFD; if (!tun) goto unlock; netif_info(tun, drv, tun->dev, "tun_chr_ioctl cmd %u\n", cmd); net = dev_net(tun->dev); ret = 0; switch (cmd) { case TUNGETIFF: tun_get_iff(tun, &ifr); if (tfile->detached) ifr.ifr_flags |= IFF_DETACH_QUEUE; if (!tfile->socket.sk->sk_filter) ifr.ifr_flags |= IFF_NOFILTER; if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case TUNSETNOCSUM: /* Disable/Enable checksum */ /* [unimplemented] */ netif_info(tun, drv, tun->dev, "ignored: set checksum %s\n", arg ? "disabled" : "enabled"); break; case TUNSETPERSIST: /* Disable/Enable persist mode. Keep an extra reference to the * module to prevent the module being unprobed. */ if (arg && !(tun->flags & IFF_PERSIST)) { tun->flags |= IFF_PERSIST; __module_get(THIS_MODULE); do_notify = true; } if (!arg && (tun->flags & IFF_PERSIST)) { tun->flags &= ~IFF_PERSIST; module_put(THIS_MODULE); do_notify = true; } netif_info(tun, drv, tun->dev, "persist %s\n", arg ? "enabled" : "disabled"); break; case TUNSETOWNER: /* Set owner of the device */ owner = make_kuid(current_user_ns(), arg); if (!uid_valid(owner)) { ret = -EINVAL; break; } tun->owner = owner; do_notify = true; netif_info(tun, drv, tun->dev, "owner set to %u\n", from_kuid(&init_user_ns, tun->owner)); break; case TUNSETGROUP: /* Set group of the device */ group = make_kgid(current_user_ns(), arg); if (!gid_valid(group)) { ret = -EINVAL; break; } tun->group = group; do_notify = true; netif_info(tun, drv, tun->dev, "group set to %u\n", from_kgid(&init_user_ns, tun->group)); break; case TUNSETLINK: /* Only allow setting the type when the interface is down */ if (tun->dev->flags & IFF_UP) { netif_info(tun, drv, tun->dev, "Linktype set failed because interface is up\n"); ret = -EBUSY; } else { ret = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, tun->dev); ret = notifier_to_errno(ret); if (ret) { netif_info(tun, drv, tun->dev, "Refused to change device type\n"); break; } tun->dev->type = (int) arg; tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, tun->dev); } break; case TUNSETDEBUG: tun->msg_enable = (u32)arg; break; case TUNSETOFFLOAD: ret = set_offload(tun, arg); break; case TUNSETTXFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = update_filter(&tun->txflt, (void __user *)arg); break; case SIOCGIFHWADDR: /* Get hw address */ netif_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; case SIOCSIFHWADDR: /* Set hw address */ if (tun->dev->addr_len > sizeof(ifr.ifr_hwaddr)) { ret = -EINVAL; break; } ret = dev_set_mac_address_user(tun->dev, (struct sockaddr_storage *)&ifr.ifr_hwaddr, NULL); break; case TUNGETSNDBUF: sndbuf = tfile->socket.sk->sk_sndbuf; if (copy_to_user(argp, &sndbuf, sizeof(sndbuf))) ret = -EFAULT; break; case TUNSETSNDBUF: if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) { ret = -EFAULT; break; } if (sndbuf <= 0) { ret = -EINVAL; break; } tun->sndbuf = sndbuf; tun_set_sndbuf(tun); break; case TUNATTACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog))) break; ret = tun_attach_filter(tun); break; case TUNDETACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = 0; tun_detach_filter(tun, tun->numqueues); break; case TUNGETFILTER: ret = -EINVAL; if ((tun->flags & TUN_TYPE_MASK) != IFF_TAP) break; ret = -EFAULT; if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) break; ret = 0; break; case TUNSETSTEERINGEBPF: ret = tun_set_ebpf(tun, &tun->steering_prog, argp); break; case TUNSETFILTEREBPF: ret = tun_set_ebpf(tun, &tun->filter_prog, argp); break; case TUNSETCARRIER: ret = -EFAULT; if (copy_from_user(&carrier, argp, sizeof(carrier))) goto unlock; ret = tun_net_change_carrier(tun->dev, (bool)carrier); break; case TUNGETDEVNETNS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto unlock; ret = open_related_ns(&net->ns, get_net_ns); break; default: ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp); break; } if (do_notify) netdev_state_change(tun->dev); unlock: rtnl_unlock(); if (tun) tun_put(tun); return ret; } static long tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq)); } #ifdef CONFIG_COMPAT static long tun_chr_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { case TUNSETIFF: case TUNGETIFF: case TUNSETTXFILTER: case TUNGETSNDBUF: case TUNSETSNDBUF: case SIOCGIFHWADDR: case SIOCSIFHWADDR: arg = (unsigned long)compat_ptr(arg); break; default: arg = (compat_ulong_t)arg; break; } /* * compat_ifreq is shorter than ifreq, so we must not access beyond * the end of that structure. All fields that are used in this * driver are compatible though, we don't need to convert the * contents. */ return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq)); } #endif /* CONFIG_COMPAT */ static int tun_chr_fasync(int fd, struct file *file, int on) { struct tun_file *tfile = file->private_data; int ret; if (on) { ret = file_f_owner_allocate(file); if (ret) goto out; } if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) goto out; if (on) { __f_setown(file, task_pid(current), PIDTYPE_TGID, 0); tfile->flags |= TUN_FASYNC; } else tfile->flags &= ~TUN_FASYNC; ret = 0; out: return ret; } static int tun_chr_open(struct inode *inode, struct file * file) { struct net *net = current->nsproxy->net_ns; struct tun_file *tfile; tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto, 0); if (!tfile) return -ENOMEM; if (ptr_ring_init(&tfile->tx_ring, 0, GFP_KERNEL)) { sk_free(&tfile->sk); return -ENOMEM; } mutex_init(&tfile->napi_mutex); RCU_INIT_POINTER(tfile->tun, NULL); tfile->flags = 0; tfile->ifindex = 0; init_waitqueue_head(&tfile->socket.wq.wait); tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; sock_init_data_uid(&tfile->socket, &tfile->sk, current_fsuid()); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; file->private_data = tfile; INIT_LIST_HEAD(&tfile->next); sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); /* tun groks IOCB_NOWAIT just fine, mark it as such */ file->f_mode |= FMODE_NOWAIT; return 0; } static int tun_chr_close(struct inode *inode, struct file *file) { struct tun_file *tfile = file->private_data; tun_detach(tfile, true); return 0; } #ifdef CONFIG_PROC_FS static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) { struct tun_file *tfile = file->private_data; struct tun_struct *tun; struct ifreq ifr; memset(&ifr, 0, sizeof(ifr)); rtnl_lock(); tun = tun_get(tfile); if (tun) tun_get_iff(tun, &ifr); rtnl_unlock(); if (tun) tun_put(tun); seq_printf(m, "iff:\t%s\n", ifr.ifr_name); } #endif static const struct file_operations tun_fops = { .owner = THIS_MODULE, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, .unlocked_ioctl = tun_chr_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = tun_chr_compat_ioctl, #endif .open = tun_chr_open, .release = tun_chr_close, .fasync = tun_chr_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = tun_chr_show_fdinfo, #endif }; static struct miscdevice tun_miscdev = { .minor = TUN_MINOR, .name = "tun", .nodename = "net/tun", .fops = &tun_fops, }; /* ethtool interface */ static void tun_default_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { ethtool_link_ksettings_zero_link_mode(cmd, supported); ethtool_link_ksettings_zero_link_mode(cmd, advertising); cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.phy_address = 0; cmd->base.autoneg = AUTONEG_DISABLE; } static int tun_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(cmd, &tun->link_ksettings, sizeof(*cmd)); return 0; } static int tun_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct tun_struct *tun = netdev_priv(dev); memcpy(&tun->link_ksettings, cmd, sizeof(*cmd)); return 0; } static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct tun_struct *tun = netdev_priv(dev); strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: strscpy(info->bus_info, "tun", sizeof(info->bus_info)); break; case IFF_TAP: strscpy(info->bus_info, "tap", sizeof(info->bus_info)); break; } } static u32 tun_get_msglevel(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); return tun->msg_enable; } static void tun_set_msglevel(struct net_device *dev, u32 value) { struct tun_struct *tun = netdev_priv(dev); tun->msg_enable = value; } static int tun_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); ec->rx_max_coalesced_frames = tun->rx_batched; return 0; } static int tun_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); if (ec->rx_max_coalesced_frames > NAPI_POLL_WEIGHT) tun->rx_batched = NAPI_POLL_WEIGHT; else tun->rx_batched = ec->rx_max_coalesced_frames; return 0; } static void tun_get_channels(struct net_device *dev, struct ethtool_channels *channels) { struct tun_struct *tun = netdev_priv(dev); channels->combined_count = tun->numqueues; channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1; } static const struct ethtool_ops tun_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES, .get_drvinfo = tun_get_drvinfo, .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, .get_channels = tun_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = tun_get_coalesce, .set_coalesce = tun_set_coalesce, .get_link_ksettings = tun_get_link_ksettings, .set_link_ksettings = tun_set_link_ksettings, }; static int tun_queue_resize(struct tun_struct *tun) { struct net_device *dev = tun->dev; struct tun_file *tfile; struct ptr_ring **rings; int n = tun->numqueues + tun->numdisabled; int ret, i; rings = kmalloc_objs(*rings, n); if (!rings) return -ENOMEM; for (i = 0; i < tun->numqueues; i++) { tfile = rtnl_dereference(tun->tfiles[i]); rings[i] = &tfile->tx_ring; } list_for_each_entry(tfile, &tun->disabled, next) rings[i++] = &tfile->tx_ring; ret = ptr_ring_resize_multiple_bh(rings, n, dev->tx_queue_len, GFP_KERNEL, tun_ptr_free); kfree(rings); return ret; } static int tun_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; switch (event) { case NETDEV_CHANGE_TX_QUEUE_LEN: if (tun_queue_resize(tun)) return NOTIFY_BAD; break; case NETDEV_UP: for (i = 0; i < tun->numqueues; i++) { struct tun_file *tfile; tfile = rtnl_dereference(tun->tfiles[i]); tfile->socket.sk->sk_write_space(tfile->socket.sk); } break; default: break; } return NOTIFY_DONE; } static struct notifier_block tun_notifier_block __read_mostly = { .notifier_call = tun_device_event, }; static int __init tun_init(void) { int ret = 0; pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); ret = rtnl_link_register(&tun_link_ops); if (ret) { pr_err("Can't register link_ops\n"); goto err_linkops; } ret = misc_register(&tun_miscdev); if (ret) { pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } ret = register_netdevice_notifier(&tun_notifier_block); if (ret) { pr_err("Can't register netdevice notifier\n"); goto err_notifier; } return 0; err_notifier: misc_deregister(&tun_miscdev); err_misc: rtnl_link_unregister(&tun_link_ops); err_linkops: return ret; } static void __exit tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is * attached to a device. The returned object works like a packet socket, it * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for * holding a reference to the file for as long as the socket is in use. */ struct socket *tun_get_socket(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->socket; } EXPORT_SYMBOL_GPL(tun_get_socket); struct ptr_ring *tun_get_tx_ring(struct file *file) { struct tun_file *tfile; if (file->f_op != &tun_fops) return ERR_PTR(-EINVAL); tfile = file->private_data; if (!tfile) return ERR_PTR(-EBADFD); return &tfile->tx_ring; } EXPORT_SYMBOL_GPL(tun_get_tx_ring); module_init(tun_init); module_exit(tun_cleanup); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); MODULE_ALIAS("devname:net/tun"); MODULE_IMPORT_NS("NETDEV_INTERNAL"); |
| 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 | /* * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #ifndef _TLS_OFFLOAD_H #define _TLS_OFFLOAD_H #include <linux/types.h> #include <asm/byteorder.h> #include <linux/crypto.h> #include <linux/socket.h> #include <linux/tcp.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/tcp.h> #include <net/strparser.h> #include <crypto/aead.h> #include <uapi/linux/tls.h> struct tls_rec; /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) /* Minimum record size limit as per RFC8449 */ #define TLS_MIN_RECORD_SIZE_LIM ((size_t)1 << 6) #define TLS_HEADER_SIZE 5 #define TLS_NONCE_OFFSET TLS_HEADER_SIZE #define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type) #define TLS_HANDSHAKE_KEYUPDATE 24 /* rfc8446 B.3: Key update */ #define TLS_AAD_SPACE_SIZE 13 #define TLS_MAX_IV_SIZE 16 #define TLS_MAX_SALT_SIZE 4 #define TLS_TAG_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 #define TLS_MAX_AAD_SIZE TLS_AAD_SPACE_SIZE /* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. * * IV[16] = b0[1] || implicit nonce[4] || explicit nonce[8] || length[3] * * The field 'length' is encoded in field 'b0' as '(length width - 1)'. * Hence b0 contains (3 - 1) = 2. */ #define TLS_AES_CCM_IV_B0_BYTE 2 #define TLS_SM4_CCM_IV_B0_BYTE 2 enum { TLS_BASE, TLS_SW, TLS_HW, TLS_HW_RECORD, TLS_NUM_CONFIG, }; struct tx_work { struct delayed_work work; struct sock *sk; }; struct tls_sw_context_tx { struct crypto_aead *aead_send; struct crypto_wait async_wait; struct tx_work tx_work; struct tls_rec *open_rec; struct list_head tx_list; atomic_t encrypt_pending; u8 async_capable:1; #define BIT_TX_SCHEDULED 0 #define BIT_TX_CLOSING 1 unsigned long tx_bitmask; }; struct tls_strparser { struct sock *sk; u32 mark : 8; u32 stopped : 1; u32 copy_mode : 1; u32 mixed_decrypted : 1; bool msg_ready; struct strp_msg stm; struct sk_buff *anchor; struct work_struct work; }; struct tls_sw_context_rx { struct crypto_aead *aead_recv; struct crypto_wait async_wait; struct sk_buff_head rx_list; /* list of decrypted 'data' records */ void (*saved_data_ready)(struct sock *sk); u8 reader_present; u8 async_capable:1; u8 zc_capable:1; u8 reader_contended:1; bool key_update_pending; struct tls_strparser strp; atomic_t decrypt_pending; struct sk_buff_head async_hold; struct wait_queue_head wq; }; struct tls_record_info { struct list_head list; u32 end_seq; int len; int num_frags; skb_frag_t frags[MAX_SKB_FRAGS]; }; #define TLS_DRIVER_STATE_SIZE_TX 16 struct tls_offload_context_tx { struct crypto_aead *aead_send; spinlock_t lock; /* protects records list */ struct list_head records_list; struct tls_record_info *open_record; struct tls_record_info *retransmit_hint; u64 hint_record_sn; u64 unacked_record_sn; struct scatterlist sg_tx_data[MAX_SKB_FRAGS]; void (*sk_destruct)(struct sock *sk); struct work_struct destruct_work; struct tls_context *ctx; /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ u8 driver_state[TLS_DRIVER_STATE_SIZE_TX] __aligned(8); }; enum tls_context_flags { /* tls_device_down was called after the netdev went down, device state * was released, and kTLS works in software, even though rx_conf is * still TLS_HW (needed for transition). */ TLS_RX_DEV_DEGRADED = 0, /* Unlike RX where resync is driven entirely by the core in TX only * the driver knows when things went out of sync, so we need the flag * to be atomic. */ TLS_TX_SYNC_SCHED = 1, /* tls_dev_del was called for the RX side, device state was released, * but tls_ctx->netdev might still be kept, because TX-side driver * resources might not be released yet. Used to prevent the second * tls_dev_del call in tls_device_down if it happens simultaneously. */ TLS_RX_DEV_CLOSED = 2, }; struct cipher_context { char iv[TLS_MAX_IV_SIZE + TLS_MAX_SALT_SIZE]; char rec_seq[TLS_MAX_REC_SEQ_SIZE]; }; union tls_crypto_context { struct tls_crypto_info info; union { struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; struct tls12_crypto_info_chacha20_poly1305 chacha20_poly1305; struct tls12_crypto_info_sm4_gcm sm4_gcm; struct tls12_crypto_info_sm4_ccm sm4_ccm; }; }; struct tls_prot_info { u16 version; u16 cipher_type; u16 prepend_size; u16 tag_size; u16 overhead_size; u16 iv_size; u16 salt_size; u16 rec_seq_size; u16 aad_size; u16 tail_size; }; struct tls_context { /* read-only cache line */ struct tls_prot_info prot_info; u8 tx_conf:3; u8 rx_conf:3; u8 zerocopy_sendfile:1; u8 rx_no_pad:1; u16 tx_max_payload_len; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); void *priv_ctx_tx; void *priv_ctx_rx; struct net_device __rcu *netdev; /* rw cache line */ struct cipher_context tx; struct cipher_context rx; struct scatterlist *partially_sent_record; u16 partially_sent_offset; bool splicing_pages; bool pending_open_record_frags; struct mutex tx_lock; /* protects partially_sent_* fields and * per-type TX fields */ unsigned long flags; /* cache cold stuff */ struct proto *sk_proto; struct sock *sk; void (*sk_destruct)(struct sock *sk); union tls_crypto_context crypto_send; union tls_crypto_context crypto_recv; struct list_head list; refcount_t refcount; struct rcu_head rcu; }; enum tls_offload_ctx_dir { TLS_OFFLOAD_CTX_DIR_RX, TLS_OFFLOAD_CTX_DIR_TX, }; struct tlsdev_ops { int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, enum tls_offload_ctx_dir direction, struct tls_crypto_info *crypto_info, u32 start_offload_tcp_sn); void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); int (*tls_dev_resync)(struct net_device *netdev, struct sock *sk, u32 seq, u8 *rcd_sn, enum tls_offload_ctx_dir direction); }; enum tls_offload_sync_type { TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ = 0, TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT = 1, TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC = 2, }; #define TLS_DEVICE_RESYNC_NH_START_IVAL 2 #define TLS_DEVICE_RESYNC_NH_MAX_IVAL 128 #define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13 struct tls_offload_resync_async { atomic64_t req; u16 loglen; u16 rcd_delta; u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX]; }; #define TLS_DRIVER_STATE_SIZE_RX 8 struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; enum tls_offload_sync_type resync_type; /* this member is set regardless of resync_type, to avoid branches */ u8 resync_nh_reset:1; /* CORE_NEXT_HINT-only member, but use the hole here */ u8 resync_nh_do_now:1; union { /* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ */ struct { atomic64_t resync_req; }; /* TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT */ struct { u32 decrypted_failed; u32 decrypted_tgt; } resync_nh; /* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC */ struct { struct tls_offload_resync_async *resync_async; }; }; /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ u8 driver_state[TLS_DRIVER_STATE_SIZE_RX] __aligned(8); }; struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn); static inline bool tls_record_is_start_marker(struct tls_record_info *rec) { return rec->len == 0; } static inline u32 tls_record_start_seq(struct tls_record_info *rec) { return rec->end_seq - rec->len; } struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); struct sk_buff * tls_validate_xmit_skb_sw(struct sock *sk, struct net_device *dev, struct sk_buff *skb); static inline bool tls_is_skb_tx_device_offloaded(const struct sk_buff *skb) { #ifdef CONFIG_TLS_DEVICE struct sock *sk = skb->sk; return sk && sk_fullsock(sk) && (smp_load_acquire(&sk->sk_validate_xmit_skb) == &tls_validate_xmit_skb); #else return false; #endif } static inline struct tls_context *tls_get_ctx(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code, * TLS data path doesn't need rcu_dereference(). */ return (__force void *)icsk->icsk_ulp_data; } static inline struct tls_sw_context_rx *tls_sw_ctx_rx( const struct tls_context *tls_ctx) { return (struct tls_sw_context_rx *)tls_ctx->priv_ctx_rx; } static inline struct tls_sw_context_tx *tls_sw_ctx_tx( const struct tls_context *tls_ctx) { return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx; } static inline struct tls_offload_context_tx * tls_offload_ctx_tx(const struct tls_context *tls_ctx) { return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx; } static inline bool tls_sw_has_ctx_tx(const struct sock *sk) { struct tls_context *ctx; if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk)) return false; ctx = tls_get_ctx(sk); if (!ctx) return false; return !!tls_sw_ctx_tx(ctx); } static inline bool tls_sw_has_ctx_rx(const struct sock *sk) { struct tls_context *ctx; if (!sk_is_inet(sk) || !inet_test_bit(IS_ICSK, sk)) return false; ctx = tls_get_ctx(sk); if (!ctx) return false; return !!tls_sw_ctx_rx(ctx); } static inline struct tls_offload_context_rx * tls_offload_ctx_rx(const struct tls_context *tls_ctx) { return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; } static inline void *__tls_driver_ctx(struct tls_context *tls_ctx, enum tls_offload_ctx_dir direction) { if (direction == TLS_OFFLOAD_CTX_DIR_TX) return tls_offload_ctx_tx(tls_ctx)->driver_state; else return tls_offload_ctx_rx(tls_ctx)->driver_state; } static inline void * tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) { return __tls_driver_ctx(tls_get_ctx(sk), direction); } #define RESYNC_REQ BIT(0) #define RESYNC_REQ_ASYNC BIT(1) /* The TLS context is valid until sk_destruct is called */ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | RESYNC_REQ); } /* Log all TLS record header TCP sequences in [seq, seq+len] */ static inline void tls_offload_rx_resync_async_request_start(struct tls_offload_resync_async *resync_async, __be32 seq, u16 len) { atomic64_set(&resync_async->req, ((u64)ntohl(seq) << 32) | ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC); resync_async->loglen = 0; resync_async->rcd_delta = 0; } static inline void tls_offload_rx_resync_async_request_end(struct tls_offload_resync_async *resync_async, __be32 seq) { atomic64_set(&resync_async->req, ((u64)ntohl(seq) << 32) | RESYNC_REQ); } static inline void tls_offload_rx_resync_async_request_cancel(struct tls_offload_resync_async *resync_async) { atomic64_set(&resync_async->req, 0); } static inline void tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type) { struct tls_context *tls_ctx = tls_get_ctx(sk); tls_offload_ctx_rx(tls_ctx)->resync_type = type; } /* Driver's seq tracking has to be disabled until resync succeeded */ static inline bool tls_offload_tx_resync_pending(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); bool ret; ret = test_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags); smp_mb__after_atomic(); return ret; } struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); #ifdef CONFIG_TLS_DEVICE void tls_device_sk_destruct(struct sock *sk); void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq); static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) { if (!sk_fullsock(sk) || smp_load_acquire(&sk->sk_destruct) != tls_device_sk_destruct) return false; return tls_get_ctx(sk)->rx_conf == TLS_HW; } #endif #endif /* _TLS_OFFLOAD_H */ |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/atomic.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_nat_masquerade.h> struct masq_dev_work { struct work_struct work; struct net *net; netns_tracker ns_tracker; union nf_inet_addr addr; int ifindex; int (*iter)(struct nf_conn *i, void *data); }; #define MAX_MASQ_WORKER_COUNT 16 static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, const struct nf_nat_range2 *range, const struct net_device *out) { struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; struct nf_nat_range2 newrange; const struct rtable *rt; __be32 newsrc, nh; WARN_ON(hooknum != NF_INET_POST_ROUTING); ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. */ if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0) return NF_ACCEPT; rt = skb_rtable(skb); nh = rt_nexthop(rt, ip_hdr(skb)->daddr); newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE); if (!newsrc) { pr_info("%s ate my IP address\n", out->name); return NF_DROP; } nat = nf_ct_nat_ext_add(ct); if (nat) nat->masq_index = out->ifindex; /* Transfer from original range. */ memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.ip = newsrc; newrange.max_addr.ip = newsrc; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); static void iterate_cleanup_work(struct work_struct *work) { struct nf_ct_iter_data iter_data = {}; struct masq_dev_work *w; w = container_of(work, struct masq_dev_work, work); iter_data.net = w->net; iter_data.data = (void *)w; nf_ct_iterate_cleanup_net(w->iter, &iter_data); put_net_track(w->net, &w->ns_tracker); kfree(w); atomic_dec(&masq_worker_count); module_put(THIS_MODULE); } /* Iterate conntrack table in the background and remove conntrack entries * that use the device/address being removed. * * In case too many work items have been queued already or memory allocation * fails iteration is skipped, conntrack entries will time out eventually. */ static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, int ifindex, int (*iter)(struct nf_conn *i, void *data), gfp_t gfp_flags) { struct masq_dev_work *w; if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) return; net = maybe_get_net(net); if (!net) return; if (!try_module_get(THIS_MODULE)) goto err_module; w = kzalloc_obj(*w, gfp_flags); if (w) { /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ atomic_inc(&masq_worker_count); INIT_WORK(&w->work, iterate_cleanup_work); w->ifindex = ifindex; w->net = net; netns_tracker_alloc(net, &w->ns_tracker, gfp_flags); w->iter = iter; if (addr) w->addr = *addr; schedule_work(&w->work); return; } module_put(THIS_MODULE); err_module: put_net(net); } static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); const struct masq_dev_work *w = arg; if (!nat) return 0; return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) { /* Device was downed. Search entire table for * conntracks which were associated with that device, * and forget them. */ nf_nat_masq_schedule(net, NULL, dev->ifindex, device_cmp, GFP_KERNEL); } return NOTIFY_DONE; } static int inet_cmp(struct nf_conn *ct, void *ptr) { struct nf_conntrack_tuple *tuple; struct masq_dev_work *w = ptr; if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { const struct in_ifaddr *ifa = ptr; const struct in_device *idev; const struct net_device *dev; union nf_inet_addr addr; if (event != NETDEV_DOWN) return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; memset(&addr, 0, sizeof(addr)); addr.ip = ifa->ifa_address; dev = idev->dev; nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; #if IS_ENABLED(CONFIG_IPV6) static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr) { #ifdef CONFIG_IPV6_MODULE const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (!v6_ops) return -EHOSTUNREACH; return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr); #else return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr); #endif } unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out) { enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; struct in6_addr src; struct nf_conn *ct; struct nf_nat_range2 newrange; ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out, &ipv6_hdr(skb)->daddr, 0, &src) < 0) return NF_DROP; nat = nf_ct_nat_ext_add(ct); if (nat) nat->masq_index = out->ifindex; newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.in6 = src; newrange.max_addr.in6 = src; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount of ipv6 * addresses being deleted), we also need to limit work item queue. */ static int masq_inet6_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; union nf_inet_addr addr; if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; memset(&addr, 0, sizeof(addr)); addr.in6 = ifa->addr; nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, GFP_ATOMIC); return NOTIFY_DONE; } static struct notifier_block masq_inet6_notifier = { .notifier_call = masq_inet6_event, }; static int nf_nat_masquerade_ipv6_register_notifier(void) { return register_inet6addr_notifier(&masq_inet6_notifier); } #else static inline int nf_nat_masquerade_ipv6_register_notifier(void) { return 0; } #endif int nf_nat_masquerade_inet_register_notifiers(void) { int ret = 0; mutex_lock(&masq_mutex); if (WARN_ON_ONCE(masq_refcnt == UINT_MAX)) { ret = -EOVERFLOW; goto out_unlock; } /* check if the notifier was already set */ if (++masq_refcnt > 1) goto out_unlock; /* Register for device down reports */ ret = register_netdevice_notifier(&masq_dev_notifier); if (ret) goto err_dec; /* Register IP address change reports */ ret = register_inetaddr_notifier(&masq_inet_notifier); if (ret) goto err_unregister; ret = nf_nat_masquerade_ipv6_register_notifier(); if (ret) goto err_unreg_inet; mutex_unlock(&masq_mutex); return ret; err_unreg_inet: unregister_inetaddr_notifier(&masq_inet_notifier); err_unregister: unregister_netdevice_notifier(&masq_dev_notifier); err_dec: masq_refcnt--; out_unlock: mutex_unlock(&masq_mutex); return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_register_notifiers); void nf_nat_masquerade_inet_unregister_notifiers(void) { mutex_lock(&masq_mutex); /* check if the notifiers still have clients */ if (--masq_refcnt > 0) goto out_unlock; unregister_netdevice_notifier(&masq_dev_notifier); unregister_inetaddr_notifier(&masq_inet_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&masq_inet6_notifier); #endif out_unlock: mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_unregister_notifiers); |
| 1 699 30 4 714 | 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-only */ #ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H #include <linux/bits.h> #include <asm/barrier.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif /* * Generic definitions for bit operations, should not be used in regular code * directly. */ /** * generic___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic and may be reordered. * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ static __always_inline void generic___set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p |= mask; } static __always_inline void generic___clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p &= ~mask; } /** * generic___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic and may be reordered. * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ static __always_inline void generic___change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p ^= mask; } /** * generic___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic and can be reordered. * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ static __always_inline bool generic___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old | mask; return (old & mask) != 0; } /** * generic___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic and can be reordered. * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ static __always_inline bool generic___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old & ~mask; return (old & mask) != 0; } /* WARNING: non atomic and it can be reordered! */ static __always_inline bool generic___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old ^ mask; return (old & mask) != 0; } /** * generic_test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool generic_test_bit(unsigned long nr, const volatile unsigned long *addr) { /* * Unlike the bitops with the '__' prefix above, this one *is* atomic, * so `volatile` must always stay here with no cast-aways. See * `Documentation/atomic_bitops.txt` for the details. */ return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } /** * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1))); } /* * const_*() definitions provide good compile-time optimizations when * the passed arguments can be resolved at compile time. */ #define const___set_bit generic___set_bit #define const___clear_bit generic___clear_bit #define const___change_bit generic___change_bit #define const___test_and_set_bit generic___test_and_set_bit #define const___test_and_clear_bit generic___test_and_clear_bit #define const___test_and_change_bit generic___test_and_change_bit #define const_test_bit_acquire generic_test_bit_acquire /** * const_test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from * * A version of generic_test_bit() which discards the `volatile` qualifier to * allow a compiler to optimize code harder. Non-atomic and to be called only * for testing compile-time constants, e.g. by the corresponding macros, not * directly from "regular" code. */ static __always_inline bool const_test_bit(unsigned long nr, const volatile unsigned long *addr) { const unsigned long *p = (const unsigned long *)addr + BIT_WORD(nr); unsigned long mask = BIT_MASK(nr); unsigned long val = *p; return !!(val & mask); } #endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */ |
| 41 224 43 222 130 10 | 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 | /* 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/bug.h> #include <linux/cache.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> #include <linux/hash.h> enum _slab_flag_bits { _SLAB_CONSISTENCY_CHECKS, _SLAB_RED_ZONE, _SLAB_POISON, _SLAB_KMALLOC, _SLAB_HWCACHE_ALIGN, _SLAB_CACHE_DMA, _SLAB_CACHE_DMA32, _SLAB_STORE_USER, _SLAB_PANIC, _SLAB_TYPESAFE_BY_RCU, _SLAB_TRACE, #ifdef CONFIG_DEBUG_OBJECTS _SLAB_DEBUG_OBJECTS, #endif _SLAB_NOLEAKTRACE, _SLAB_NO_MERGE, #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif #ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC _SLAB_KASAN, #endif _SLAB_NO_USER_FLAGS, #ifdef CONFIG_KFENCE _SLAB_SKIP_KFENCE, #endif #ifndef CONFIG_SLUB_TINY _SLAB_RECLAIM_ACCOUNT, #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, _SLAB_NO_OBJ_EXT, #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) _SLAB_OBJ_EXT_IN_OBJ, #endif _SLAB_FLAGS_LAST_BIT }; #define __SLAB_FLAG_BIT(nr) ((slab_flags_t __force)(1U << (nr))) #define __SLAB_FLAG_UNUSED ((slab_flags_t __force)(0U)) /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS __SLAB_FLAG_BIT(_SLAB_CONSISTENCY_CHECKS) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE __SLAB_FLAG_BIT(_SLAB_RED_ZONE) /* DEBUG: Poison objects */ #define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON) /* Indicate a kmalloc slab */ #define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC) /** * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries. * * Sufficiently large objects are aligned on cache line boundary. For object * size smaller than a half of cache line size, the alignment is on the half of * cache line size. In general, if object size is smaller than 1/2^n of cache * line size, the alignment is adjusted to 1/2^n. * * If explicit alignment is also requested by the respective * &struct kmem_cache_args field, the greater of both is alignments is applied. */ #define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 __SLAB_FLAG_BIT(_SLAB_CACHE_DMA32) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC) /** * define 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: * * :: * * begin: * rcu_read_lock(); * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * rcu_read_unlock(); * goto begin; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * rcu_read_unlock(); * goto begin; * } * } * 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 object identity check has to be done *after* acquiring a * reference, therefore user has to ensure proper ordering for loads. * Similarly, when initializing objects allocated with SLAB_TYPESAFE_BY_RCU, * the newly allocated object has to be fully initialized *before* its * refcount gets initialized and proper ordering for stores is required. * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() are * designed with the proper fences required for reference counting objects * allocated with SLAB_TYPESAFE_BY_RCU. * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages * are not zeroed before being given to the slab, which means that any * locks must be initialized after each and every kmem_struct_alloc(). * Alternatively, make the ctor passed to kmem_cache_create() initialize * the locks at page-allocation time, as is done in __i915_request_ctor(), * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers * to safely acquire those ctor-initialized locks under rcu_read_lock() * protection. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ #define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU) /* Trace allocations and frees */ #define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_BIT(_SLAB_DEBUG_OBJECTS) #else # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_UNUSED #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE __SLAB_FLAG_BIT(_SLAB_NOLEAKTRACE) /* * Prevent merging with compatible kmem caches. This flag should be used * cautiously. Valid use cases: * * - caches created for self-tests (e.g. kunit) * - general caches created and used by a subsystem, only when a * (subsystem-specific) debug option is enabled * - performance critical caches, should be very rare and consulted with slab * maintainers, and not used together with CONFIG_SLUB_TINY */ #define SLAB_NO_MERGE __SLAB_FLAG_BIT(_SLAB_NO_MERGE) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB __SLAB_FLAG_BIT(_SLAB_FAILSLAB) #else # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /** * define SLAB_ACCOUNT - Account allocations to memcg. * * All object allocations from this cache will be memcg accounted, regardless of * __GFP_ACCOUNT being or not being passed to individual allocations. */ #ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED #endif #ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN __SLAB_FLAG_BIT(_SLAB_KASAN) #else #define SLAB_KASAN __SLAB_FLAG_UNUSED #endif /* * Ignore user specified debugging flags. * Intended for caches created for self-tests so they have only flags * specified in the code and other flags are ignored. */ #define SLAB_NO_USER_FLAGS __SLAB_FLAG_BIT(_SLAB_NO_USER_FLAGS) #ifdef CONFIG_KFENCE #define SLAB_SKIP_KFENCE __SLAB_FLAG_BIT(_SLAB_SKIP_KFENCE) #else #define SLAB_SKIP_KFENCE __SLAB_FLAG_UNUSED #endif /* The following flags affect the page allocator grouping pages by mobility */ /** * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable. * * Use this flag for caches that have an associated shrinker. As a result, slab * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by * mobility, and are accounted in SReclaimable counter in /proc/meminfo */ #ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT) #else #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_UNUSED #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab created using create_boot_cache */ #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_BIT(_SLAB_OBJ_EXT_IN_OBJ) #else #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_UNUSED #endif /* * 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 list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes */ bool slab_is_available(void); /** * struct kmem_cache_args - Less common arguments for kmem_cache_create() * * Any uninitialized fields of the structure are interpreted as unused. The * exception is @freeptr_offset where %0 is a valid value, so * @use_freeptr_offset must be also set to %true in order to interpret the field * as used. For @useroffset %0 is also valid, but only with non-%0 * @usersize. * * When %NULL args is passed to kmem_cache_create(), it is equivalent to all * fields unused. */ struct kmem_cache_args { /** * @align: The required alignment for the objects. * * %0 means no specific alignment is requested. */ unsigned int align; /** * @useroffset: Usercopy region offset. * * %0 is a valid offset, when @usersize is non-%0 */ unsigned int useroffset; /** * @usersize: Usercopy region size. * * %0 means no usercopy region is specified. */ unsigned int usersize; /** * @freeptr_offset: Custom offset for the free pointer * in caches with &SLAB_TYPESAFE_BY_RCU or @ctor * * By default, &SLAB_TYPESAFE_BY_RCU and @ctor caches place the free * pointer outside of the object. This might cause the object to grow * in size. Cache creators that have a reason to avoid this can specify * a custom free pointer offset in their data structure where the free * pointer will be placed. * * For caches with &SLAB_TYPESAFE_BY_RCU, the caller must ensure that * the free pointer does not overlay fields required to guard against * object recycling (See &SLAB_TYPESAFE_BY_RCU for details). * * For caches with @ctor, the caller must ensure that the free pointer * does not overlay fields initialized by the constructor. * * Currently, only caches with &SLAB_TYPESAFE_BY_RCU or @ctor * may specify @freeptr_offset. * * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset * is specified, @use_freeptr_offset must be set %true. */ unsigned int freeptr_offset; /** * @use_freeptr_offset: Whether a @freeptr_offset is used. */ bool use_freeptr_offset; /** * @ctor: A constructor for the objects. * * The constructor is invoked for each object in a newly allocated slab * page. It is the cache user's responsibility to free object in the * same state as after calling the constructor, or deal appropriately * with any differences between a freshly constructed and a reallocated * object. * * %NULL means no constructor. */ void (*ctor)(void *); /** * @sheaf_capacity: Enable sheaves of given capacity for the cache. * * With a non-zero value, allocations from the cache go through caching * arrays called sheaves. Each cpu has a main sheaf that's always * present, and a spare sheaf that may be not present. When both become * empty, there's an attempt to replace an empty sheaf with a full sheaf * from the per-node barn. * * When no full sheaf is available, and gfp flags allow blocking, a * sheaf is allocated and filled from slab(s) using bulk allocation. * Otherwise the allocation falls back to the normal operation * allocating a single object from a slab. * * Analogically when freeing and both percpu sheaves are full, the barn * may replace it with an empty sheaf, unless it's over capacity. In * that case a sheaf is bulk freed to slab pages. * * The sheaves do not enforce NUMA placement of objects, so allocations * via kmem_cache_alloc_node() with a node specified other than * NUMA_NO_NODE will bypass them. * * Bulk allocation and free operations also try to use the cpu sheaves * and barn, but fallback to using slab pages directly. * * When slub_debug is enabled for the cache, the sheaf_capacity argument * is ignored. * * %0 means no sheaves will be created. */ unsigned int sheaf_capacity; }; struct kmem_cache *__kmem_cache_create_args(const char *name, unsigned int object_size, struct kmem_cache_args *args, slab_flags_t flags); static inline 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_args kmem_args = { .align = align, .ctor = ctor, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /** * kmem_cache_create_usercopy - Create a kmem cache with a region suitable * for copying to userspace. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. * @flags: SLAB flags * @useroffset: Usercopy region offset * @usersize: Usercopy region size * @ctor: A constructor for the objects, or %NULL. * * This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY() * if whitelisting a single field is sufficient, or kmem_cache_create() with * the necessary parameters passed via the args parameter (see * &struct kmem_cache_args) * * Return: a pointer to the cache on success, NULL on failure. */ static inline 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 *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, .useroffset = useroffset, .usersize = usersize, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /* If NULL is passed for @args, use this variant with default arguments. */ static inline struct kmem_cache * __kmem_cache_default_args(const char *name, unsigned int size, struct kmem_cache_args *args, slab_flags_t flags) { struct kmem_cache_args kmem_default_args = {}; /* Make sure we don't get passed garbage. */ if (WARN_ON_ONCE(args)) return ERR_PTR(-EINVAL); return __kmem_cache_create_args(name, size, &kmem_default_args, flags); } /** * kmem_cache_create - Create a kmem cache. * @__name: A string which is used in /proc/slabinfo to identify this cache. * @__object_size: The size of objects to be created in this cache. * @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL * means defaults will be used for all the arguments. * * This is currently implemented as a macro using ``_Generic()`` to call * either the new variant of the function, or a legacy one. * * The new variant has 4 parameters: * ``kmem_cache_create(name, object_size, args, flags)`` * * See __kmem_cache_create_args() which implements this. * * The legacy variant has 5 parameters: * ``kmem_cache_create(name, object_size, align, flags, ctor)`` * * The align and ctor parameters map to the respective fields of * &struct kmem_cache_args * * Context: Cannot be called within a interrupt, but can be interrupted. * * Return: a pointer to the cache on success, NULL on failure. */ #define kmem_cache_create(__name, __object_size, __args, ...) \ _Generic((__args), \ struct kmem_cache_args *: __kmem_cache_create_args, \ void *: __kmem_cache_default_args, \ default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__) void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); /* * 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_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ }, (__flags)) /* * 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_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ .useroffset = offsetof(struct __struct, __field), \ .usersize = sizeof_field(struct __struct, __field), \ }, (__flags)) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc_node_align_noprof(const void *objp, size_t new_size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define krealloc_noprof(_o, _s, _f) krealloc_node_align_noprof(_o, _s, 1, _f, NUMA_NO_NODE) #define krealloc_node_align(...) alloc_hooks(krealloc_node_align_noprof(__VA_ARGS__)) #define krealloc_node(_o, _s, _f, _n) krealloc_node_align(_o, _s, 1, _f, _n) #define krealloc(...) krealloc_node(__VA_ARGS__, NUMA_NO_NODE) void kfree(const void *objp); void kfree_nolock(const void *objp); void kfree_sensitive(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_dump_obj(void *object); #else static inline bool kmem_dump_obj(void *object) { return false; } #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_DMA_MINALIGN in arch headers allows that. */ #ifdef ARCH_HAS_DMA_MINALIGN #if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN) #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #endif #endif #ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #elif ARCH_KMALLOC_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) #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 /* * Arches can define this function if they want to decide the minimum slab * alignment at runtime. The value returned by the function must be a power * of two and >= ARCH_SLAB_MINALIGN. */ #ifndef arch_slab_minalign static inline unsigned int arch_slab_minalign(void) { return ARCH_SLAB_MINALIGN; } #endif /* * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #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 */ /* * 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_PAGE_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #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) #ifdef CONFIG_RANDOM_KMALLOC_CACHES #define RANDOM_KMALLOC_CACHES_NR 15 // # of cache copies #else #define RANDOM_KMALLOC_CACHES_NR 0 #endif /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. * * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP * is for accounted but unreclaimable and non-dma objects. All the other * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR, #ifdef CONFIG_SLUB_TINY KMALLOC_RECLAIM = KMALLOC_NORMAL, #else KMALLOC_RECLAIM, #endif #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif #ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1]; extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. */ #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller) { /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for all the relevant flags. */ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) #ifdef CONFIG_RANDOM_KMALLOC_CACHES /* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */ return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed, ilog2(RANDOM_KMALLOC_CACHES_NR + 1)); #else return KMALLOC_NORMAL; #endif /* * At least one of the flags has to be set. Their priorities in * decreasing order are: * 1) __GFP_DMA * 2) __GFP_RECLAIMABLE * 3) __GFP_ACCOUNT */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; } /* * 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 * * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; * typical usage is via kmalloc_index() and therefore evaluated at compile-time. * Callers where !size_is_constant should only be test modules, where runtime * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ static __always_inline unsigned int __kmalloc_index(size_t size, bool size_is_constant) { 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 (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #include <linux/alloc_tag.h> /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. * @flags: See kmalloc(). * * Allocate an object from this cache. * See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags. * * Return: pointer to the new object or %NULL in case of error */ void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; #define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) __assume_slab_alignment __malloc; #define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) /** * kmem_cache_charge - memcg charge an already allocated slab memory * @objp: address of the slab object to memcg charge * @gfpflags: describe the allocation context * * kmem_cache_charge allows charging a slab object to the current memcg, * primarily in cases where charging at allocation time might not be possible * because the target memcg is not known (i.e. softirq context) * * The objp should be pointer returned by the slab allocator functions like * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge * behavior can be controlled through gfpflags parameter, which affects how the * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes * that overcharging is requested instead of failure, but is not applied for the * internal metadata allocation. * * There are several cases where it will return true even if the charging was * not done: * More specifically: * * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems. * 2. Already charged slab objects. * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc() * without __GFP_ACCOUNT * 4. Allocating internal metadata has failed * * Return: true if charge was successful otherwise false. */ bool kmem_cache_charge(void *objp, gfp_t gfpflags); void kmem_cache_free(struct kmem_cache *s, void *objp); kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(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 *s, size_t size, void **p); int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); #define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) struct slab_sheaf * kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size); int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp, struct slab_sheaf **sheafp, unsigned int size); void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp, struct slab_sheaf *sheaf); void *kmem_cache_alloc_from_sheaf_noprof(struct kmem_cache *cachep, gfp_t gfp, struct slab_sheaf *sheaf) __assume_slab_alignment __malloc; #define kmem_cache_alloc_from_sheaf(...) \ alloc_hooks(kmem_cache_alloc_from_sheaf_noprof(__VA_ARGS__)) unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf); /* * These macros allow declaring a kmem_buckets * parameter alongside size, which * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call * sites don't have to pass NULL. */ #ifdef CONFIG_SLAB_BUCKETS #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b) #define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b) #define PASS_BUCKET_PARAM(_b) (_b) #else #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size) #define PASS_BUCKET_PARAMS(_size, _b) (_size) #define PASS_BUCKET_PARAM(_b) NULL #endif /* * The following functions are not to be used directly and are intended only * for internal use from kmalloc() and kmalloc_node() * with the exception of kunit tests */ void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); void *__kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory * @size: how many bytes of memory are required. * @flags: describe the allocation context * * 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. For other sizes, the alignment is guaranteed to * be at least the largest power-of-two divisor of @size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.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. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_ZERO * Zero the allocated memory before returning. Also see kzalloc(). * * %__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 __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } return __kmalloc_noprof(size, flags); } #define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); #define kmalloc_nolock(...) alloc_hooks(kmalloc_nolock_noprof(__VA_ARGS__)) /** * __alloc_objs - Allocate objects of a given type using * @KMALLOC: which size-based kmalloc wrapper to allocate with. * @GFP: GFP flags for the allocation. * @TYPE: type to allocate space for. * @COUNT: how many @TYPE objects to allocate. * * Returns: Newly allocated pointer to (first) @TYPE of @COUNT-many * allocated @TYPE objects, or NULL on failure. */ #define __alloc_objs(KMALLOC, GFP, TYPE, COUNT) \ ({ \ const size_t __obj_size = size_mul(sizeof(TYPE), COUNT); \ (TYPE *)KMALLOC(__obj_size, GFP); \ }) /** * __alloc_flex - Allocate an object that has a trailing flexible array * @KMALLOC: kmalloc wrapper function to use for allocation. * @GFP: GFP flags for the allocation. * @TYPE: type of structure to allocate space for. * @FAM: The name of the flexible array member of @TYPE structure. * @COUNT: how many @FAM elements to allocate space for. * * Returns: Newly allocated pointer to @TYPE with @COUNT-many trailing * @FAM elements, or NULL on failure or if @COUNT cannot be represented * by the member of @TYPE that counts the @FAM elements (annotated via * __counted_by()). */ #define __alloc_flex(KMALLOC, GFP, TYPE, FAM, COUNT) \ ({ \ const size_t __count = (COUNT); \ const size_t __obj_size = struct_size_t(TYPE, FAM, __count); \ TYPE *__obj_ptr = KMALLOC(__obj_size, GFP); \ if (__obj_ptr) \ __set_flex_counter(__obj_ptr->FAM, __count); \ __obj_ptr; \ }) /** * kmalloc_obj - Allocate a single instance of the given type * @VAR_OR_TYPE: Variable or type to allocate. * @GFP: GFP flags for the allocation. * * Returns: newly allocated pointer to a @VAR_OR_TYPE on success, or NULL * on failure. */ #define kmalloc_obj(VAR_OR_TYPE, ...) \ __alloc_objs(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), 1) /** * kmalloc_objs - Allocate an array of the given type * @VAR_OR_TYPE: Variable or type to allocate an array of. * @COUNT: How many elements in the array. * @GFP: GFP flags for the allocation. * * Returns: newly allocated pointer to array of @VAR_OR_TYPE on success, * or NULL on failure. */ #define kmalloc_objs(VAR_OR_TYPE, COUNT, ...) \ __alloc_objs(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), COUNT) /** * kmalloc_flex - Allocate a single instance of the given flexible structure * @VAR_OR_TYPE: Variable or type to allocate (with its flex array). * @FAM: The name of the flexible array member of the structure. * @COUNT: How many flexible array member elements are desired. * @GFP: GFP flags for the allocation. * * Returns: newly allocated pointer to @VAR_OR_TYPE on success, NULL on * failure. If @FAM has been annotated with __counted_by(), the allocation * will immediately fail if @COUNT is larger than what the type of the * struct's counter variable can represent. */ #define kmalloc_flex(VAR_OR_TYPE, FAM, COUNT, ...) \ __alloc_flex(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), FAM, COUNT) /* All kzalloc aliases for kmalloc_(obj|objs|flex). */ #define kzalloc_obj(P, ...) \ __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) #define kzalloc_objs(P, COUNT, ...) \ __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) #define kzalloc_flex(P, FAM, COUNT, ...) \ __alloc_flex(kzalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) /* All kvmalloc aliases for kmalloc_(obj|objs|flex). */ #define kvmalloc_obj(P, ...) \ __alloc_objs(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), 1) #define kvmalloc_objs(P, COUNT, ...) \ __alloc_objs(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) #define kvmalloc_flex(P, FAM, COUNT, ...) \ __alloc_flex(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) /* All kvzalloc aliases for kmalloc_(obj|objs|flex). */ #define kvzalloc_obj(P, ...) \ __alloc_objs(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) #define kvzalloc_objs(P, COUNT, ...) \ __alloc_objs(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) #define kvzalloc_flex(P, FAM, COUNT, ...) \ __alloc_flex(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) #define kmem_buckets_alloc_track_caller(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_)) static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node); } #define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * 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 __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kmalloc_noprof(bytes, flags); } #define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. * @p: pointer to the memory chunk to reallocate * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * See krealloc_noprof() for further details. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. */ static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return krealloc_noprof(p, bytes, flags); } #define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * 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). */ #define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node, unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller_noprof(size, flags, node, caller) \ __kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller) #define kmalloc_node_track_caller(...) \ alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * 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. */ #define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) #define kmalloc_track_caller_noprof(...) \ kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(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_noprof(bytes, flags, node); return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node); } #define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) #define kcalloc_node(_n, _size, _flags, _node) \ kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ #define kmem_cache_zalloc(_k, _flags) 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 __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { return kmalloc_noprof(size, flags | __GFP_ZERO); } #define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) #define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align, gfp_t flags, int node) __alloc_size(1); #define kvmalloc_node_align_noprof(_size, _align, _flags, _node) \ __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, NULL), _align, _flags, _node) #define kvmalloc_node_align(...) \ alloc_hooks(kvmalloc_node_align_noprof(__VA_ARGS__)) #define kvmalloc_node(_s, _f, _n) kvmalloc_node_align(_s, 1, _f, _n) #define kvmalloc(...) kvmalloc_node(__VA_ARGS__, NUMA_NO_NODE) #define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) #define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) #define kmem_buckets_valloc(_b, _size, _flags) \ alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), 1, _flags, NUMA_NO_NODE)) static inline __alloc_size(1, 2) void * kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc_node_align_noprof(bytes, 1, flags, node); } #define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) #define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define kvrealloc_node_align(...) \ alloc_hooks(kvrealloc_node_align_noprof(__VA_ARGS__)) #define kvrealloc_node(_p, _s, _f, _n) kvrealloc_node_align(_p, _s, 1, _f, _n) #define kvrealloc(...) kvrealloc_node(__VA_ARGS__, NUMA_NO_NODE) extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); #ifndef CONFIG_KVFREE_RCU_BATCHED static inline void kvfree_rcu_barrier(void) { rcu_barrier(); } static inline void kvfree_rcu_barrier_on_cache(struct kmem_cache *s) { rcu_barrier(); } static inline void kfree_rcu_scheduler_running(void) { } #else void kvfree_rcu_barrier(void); void kvfree_rcu_barrier_on_cache(struct kmem_cache *s); void kfree_rcu_scheduler_running(void); #endif /** * kmalloc_size_roundup - Report allocation bucket size for the given size * * @size: Number of bytes to round up from. * * This returns the number of bytes that would be available in a kmalloc() * allocation of @size bytes. For example, a 126 byte request would be * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly * for the general-purpose kmalloc()-based allocations, and is not for the * pre-sized kmem_cache_alloc()-based allocations.) * * Use this to kmalloc() the full bucket size ahead of time instead of using * ksize() to query the size after an allocation. */ size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); void __init kvfree_rcu_init(void); #endif /* _LINUX_SLAB_H */ |
| 484 561 327 328 247 247 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ bool lockref_get_not_zero(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count > 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return false; lockref->count--; spin_unlock(&lockref->lock); return true; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ bool lockref_get_not_dead(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count >= 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/xarray.h> #include <net/busy_poll.h> #include <net/net_debug.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/page_pool/types.h> #include <net/page_pool/memory_provider.h> #include <net/sock.h> #include "page_pool_priv.h" #include "netdev-genl-gen.h" static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); /* Protects: page_pools, netdevice->page_pools, pool->p.napi, pool->slow.netdev, * pool->user. * Ordering: inside rtnl_lock */ DEFINE_MUTEX(page_pools_lock); /* Page pools are only reachable from user space (via netlink) if they are * linked to a netdev at creation time. Following page pool "visibility" * states are possible: * - normal * - user.list: linked to real netdev, netdev: real netdev * - orphaned - real netdev has disappeared * - user.list: linked to lo, netdev: lo * - invisible - either (a) created without netdev linking, (b) unlisted due * to error, or (c) the entire namespace which owned this pool disappeared * - user.list: unhashed, netdev: unknown */ typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info); static int netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill) { struct page_pool *pool; struct sk_buff *rsp; int err; mutex_lock(&page_pools_lock); pool = xa_load(&page_pools, id); if (!pool || hlist_unhashed(&pool->user.list) || !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) { err = -ENOENT; goto err_unlock; } rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!rsp) { err = -ENOMEM; goto err_unlock; } err = fill(rsp, pool, info); if (err) goto err_free_msg; mutex_unlock(&page_pools_lock); return genlmsg_reply(rsp, info); err_free_msg: nlmsg_free(rsp); err_unlock: mutex_unlock(&page_pools_lock); return err; } struct page_pool_dump_cb { unsigned long ifindex; u32 pp_id; }; static int netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, pp_nl_fill_cb fill) { struct page_pool_dump_cb *state = (void *)cb->ctx; const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; struct page_pool *pool; int err = 0; rtnl_lock(); mutex_lock(&page_pools_lock); for_each_netdev_dump(net, netdev, state->ifindex) { hlist_for_each_entry(pool, &netdev->page_pools, user.list) { if (state->pp_id && state->pp_id < pool->user.id) continue; state->pp_id = pool->user.id; err = fill(skb, pool, info); if (err) goto out; } state->pp_id = 0; } out: mutex_unlock(&page_pools_lock); rtnl_unlock(); return err; } static int page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { #ifdef CONFIG_PAGE_POOL_STATS struct page_pool_stats stats = {}; struct nlattr *nest; void *hdr; if (!page_pool_get_stats(pool, &stats)) return 0; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO); if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) || (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex))) goto err_cancel_nest; nla_nest_end(rsp, nest); if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST, stats.alloc_stats.fast) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, stats.alloc_stats.slow) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, stats.alloc_stats.slow_high_order) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, stats.alloc_stats.empty) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, stats.alloc_stats.refill) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, stats.alloc_stats.waive) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, stats.recycle_stats.cached) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, stats.recycle_stats.cache_full) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, stats.recycle_stats.ring) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, stats.recycle_stats.ring_full) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, stats.recycle_stats.released_refcnt)) goto err_cancel_msg; genlmsg_end(rsp, hdr); return 0; err_cancel_nest: nla_nest_cancel(rsp, nest); err_cancel_msg: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; #else GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS"); return -EOPNOTSUPP; #endif } int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)]; struct nlattr *nest; int err; u32 id; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO)) return -EINVAL; nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO]; err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest, netdev_page_pool_info_nl_policy, info->extack); if (err) return err; if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID)) return -EINVAL; if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NETDEV_A_PAGE_POOL_IFINDEX], "selecting by ifindex not supported"); return -EINVAL; } id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]); return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill); } int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill); } static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { size_t inflight, refsz; unsigned int napi_id; void *hdr; hdr = genlmsg_iput(rsp, info); if (!hdr) return -EMSGSIZE; if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id)) goto err_cancel; if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex)) goto err_cancel; napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0; if (napi_id_valid(napi_id) && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id)) goto err_cancel; inflight = page_pool_inflight(pool, false); refsz = PAGE_SIZE << pool->p.order; if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) || nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, inflight * refsz)) goto err_cancel; if (pool->user.detach_time && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, ktime_divns(pool->user.detach_time, NSEC_PER_SEC))) goto err_cancel; if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL)) goto err_cancel; genlmsg_end(rsp, hdr); return 0; err_cancel: genlmsg_cancel(rsp, hdr); return -EMSGSIZE; } static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd) { struct genl_info info; struct sk_buff *ntf; struct net *net; lockdep_assert_held(&page_pools_lock); /* 'invisible' page pools don't matter */ if (hlist_unhashed(&pool->user.list)) return; net = dev_net(pool->slow.netdev); if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL)) return; genl_info_init_ntf(&info, &netdev_nl_family, cmd); ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ntf) return; if (page_pool_nl_fill(ntf, pool, &info)) { nlmsg_free(ntf); return; } genlmsg_multicast_netns(&netdev_nl_family, net, ntf, 0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL); } int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { u32 id; if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID)) return -EINVAL; id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]); return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill); } int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill); } int page_pool_list(struct page_pool *pool) { static u32 id_alloc_next; int err; mutex_lock(&page_pools_lock); err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b, &id_alloc_next, GFP_KERNEL); if (err < 0) goto err_unlock; INIT_HLIST_NODE(&pool->user.list); if (pool->slow.netdev) { hlist_add_head(&pool->user.list, &pool->slow.netdev->page_pools); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); } mutex_unlock(&page_pools_lock); return 0; err_unlock: mutex_unlock(&page_pools_lock); return err; } void page_pool_detached(struct page_pool *pool) { mutex_lock(&page_pools_lock); pool->user.detach_time = ktime_get_boottime(); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); mutex_unlock(&page_pools_lock); } void page_pool_unlist(struct page_pool *pool) { mutex_lock(&page_pools_lock); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF); xa_erase(&page_pools, pool->user.id); if (!hlist_unhashed(&pool->user.list)) hlist_del(&pool->user.list); mutex_unlock(&page_pools_lock); } int page_pool_check_memory_provider(struct net_device *dev, struct netdev_rx_queue *rxq) { void *binding = rxq->mp_params.mp_priv; struct page_pool *pool; struct hlist_node *n; if (!binding) return 0; mutex_lock(&page_pools_lock); hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) { if (pool->mp_priv != binding) continue; if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) { mutex_unlock(&page_pools_lock); return 0; } } mutex_unlock(&page_pools_lock); return -ENODATA; } static void page_pool_unreg_netdev_wipe(struct net_device *netdev) { struct page_pool *pool; struct hlist_node *n; mutex_lock(&page_pools_lock); hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) { hlist_del_init(&pool->user.list); pool->slow.netdev = NET_PTR_POISON; } mutex_unlock(&page_pools_lock); } static void page_pool_unreg_netdev(struct net_device *netdev) { struct page_pool *pool, *last; struct net_device *lo; lo = dev_net(netdev)->loopback_dev; mutex_lock(&page_pools_lock); last = NULL; hlist_for_each_entry(pool, &netdev->page_pools, user.list) { pool->slow.netdev = lo; netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); last = pool; } if (last) hlist_splice_init(&netdev->page_pools, &last->user.list, &lo->page_pools); mutex_unlock(&page_pools_lock); } static int page_pool_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; if (hlist_empty(&netdev->page_pools)) return NOTIFY_OK; if (netdev->ifindex != LOOPBACK_IFINDEX) page_pool_unreg_netdev(netdev); else page_pool_unreg_netdev_wipe(netdev); return NOTIFY_OK; } static struct notifier_block page_pool_netdevice_nb = { .notifier_call = page_pool_netdevice_event, }; static int __init page_pool_user_init(void) { return register_netdevice_notifier(&page_pool_netdevice_nb); } subsys_initcall(page_pool_user_init); |
| 2 5 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILEATTR_H #define _LINUX_FILEATTR_H /* Flags shared betwen flags/xflags */ #define FS_COMMON_FL \ (FS_SYNC_FL | FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NODUMP_FL | FS_NOATIME_FL | FS_DAX_FL | \ FS_PROJINHERIT_FL | FS_VERITY_FL) #define FS_XFLAG_COMMON \ (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND | \ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ FS_XFLAG_PROJINHERIT | FS_XFLAG_VERITY) /* Read-only inode flags */ #define FS_XFLAG_RDONLY_MASK \ (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR | FS_XFLAG_VERITY) /* Flags to indicate valid value of fsx_ fields */ #define FS_XFLAG_VALUES_MASK \ (FS_XFLAG_EXTSIZE | FS_XFLAG_COWEXTSIZE) /* Flags for directories */ #define FS_XFLAG_DIRONLY_MASK \ (FS_XFLAG_RTINHERIT | FS_XFLAG_NOSYMLINKS | FS_XFLAG_EXTSZINHERIT) /* Misc settable flags */ #define FS_XFLAG_MISC_MASK \ (FS_XFLAG_REALTIME | FS_XFLAG_NODEFRAG | FS_XFLAG_FILESTREAM) #define FS_XFLAGS_MASK \ (FS_XFLAG_COMMON | FS_XFLAG_RDONLY_MASK | FS_XFLAG_VALUES_MASK | \ FS_XFLAG_DIRONLY_MASK | FS_XFLAG_MISC_MASK) /* * Merged interface for miscellaneous file attributes. 'flags' originates from * ext* and 'fsx_flags' from xfs. There's some overlap between the two, which * is handled by the VFS helpers, so filesystems are free to implement just one * or both of these sub-interfaces. */ struct file_kattr { u32 flags; /* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */ /* struct fsxattr: */ u32 fsx_xflags; /* xflags field value (get/set) */ u32 fsx_extsize; /* extsize field value (get/set)*/ u32 fsx_nextents; /* nextents field value (get) */ u32 fsx_projid; /* project identifier (get/set) */ u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ /* selectors: */ bool flags_valid:1; bool fsx_valid:1; }; int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa); void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags); void fileattr_fill_flags(struct file_kattr *fa, u32 flags); /** * fileattr_has_fsx - check for extended flags/attributes * @fa: fileattr pointer * * Return: true if any attributes are present that are not represented in * ->flags. */ static inline bool fileattr_has_fsx(const struct file_kattr *fa) { return fa->fsx_valid && ((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 || fa->fsx_projid != 0 || fa->fsx_cowextsize != 0); } int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa); int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa); int ioctl_getflags(struct file *file, unsigned int __user *argp); int ioctl_setflags(struct file *file, unsigned int __user *argp); int ioctl_fsgetxattr(struct file *file, void __user *argp); int ioctl_fssetxattr(struct file *file, void __user *argp); #endif /* _LINUX_FILEATTR_H */ |
| 153 150 153 152 670 671 671 670 670 669 483 60 439 481 3 478 6 478 3 482 482 482 120 119 120 117 2 71 48 116 6 118 120 120 70 105 36 70 1577 1587 69 52 52 36 36 | 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 | // 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/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/filelock.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/swap.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ static struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __ro_after_init; static struct kmem_cache *bfilp_cachep __ro_after_init; static struct percpu_counter nr_files __cacheline_aligned_in_smp; /* Container for backing file with optional user path */ struct backing_file { struct file file; union { struct path user_path; freeptr_t bf_freeptr; }; }; #define backing_file(f) container_of(f, struct backing_file, file) const struct path *backing_file_user_path(const struct file *f) { return &backing_file(f)->user_path; } EXPORT_SYMBOL_GPL(backing_file_user_path); void backing_file_set_user_path(struct file *f, const struct path *path) { backing_file(f)->user_path = *path; } EXPORT_SYMBOL_GPL(backing_file_set_user_path); static inline void file_free(struct file *f) { security_file_free(f); if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); put_cred(f->f_cred); if (unlikely(f->f_mode & FMODE_BACKING)) { path_put(backing_file_user_path(f)); kmem_cache_free(bfilp_cachep, backing_file(f)); } else { kmem_cache_free(filp_cachep, f); } } /* * 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); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Handle nr_files sysctl */ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = percpu_counter_sum_positive(&nr_files); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = SYSCTL_LONG_ZERO, .extra2 = SYSCTL_LONG_MAX, }, { .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, }; static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); if (IS_ENABLED(CONFIG_BINFMT_MISC)) { struct ctl_table_header *hdr; hdr = register_sysctl_mount_point("fs/binfmt_misc"); kmemleak_not_leak(hdr); } return 0; } fs_initcall(init_fs_stat_sysctls); #endif static int init_file(struct file *f, int flags, const struct cred *cred) { int error; f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { put_cred(f->f_cred); return error; } spin_lock_init(&f->f_lock); /* * Note that f_pos_lock is only used for files raising * FMODE_ATOMIC_POS and directories. Other files such as pipes * don't need it and since f_pos_lock is in a union may reuse * the space for other purposes. They are expected to initialize * the respective member when opening the file. */ mutex_init(&f->f_pos_lock); memset(&f->__f_path, 0, sizeof(f->f_path)); memset(&f->f_ra, 0, sizeof(f->f_ra)); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); /* * Disable permission and pre-content events for all files by default. * They may be enabled later by fsnotify_open_perm_and_set_mode(). */ file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); f->f_op = NULL; f->f_mapping = NULL; f->private_data = NULL; f->f_inode = NULL; f->f_owner = NULL; #ifdef CONFIG_EPOLL f->f_ep = NULL; #endif f->f_iocb_flags = 0; f->f_pos = 0; f->f_wb_err = 0; f->f_sb_err = 0; /* * We're SLAB_TYPESAFE_BY_RCU so initialize f_ref last. While * fget-rcu pattern users need to be able to handle spurious * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); return 0; } /* 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; int error; /* * Privileged users can go above max_files */ if (unlikely(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 = kmem_cache_alloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } 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. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } f->f_mode |= FMODE_NOACCOUNT; return f; } /* * Variant of alloc_empty_file() that allocates a backing_file container * and doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_backing_file(int flags, const struct cred *cred) { struct backing_file *ff; int error; ff = kmem_cache_alloc(bfilp_cachep, GFP_KERNEL); if (unlikely(!ff)) return ERR_PTR(-ENOMEM); error = init_file(&ff->file, flags, cred); if (unlikely(error)) { kmem_cache_free(bfilp_cachep, ff); return ERR_PTR(error); } ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT; return &ff->file; } EXPORT_SYMBOL_GPL(alloc_empty_backing_file); /** * file_init_path - initialize a 'struct file' based on path * * @file: the file to set up * @path: the (dentry, vfsmount) pair for the new file * @fop: the 'struct file_operations' for the new file */ static void file_init_path(struct file *file, const struct path *path, const struct file_operations *fop) { 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 (fop->llseek) file->f_mode |= FMODE_LSEEK; 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_iocb_flags = iocb_flags(file); 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); } /** * 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)) file_init_path(file, path, fop); return file; } static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name)); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); d_instantiate(path->dentry, inode); return 0; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } /* * Disable all fsnotify events for pseudo files by default. * They may be enabled by caller with file_set_fsnotify_mode(). */ file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_pseudo_noaccount(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_empty_file_noaccount(flags, current_cred()); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } file_init_path(file, &path, fops); /* * Disable all fsnotify events for pseudo files by default. * They may be enabled by caller with file_set_fsnotify_mode(). */ file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f; 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); security_file_release(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); file_f_owner_release(file); put_file_access(file); 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_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_task_work)); } static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); /* * 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); flush_delayed_work(&delayed_fput_work); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static void __fput_deferred(struct file *file) { struct task_struct *task = current; if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) { file_free(file); return; } if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_task_work, ____fput); if (!task_work_add(task, &file->f_task_work, 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_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } void fput(struct file *file) { if (unlikely(file_ref_put(&file->f_ref))) __fput_deferred(file); } EXPORT_SYMBOL(fput); /* * 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 (file_ref_put(&file->f_ref)) __fput(file); } EXPORT_SYMBOL(__fput_sync); /* * Equivalent to __fput_sync(), but optimized for being called with the last * reference. * * See file_ref_put_close() for details. */ void fput_close_sync(struct file *file) { if (likely(file_ref_put_close(&file->f_ref))) __fput(file); } /* * Equivalent to fput(), but optimized for being called with the last * reference. * * See file_ref_put_close() for details. */ void fput_close(struct file *file) { if (file_ref_put_close(&file->f_ref)) __fput_deferred(file); } void __init files_init(void) { struct kmem_cache_args args = { .use_freeptr_offset = true, .freeptr_offset = offsetof(struct file, f_freeptr), }; filp_cachep = kmem_cache_create("filp", sizeof(struct file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); args.freeptr_offset = offsetof(struct backing_file, bf_freeptr); bfilp_cachep = kmem_cache_create("bfilp", sizeof(struct backing_file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 3 1 2 2 1 5 1 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* linux/net/ipv4/arp.c * * Copyright (C) 1994 by Florian La Roche * * This module implements the Address Resolution Protocol ARP (RFC 826), * which is used to convert IP addresses (or in the future maybe other * high-level addresses) into a low-level hardware address (like an Ethernet * address). * * Fixes: * Alan Cox : Removed the Ethernet assumptions in * Florian's code * Alan Cox : Fixed some small errors in the ARP * logic * Alan Cox : Allow >4K in /proc * Alan Cox : Make ARP add its own protocol entry * Ross Martin : Rewrote arp_rcv() and arp_get_info() * Stephen Henson : Add AX25 support to arp_get_info() * Alan Cox : Drop data when a device is downed. * Alan Cox : Use init_timer(). * Alan Cox : Double lock fixes. * Martin Seine : Move the arphdr structure * to if_arp.h for compatibility. * with BSD based programs. * Andrew Tridgell : Added ARP netmask code and * re-arranged proxy handling. * Alan Cox : Changed to use notifiers. * Niibe Yutaka : Reply for this device or proxies only. * Alan Cox : Don't proxy across hardware types! * Jonathan Naylor : Added support for NET/ROM. * Mike Shaver : RFC1122 checks. * Jonathan Naylor : Only lookup the hardware address for * the correct hardware type. * Germano Caronni : Assorted subtle races. * Craig Schlenter : Don't modify permanent entry * during arp_rcv. * Russ Nelson : Tidied up a few bits. * Alexey Kuznetsov: Major changes to caching and behaviour, * eg intelligent arp probing and * generation * of host down events. * Alan Cox : Missing unlock in device events. * Eckes : ARP ioctl control errors. * Alexey Kuznetsov: Arp free fix. * Manuel Rodriguez: Gratuitous ARP. * Jonathan Layes : Added arpd support through kerneld * message queue (960314) * Mike Shaver : /proc/sys/net/ipv4/arp_* support * Mike McLagan : Routing by source * Stuart Cheshire : Metricom and grat arp fixes * *** FOR 2.1 clean this up *** * Lawrence V. Stefani: (08/12/96) Added FDDI support. * Alan Cox : Took the AP1000 nasty FDDI hack and * folded into the mainstream FDDI code. * Ack spit, Linus how did you allow that * one in... * Jes Sorensen : Make FDDI work again in 2.1.x and * clean up the APFDDI & gen. FDDI bits. * Alexey Kuznetsov: new arp state machine; * now it is in net/core/neighbour.c. * Krzysztof Halasa: Added Frame Relay ARP support. * Arnaldo C. Melo : convert /proc/net/arp to seq_file * Shmulik Hen: Split arp_send to arp_create and * arp_xmit so intermediate drivers like * bonding can change the skb before * sending (e.g. insert 8021q tag). * Harald Welte : convert to make use of jenkins hash * Jesper D. Brouer: Proxy ARP PVLAN RFC 3069 support. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/capability.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/hex.h> #include <linux/in.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/fddidevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/net_namespace.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ax25.h> #include <net/netrom.h> #include <net/dst_metadata.h> #include <net/ip_tunnels.h> #include <linux/uaccess.h> #include <linux/netfilter_arp.h> /* * Interface to generic neighbour cache. */ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool arp_key_eq(const struct neighbour *n, const void *pkey); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); static void parp_redo(struct sk_buff *skb); static int arp_is_multicast(const void *pkey); static const struct neigh_ops arp_generic_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops arp_hh_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops arp_direct_ops = { .family = AF_INET, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table arp_tbl = { .family = AF_INET, .key_len = 4, .protocol = cpu_to_be16(ETH_P_IP), .hash = arp_hash, .key_eq = arp_key_eq, .constructor = arp_constructor, .proxy_redo = parp_redo, .is_multicast = arp_is_multicast, .id = "arp_cache", .parms = { .tbl = &arp_tbl, .reachable_time = 30 * HZ, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, [NEIGH_VAR_LOCKTIME] = 1 * HZ, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL(arp_tbl); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802: ip_eth_mc_map(addr, haddr); return 0; case ARPHRD_INFINIBAND: ip_ib_mc_map(addr, dev->broadcast, haddr); return 0; case ARPHRD_IPGRE: ip_ipgre_mc_map(addr, dev->broadcast, haddr); return 0; default: if (dir) { memcpy(haddr, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return arp_hashfn(pkey, dev, hash_rnd); } static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) { return neigh_key_eq32(neigh, pkey); } static int arp_constructor(struct neighbour *neigh) { __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; u32 inaddr_any = INADDR_ANY; if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return -EINVAL; } neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); rcu_read_unlock(); if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &arp_direct_ops; neigh->output = neigh_direct_output; } else { /* Good devices (checked by reading texts, but only Ethernet is tested) ARPHRD_ETHER: (ethernet, apfddi) ARPHRD_FDDI: (fddi) ARPHRD_IEEE802: (tr) ARPHRD_METRICOM: (strip) ARPHRD_ARCNET: etc. etc. etc. ARPHRD_IPDDP will also work, if author repairs it. I did not it, because this driver does not work even in old paradigm. */ if (neigh->type == RTN_MULTICAST) { neigh->nud_state = NUD_NOARP; arp_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); } else if (neigh->type == RTN_BROADCAST || (dev->flags & IFF_POINTOPOINT)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &arp_hh_ops; else neigh->ops = &arp_generic_ops; if (neigh->nud_state & NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } return 0; } static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) { dst_link_failure(skb); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_FAILED); } /* Create and send an arp packet. */ static void arp_send_dst(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw, struct dst_entry *dst) { struct sk_buff *skb; /* arp on this interface. */ if (dev->flags & IFF_NOARP) return; skb = arp_create(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); if (!skb) return; skb_dst_set(skb, dst_clone(dst)); arp_xmit(skb); } void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw, NULL); } EXPORT_SYMBOL(arp_send); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; u8 dst_ha[MAX_ADDR_LEN], *dst_hw = NULL; struct net_device *dev = neigh->dev; __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; struct dst_entry *dst = NULL; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return; } switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ if (skb && inet_addr_type_dev_table(dev_net(dev), dev, ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; case 1: /* Restrict announcements of saddr in same subnet */ if (!skb) break; saddr = ip_hdr(skb)->saddr; if (inet_addr_type_dev_table(dev_net(dev), dev, saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; } saddr = 0; break; case 2: /* Avoid secondary IPs, get a primary/preferred one */ break; } rcu_read_unlock(); if (!saddr) saddr = inet_select_addr(dev, target, RT_SCOPE_LINK); probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); neigh_ha_snapshot(dst_ha, neigh, dev); dst_hw = dst_ha; } else { probes -= NEIGH_VAR(neigh->parms, APP_PROBES); if (probes < 0) { neigh_app_ns(neigh); return; } } if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) dst = skb_dst(skb); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_hw, dev->dev_addr, NULL, dst); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) { struct net *net = dev_net(in_dev->dev); int scope; switch (IN_DEV_ARP_IGNORE(in_dev)) { case 0: /* Reply, the tip is already validated */ return 0; case 1: /* Reply only if tip is configured on the incoming interface */ sip = 0; scope = RT_SCOPE_HOST; break; case 2: /* * Reply only if tip is configured on the incoming interface * and is in same subnet as sip */ scope = RT_SCOPE_HOST; break; case 3: /* Do not reply for scope host addresses */ sip = 0; scope = RT_SCOPE_LINK; in_dev = NULL; break; case 4: /* Reserved */ case 5: case 6: case 7: return 0; case 8: /* Do not reply */ return 1; default: return 0; } return !inet_confirm_addr(net, in_dev, sip, tip, scope); } static int arp_accept(struct in_device *in_dev, __be32 sip) { struct net *net = dev_net(in_dev->dev); int scope = RT_SCOPE_LINK; switch (IN_DEV_ARP_ACCEPT(in_dev)) { case 0: /* Don't create new entries from garp */ return 0; case 1: /* Create new entries from garp */ return 1; case 2: /* Create a neighbor in the arp table only if sip * is in the same subnet as an address configured * on the interface that received the garp message */ return !!inet_confirm_addr(net, in_dev, sip, 0, scope); default: return 0; } } static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) { struct rtable *rt; int flag = 0; /*unsigned long now; */ struct net *net = dev_net(dev); rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev), RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return 1; if (rt->dst.dev != dev) { __NET_INC_STATS(net, LINUX_MIB_ARPFILTER); flag = 1; } ip_rt_put(rt); return flag; } /* * Check if we can use proxy ARP for this path */ static inline int arp_fwd_proxy(struct in_device *in_dev, struct net_device *dev, struct rtable *rt) { struct in_device *out_dev; int imi, omi = -1; if (rt->dst.dev == dev) return 0; if (!IN_DEV_PROXY_ARP(in_dev)) return 0; imi = IN_DEV_MEDIUM_ID(in_dev); if (imi == 0) return 1; if (imi == -1) return 0; /* place to check for proxy_arp for routes */ out_dev = __in_dev_get_rcu(rt->dst.dev); if (out_dev) omi = IN_DEV_MEDIUM_ID(out_dev); return omi != imi && omi != -1; } /* * Check for RFC3069 proxy arp private VLAN (allow to send back to same dev) * * RFC3069 supports proxy arp replies back to the same interface. This * is done to support (ethernet) switch features, like RFC 3069, where * the individual ports are not allowed to communicate with each * other, BUT they are allowed to talk to the upstream router. As * described in RFC 3069, it is possible to allow these hosts to * communicate through the upstream router, by proxy_arp'ing. * * RFC 3069: "VLAN Aggregation for Efficient IP Address Allocation" * * This technology is known by different names: * In RFC 3069 it is called VLAN Aggregation. * Cisco and Allied Telesyn call it Private VLAN. * Hewlett-Packard call it Source-Port filtering or port-isolation. * Ericsson call it MAC-Forced Forwarding (RFC Draft). * */ static inline int arp_fwd_pvlan(struct in_device *in_dev, struct net_device *dev, struct rtable *rt, __be32 sip, __be32 tip) { /* Private VLAN is only concerned about the same ethernet segment */ if (rt->dst.dev != dev) return 0; /* Don't reply on self probes (often done by windowz boxes)*/ if (sip == tip) return 0; if (IN_DEV_PROXY_ARP_PVLAN(in_dev)) return 1; else return 0; } /* * Interface to link layer: send routine and receive handler. */ /* * Create an arp packet. If dest_hw is not set, we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw) { struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; /* * Allocate a buffer */ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (!skb) return NULL; skb_reserve(skb, hlen); skb_reset_network_header(skb); skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) src_hw = dev->dev_addr; if (!dest_hw) dest_hw = dev->broadcast; /* Fill the device header for the ARP frame. * Note: skb->head can be changed. */ if (dev_hard_header(skb, dev, ptype, dest_hw, src_hw, skb->len) < 0) goto out; arp = arp_hdr(skb); /* * Fill out the arp protocol part. * * The arp hardware type should match the device type, except for FDDI, * which (according to RFC 1390) should always equal 1 (Ethernet). */ /* * Exceptions everywhere. AX.25 uses the AX.25 PID value not the * DIX code for the protocol. Make these device structure fields. */ switch (dev->type) { default: arp->ar_hrd = htons(dev->type); arp->ar_pro = htons(ETH_P_IP); break; #if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: arp->ar_hrd = htons(ARPHRD_AX25); arp->ar_pro = htons(AX25_P_IP); break; #if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: arp->ar_hrd = htons(ARPHRD_NETROM); arp->ar_pro = htons(AX25_P_IP); break; #endif #endif #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif } arp->ar_hln = dev->addr_len; arp->ar_pln = 4; arp->ar_op = htons(type); arp_ptr = (unsigned char *)(arp + 1); memcpy(arp_ptr, src_hw, dev->addr_len); arp_ptr += dev->addr_len; memcpy(arp_ptr, &src_ip, 4); arp_ptr += 4; switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: if (target_hw) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); arp_ptr += dev->addr_len; } memcpy(arp_ptr, &dest_ip, 4); return skb; out: kfree_skb(skb); return NULL; } EXPORT_SYMBOL(arp_create); static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } /* * Send an arp packet. */ void arp_xmit(struct sk_buff *skb) { rcu_read_lock(); /* Send it off, maybe filter it using firewalling first. */ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, dev_net_rcu(skb->dev), NULL, skb, NULL, skb->dev, arp_xmit_finish); rcu_read_unlock(); } EXPORT_SYMBOL(arp_xmit); static bool arp_is_garp(struct net *net, struct net_device *dev, int *addr_type, __be16 ar_op, __be32 sip, __be32 tip, unsigned char *sha, unsigned char *tha) { bool is_garp = tip == sip; /* Gratuitous ARP _replies_ also require target hwaddr to be * the same as source. */ if (is_garp && ar_op == htons(ARPOP_REPLY)) is_garp = /* IPv4 over IEEE 1394 doesn't provide target * hardware address field in its ARP payload. */ tha && !memcmp(tha, sha, dev->addr_len); if (is_garp) { *addr_type = inet_addr_type_dev_table(net, dev, sip); if (*addr_type != RTN_UNICAST) is_garp = false; } return is_garp; } /* * Process an arp request. */ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); struct arphdr *arp; unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha; unsigned char *tha = NULL; __be32 sip, tip; u16 dev_type = dev->type; int addr_type; struct neighbour *n; struct dst_entry *reply_dst = NULL; bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device * is ARP'able. */ if (!in_dev) goto out_free_skb; arp = arp_hdr(skb); switch (dev_type) { default: if (arp->ar_pro != htons(ETH_P_IP) || htons(dev_type) != arp->ar_hrd) goto out_free_skb; break; case ARPHRD_ETHER: case ARPHRD_FDDI: case ARPHRD_IEEE802: /* * ETHERNET, and Fibre Channel (which are IEEE 802 * devices, according to RFC 2625) devices will accept ARP * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2). * This is the case also of FDDI, where the RFC 1390 says that * FDDI devices should accept ARP hardware of (1) Ethernet, * however, to be more robust, we'll accept both 1 (Ethernet) * or 6 (IEEE 802.2) */ if ((arp->ar_hrd != htons(ARPHRD_ETHER) && arp->ar_hrd != htons(ARPHRD_IEEE802)) || arp->ar_pro != htons(ETH_P_IP)) goto out_free_skb; break; case ARPHRD_AX25: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_AX25)) goto out_free_skb; break; case ARPHRD_NETROM: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_NETROM)) goto out_free_skb; break; } /* Understand only these message types */ if (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST)) goto out_free_skb; /* * Extract fields */ arp_ptr = (unsigned char *)(arp + 1); sha = arp_ptr; arp_ptr += dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4; switch (dev_type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: break; #endif default: tha = arp_ptr; arp_ptr += dev->addr_len; } memcpy(&tip, arp_ptr, 4); /* * Check for bad requests for 127.x.x.x and requests for multicast * addresses. If this is one such, delete it. */ if (ipv4_is_multicast(tip) || (!IN_DEV_ROUTE_LOCALNET(in_dev) && ipv4_is_loopback(tip))) goto out_free_skb; /* * For some 802.11 wireless deployments (and possibly other networks), * there will be an ARP proxy and gratuitous ARP frames are attacks * and thus should not be accepted. */ if (sip == tip && IN_DEV_ORCONF(in_dev, DROP_GRATUITOUS_ARP)) goto out_free_skb; /* * Special case: We must set Frame Relay source Q.922 address */ if (dev_type == ARPHRD_DLCI) sha = dev->broadcast; /* * Process entry. The idea here is we want to send a reply if it is a * request for us or if it is a request for someone else that we hold * a proxy for. We want to add an entry to our cache if it is a reply * to us or if it is a request for our address. * (The assumption for this last is that if someone is requesting our * address, they are probably intending to talk to us, so it saves time * if we cache their address. Their address is also probably not in * our cache, since ours is not in their cache.) * * Putting this another way, we only care about replies if they are to * us, in which case we add them to the cache. For requests, we care * about those for us and those for our proxies. We reply to both, * and in the case of requests for us we add the requester to the arp * cache. */ if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb)) reply_dst = (struct dst_entry *) iptunnel_metadata_reply(skb_metadata_dst(skb), GFP_ATOMIC); /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); goto out_consume_skb; } if (arp->ar_op == htons(ARPOP_REQUEST) && ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { int dont_send; dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) dont_send = arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); neigh_release(n); } } goto out_consume_skb; } else if (IN_DEV_FORWARD(in_dev)) { if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || (rt->dst.dev != dev && pneigh_lookup(&arp_tbl, net, &tip, dev)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha, reply_dst); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); goto out_free_dst; } goto out_consume_skb; } } } /* Update our ARP tables */ n = __neigh_lookup(&arp_tbl, &sip, dev, 0); addr_type = -1; if (n || arp_accept(in_dev, sip)) { is_garp = arp_is_garp(net, dev, &addr_type, arp->ar_op, sip, tip, sha, tha); } if (arp_accept(in_dev, sip)) { /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ if (!n && (is_garp || (arp->ar_op == htons(ARPOP_REPLY) && (addr_type == RTN_UNICAST || (addr_type < 0 && /* postpone calculation to as late as possible */ inet_addr_type_dev_table(net, dev, sip) == RTN_UNICAST))))) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } if (n) { int state = NUD_REACHABLE; int override; /* If several different ARP replies follows back-to-back, use the FIRST one. It is possible, if several proxy agents are active. Taking the first reply prevents arp trashing and chooses the fastest router. */ override = time_after(jiffies, n->updated + NEIGH_VAR(n->parms, LOCKTIME)) || is_garp; /* Broadcast replies and request packets do not assert neighbour reachability. */ if (arp->ar_op != htons(ARPOP_REPLY) || skb->pkt_type != PACKET_HOST) state = NUD_STALE; neigh_update(n, sha, state, override ? NEIGH_UPDATE_F_OVERRIDE : 0, 0); neigh_release(n); } out_consume_skb: consume_skb(skb); out_free_dst: dst_release(reply_dst); return NET_RX_SUCCESS; out_free_skb: kfree_skb(skb); return NET_RX_DROP; } static void parp_redo(struct sk_buff *skb) { arp_process(dev_net(skb->dev), NULL, skb); } static int arp_is_multicast(const void *pkey) { return ipv4_is_multicast(*((__be32 *)pkey)); } /* * Receive an arp request from the device layer. */ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason; const struct arphdr *arp; /* do not tweak dropwatch on an ARP we will ignore */ if (dev->flags & IFF_NOARP || skb->pkt_type == PACKET_OTHERHOST || skb->pkt_type == PACKET_LOOPBACK) goto consumeskb; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ drop_reason = pskb_may_pull_reason(skb, arp_hdr_len(dev)); if (drop_reason != SKB_NOT_DROPPED_YET) goto freeskb; arp = arp_hdr(skb); if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) { drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; goto freeskb; } memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, dev_net(dev), NULL, skb, dev, NULL, arp_process); consumeskb: consume_skb(skb); return NET_RX_SUCCESS; freeskb: kfree_skb_reason(skb, drop_reason); out_of_mem: return NET_RX_DROP; } /* * User level interface (ioctl) */ static struct net_device *arp_req_dev_by_name(struct net *net, struct arpreq *r, bool getarp) { struct net_device *dev; if (getarp) dev = dev_get_by_name_rcu(net, r->arp_dev); else dev = __dev_get_by_name(net, r->arp_dev); if (!dev) return ERR_PTR(-ENODEV); /* Mmmm... It is wrong... ARPHRD_NETROM == 0 */ if (!r->arp_ha.sa_family) r->arp_ha.sa_family = dev->type; if ((r->arp_flags & ATF_COM) && r->arp_ha.sa_family != dev->type) return ERR_PTR(-EINVAL); return dev; } static struct net_device *arp_req_dev(struct net *net, struct arpreq *r) { struct net_device *dev; struct rtable *rt; __be32 ip; if (r->arp_dev[0]) return arp_req_dev_by_name(net, r, false); if (r->arp_flags & ATF_PUBL) return NULL; ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; rt = ip_route_output(net, ip, 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) return ERR_CAST(rt); dev = rt->dst.dev; ip_rt_put(rt); if (!dev) return ERR_PTR(-EINVAL); return dev; } /* * Set (create) an ARP cache entry. */ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) { if (!dev) { IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } if (__in_dev_get_rtnl_net(dev)) { IN_DEV_CONF_SET(__in_dev_get_rtnl_net(dev), PROXY_ARP, on); return 0; } return -ENXIO; } static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; } if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return pneigh_create(&arp_tbl, net, &ip, dev, 0, 0, false); } return arp_req_set_proxy(net, dev, 1); } static int arp_req_set(struct net *net, struct arpreq *r) { struct neighbour *neigh; struct net_device *dev; __be32 ip; int err; dev = arp_req_dev(net, r); if (IS_ERR(dev)) return PTR_ERR(dev); if (r->arp_flags & ATF_PUBL) return arp_req_set_public(net, r, dev); switch (dev->type) { #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: /* * According to RFC 1390, FDDI devices should accept ARP * hardware types of 1 (Ethernet). However, to be more * robust, we'll accept hardware types of either 1 (Ethernet) * or 6 (IEEE 802.2). */ if (r->arp_ha.sa_family != ARPHRD_FDDI && r->arp_ha.sa_family != ARPHRD_ETHER && r->arp_ha.sa_family != ARPHRD_IEEE802) return -EINVAL; break; #endif default: if (r->arp_ha.sa_family != dev->type) return -EINVAL; break; } ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { unsigned int state = NUD_STALE; if (r->arp_flags & ATF_PERM) { r->arp_flags |= ATF_COM; state = NUD_PERMANENT; } err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, 0); neigh_release(neigh); } return err; } static unsigned int arp_state_to_flags(struct neighbour *neigh) { if (neigh->nud_state&NUD_PERMANENT) return ATF_PERM | ATF_COM; else if (neigh->nud_state&NUD_VALID) return ATF_COM; else return 0; } /* * Get an ARP cache entry. */ static int arp_req_get(struct net *net, struct arpreq *r) { __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; struct net_device *dev; if (!r->arp_dev[0]) return -ENODEV; dev = arp_req_dev_by_name(net, r, true); if (IS_ERR(dev)) return PTR_ERR(dev); neigh = neigh_lookup(&arp_tbl, &ip, dev); if (!neigh) return -ENXIO; if (READ_ONCE(neigh->nud_state) & NUD_NOARP) { neigh_release(neigh); return -ENXIO; } read_lock_bh(&neigh->lock); memcpy(r->arp_ha.sa_data, neigh->ha, min(dev->addr_len, sizeof(r->arp_ha.sa_data))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); neigh_release(neigh); r->arp_ha.sa_family = dev->type; netdev_copy_name(dev, r->arp_dev); return 0; } int arp_invalidate(struct net_device *dev, __be32 ip, bool force) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; struct neigh_table *tbl = &arp_tbl; if (neigh) { if ((READ_ONCE(neigh->nud_state) & NUD_VALID) && !force) { neigh_release(neigh); return 0; } if (READ_ONCE(neigh->nud_state) & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); spin_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh); spin_unlock_bh(&tbl->lock); } return err; } static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return pneigh_delete(&arp_tbl, net, &ip, dev); } return arp_req_set_proxy(net, dev, 0); } static int arp_req_delete(struct net *net, struct arpreq *r) { struct net_device *dev; __be32 ip; dev = arp_req_dev(net, r); if (IS_ERR(dev)) return PTR_ERR(dev); if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; return arp_invalidate(dev, ip, true); } /* * Handle an ARP layer I/O control request. */ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct arpreq r; __be32 *netmask; int err; switch (cmd) { case SIOCDARP: case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; fallthrough; case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) return -EFAULT; break; default: return -EINVAL; } if (r.arp_pa.sa_family != AF_INET) return -EPFNOSUPPORT; if (!(r.arp_flags & ATF_PUBL) && (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB))) return -EINVAL; netmask = &((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr; if (!(r.arp_flags & ATF_NETMASK)) *netmask = htonl(0xFFFFFFFFUL); else if (*netmask && *netmask != htonl(0xFFFFFFFFUL)) return -EINVAL; switch (cmd) { case SIOCDARP: rtnl_net_lock(net); err = arp_req_delete(net, &r); rtnl_net_unlock(net); break; case SIOCSARP: rtnl_net_lock(net); err = arp_req_set(net, &r); rtnl_net_unlock(net); break; case SIOCGARP: rcu_read_lock(); err = arp_req_get(net, &r); rcu_read_unlock(); if (!err && copy_to_user(arg, &r, sizeof(r))) err = -EFAULT; break; } return err; } static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct in_device *in_dev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); rt_cache_flush(dev_net(dev)); break; case NETDEV_CHANGE: change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&arp_tbl, dev); in_dev = __in_dev_get_rtnl(dev); if (!in_dev) evict_nocarrier = true; else evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&arp_tbl, dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block arp_netdev_notifier = { .notifier_call = arp_netdev_event, }; /* Note, that it is not on notifier chain. It is necessary, that this routine was called after route cache will be flushed. */ void arp_ifdown(struct net_device *dev) { neigh_ifdown(&arp_tbl, dev); } /* * Called once on startup. */ static struct packet_type arp_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_ARP), .func = arp_rcv, }; #ifdef CONFIG_PROC_FS #if IS_ENABLED(CONFIG_AX25) /* * ax25 -> ASCII conversion */ static void ax2asc2(ax25_address *a, char *buf) { char c, *s; int n; for (n = 0, s = buf; n < 6; n++) { c = (a->ax25_call[n] >> 1) & 0x7F; if (c != ' ') *s++ = c; } *s++ = '-'; n = (a->ax25_call[6] >> 1) & 0x0F; if (n > 9) { *s++ = '1'; n -= 10; } *s++ = n + '0'; *s++ = '\0'; if (*buf == '\0' || *buf == '-') { buf[0] = '*'; buf[1] = '\0'; } } #endif /* CONFIG_AX25 */ #define HBUFFERLEN 30 static void arp_format_neigh_entry(struct seq_file *seq, struct neighbour *n) { char hbuffer[HBUFFERLEN]; int k, j; char tbuf[16]; struct net_device *dev = n->dev; int hatype = dev->type; read_lock(&n->lock); /* Convert hardware address to XX:XX:XX:XX ... form. */ #if IS_ENABLED(CONFIG_AX25) if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM) ax2asc2((ax25_address *)n->ha, hbuffer); else { #endif for (k = 0, j = 0; k < HBUFFERLEN - 3 && j < dev->addr_len; j++) { hbuffer[k++] = hex_asc_hi(n->ha[j]); hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } if (k != 0) --k; hbuffer[k] = 0; #if IS_ENABLED(CONFIG_AX25) } #endif sprintf(tbuf, "%pI4", n->primary_key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s * %s\n", tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name); read_unlock(&n->lock); } static void arp_format_pneigh_entry(struct seq_file *seq, struct pneigh_entry *n) { struct net_device *dev = n->dev; int hatype = dev ? dev->type : 0; char tbuf[16]; sprintf(tbuf, "%pI4", n->key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", tbuf, hatype, ATF_PUBL | ATF_PERM, "00:00:00:00:00:00", dev ? dev->name : "*"); } static int arp_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "IP address HW type Flags " "HW address Mask Device\n"); } else { struct neigh_seq_state *state = seq->private; if (state->flags & NEIGH_SEQ_IS_PNEIGH) arp_format_pneigh_entry(seq, v); else arp_format_neigh_entry(seq, v); } return 0; } static void *arp_seq_start(struct seq_file *seq, loff_t *pos) { /* Don't want to confuse "arp -a" w/ magic entries, * so we tell the generic iterator to skip NUD_NOARP. */ return neigh_seq_start(seq, pos, &arp_tbl, NEIGH_SEQ_SKIP_NOARP); } static const struct seq_operations arp_seq_ops = { .start = arp_seq_start, .next = neigh_seq_next, .stop = neigh_seq_stop, .show = arp_seq_show, }; #endif /* CONFIG_PROC_FS */ static int __net_init arp_net_init(struct net *net) { if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops, sizeof(struct neigh_seq_state))) return -ENOMEM; return 0; } static void __net_exit arp_net_exit(struct net *net) { remove_proc_entry("arp", net->proc_net); } static struct pernet_operations arp_net_ops = { .init = arp_net_init, .exit = arp_net_exit, }; void __init arp_init(void) { neigh_table_init(NEIGH_ARP_TABLE, &arp_tbl); dev_add_pack(&arp_packet_type); register_pernet_subsys(&arp_net_ops); #ifdef CONFIG_SYSCTL neigh_sysctl_register(NULL, &arp_tbl.parms, NULL); #endif register_netdevice_notifier(&arp_netdev_notifier); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H #include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/pid.h> #include <linux/posix-timers_types.h> #include <linux/rcuref.h> #include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; struct sigqueue; struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { return ((~pid) << 3) | clock; } static inline clockid_t make_thread_cpuclock(const unsigned int tid, const clockid_t clock) { return make_process_cpuclock(tid, clock | CPUCLOCK_PERTHREAD_MASK); } static inline clockid_t fd_to_clockid(const int fd) { return make_process_cpuclock((unsigned int) fd, CLOCKFD); } static inline int clockid_to_fd(const clockid_t clk) { return ~(clk >> 3); } static inline bool clockid_aux_valid(clockid_t id) { return IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS) && id >= CLOCK_AUX && id <= CLOCK_AUX_LAST; } #ifdef CONFIG_POSIX_TIMERS #include <linux/signal_types.h> /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing * @nanosleep: Timer is used for nanosleep and is not a regular posix-timer * @handling: Pointer to the task which handles expiry */ struct cpu_timer { struct timerqueue_node node; struct timerqueue_head *head; struct pid *pid; struct list_head elist; bool firing; bool nanosleep; struct task_struct __rcu *handling; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, struct cpu_timer *ctmr) { ctmr->head = head; return timerqueue_add(head, &ctmr->node); } static inline bool cpu_timer_queued(struct cpu_timer *ctmr) { return !!ctmr->head; } static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr) { if (cpu_timer_queued(ctmr)) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; return true; } return false; } static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr) { return ctmr->node.expires; } static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) { ctmr->node.expires = exp; } static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); pct->bases[0].nextevt = U64_MAX; pct->bases[1].nextevt = U64_MAX; pct->bases[2].nextevt = U64_MAX; } void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit); static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, u64 runtime) { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_init_sigqueue(struct sigqueue *q); void posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); long posixtimer_create_prctl(unsigned long ctrl); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ } #define INIT_CPU_TIMERBASES(b) { \ INIT_CPU_TIMERBASE(b[0]), \ INIT_CPU_TIMERBASE(b[1]), \ INIT_CPU_TIMERBASE(b[2]), \ } #define INIT_CPU_TIMERS(s) \ .posix_cputimers = { \ .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } static inline void posixtimer_rearm_itimer(struct task_struct *p) { } static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { return false; } static inline void posixtimer_free_timer(struct k_itimer *timer) { } static inline long posixtimer_create_prctl(unsigned long ctrl) { return -EINVAL; } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK void clear_posix_cputimers_work(struct task_struct *p); void posix_cputimers_init_work(void); #else static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif /** * struct k_itimer - POSIX.1b interval timer structure. * @list: List node for binding the timer to tsk::signal::posix_timers * @ignored_list: List node for tracking ignored timers in tsk::signal::ignored_posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer * @it_status: The status of the timer * @it_sig_periodic: The periodic status at signal delivery * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_signal_seq: Sequence count to control signal delivery * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) * @rcuref: Reference count for life time management * @sigq: Embedded sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { /* 1st cacheline contains read-mostly fields */ struct hlist_node t_hash; struct hlist_node list; timer_t it_id; clockid_t it_clock; int it_sigev_notify; enum pid_type it_pid_type; struct signal_struct *it_signal; const struct k_clock *kclock; /* 2nd cacheline and above contain fields which are modified regularly */ spinlock_t it_lock; int it_status; bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; unsigned int it_sigqueue_seq; ktime_t it_interval; struct hlist_node ignored_list; union { struct pid *it_pid; struct task_struct *it_process; }; struct sigqueue sigq; rcuref_t rcuref; union { struct { struct hrtimer timer; } real; struct cpu_timer cpu; struct { struct alarm alarmtimer; } alarm; } it; struct rcu_head rcu; } ____cacheline_aligned_in_smp; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); #ifdef CONFIG_POSIX_TIMERS static inline void posixtimer_putref(struct k_itimer *tmr) { if (rcuref_put(&tmr->rcuref)) posixtimer_free_timer(tmr); } static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); WARN_ON_ONCE(!rcuref_get(&tmr->rcuref)); } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); posixtimer_putref(tmr); } static inline bool posixtimer_valid(const struct k_itimer *timer) { unsigned long val = (unsigned long)timer->it_signal; return !(val & 0x1UL); } #else /* CONFIG_POSIX_TIMERS */ static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } #endif /* !CONFIG_POSIX_TIMERS */ #endif |
| 130 10 120 131 119 118 16 102 128 3 3 130 131 10 121 12 117 127 133 42 10 121 26 108 130 133 21 21 21 1 3 18 21 21 21 21 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/filelock.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap_prepare = generic_file_readonly_mmap_prepare, .splice_read = filemap_splice_read, .setlease = generic_setlease, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_op->fop_flags & FOP_UNSIGNED_OFFSET; } /** * vfs_setpos_cookie - update the file offset for lseek and reset cookie * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * @cookie: cookie to reset * * Update the file offset to the value specified by @offset if the given * offset is valid and it is not equal to the current file offset and * reset the specified cookie to indicate that a seek happened. * * Return the specified offset on success and -EINVAL on invalid offset. */ static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, loff_t maxsize, u64 *cookie) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; if (cookie) *cookie = 0; } return offset; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { return vfs_setpos_cookie(file, offset, maxsize, NULL); } EXPORT_SYMBOL(vfs_setpos); /** * must_set_pos - check whether f_pos has to be updated * @file: file to seek on * @offset: offset to use * @whence: type of seek operation * @eof: end of file * * Check whether f_pos needs to be updated and update @offset according * to @whence. * * Return: 0 if f_pos doesn't need to be updated, 1 if f_pos has to be * updated, and negative error code on failure. */ static int must_set_pos(struct file *file, loff_t *offset, int whence, loff_t eof) { switch (whence) { case SEEK_END: *offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (*offset == 0) { *offset = file->f_pos; return 0; } break; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)*offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)*offset >= eof) return -ENXIO; *offset = eof; break; } return 1; } /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @maxsize: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { int ret; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; if (whence == SEEK_CUR) { /* * If the file requires locking via f_pos_lock we know * that mutual exclusion for SEEK_CUR on the same file * is guaranteed. If the file isn't locked, we take * f_lock to protect against f_pos races with other * SEEK_CURs. */ if (file_seek_cur_needs_f_lock(file)) { guard(spinlock)(&file->f_lock); return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_llseek_cookie - versioned llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @cookie: cookie to update * * See generic_file_llseek for a general description and locking assumptions. * * In contrast to generic_file_llseek, this function also resets a * specified cookie to indicate a seek took place. */ loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie) { struct inode *inode = file->f_mapping->host; loff_t maxsize = inode->i_sb->s_maxbytes; loff_t eof = i_size_read(inode); int ret; if (WARN_ON_ONCE(!cookie)) return -EINVAL; /* * Require that this is only used for directories that guarantee * synchronization between readdir and seek so that an update to * @cookie is correctly synchronized with concurrent readdir. */ if (WARN_ON_ONCE(!(file->f_mode & FMODE_ATOMIC_POS))) return -EINVAL; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; /* No need to hold f_lock because we know that f_pos_lock is held. */ if (whence == SEEK_CUR) return vfs_setpos_cookie(file, file->f_pos + offset, maxsize, cookie); return vfs_setpos_cookie(file, offset, maxsize, cookie); } EXPORT_SYMBOL(generic_llseek_cookie); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implementation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; retval = inode_lock_killable(inode); if (retval) return retval; switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) file->f_pos = offset; retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; CLASS(fd_pos, f)(fd); if (fd_empty(f)) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(fd_file(f), offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; CLASS(fd_pos, f)(fd); loff_t offset; if (fd_empty(f)) return -EBADF; if (whence > SEEK_MAX) return -EINVAL; offset = vfs_llseek(fd_file(f), ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { int mask = read_write == READ ? MAY_READ : MAY_WRITE; int ret; if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, ppos, count); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = filp->f_op->read_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = filp->f_op->write_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PREAD) return vfs_read(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PWRITE) return vfs_write(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = filp->f_op->read_iter(&kiocb, iter); else ret = filp->f_op->write_iter(&kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } else { nr = filp->f_op->write(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = file->f_op->read_iter(iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, ppos, tot_len); if (ret < 0) return ret; ret = do_iter_readv_writev(file, iter, ppos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iter_read); /* * Caller is responsible for calling kiocb_end_write() on completion * if async iocb was queued. */ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; kiocb_start_write(iocb); ret = file->f_op->write_iter(iocb, iter); if (ret != -EIOCBQUEUED) kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!file->f_op->write_iter) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, ppos, tot_len); if (ret < 0) return ret; file_start_write(file); ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) goto out; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, &iter, pos, READ, flags); else ret = do_loop_readv_writev(file, &iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); kfree(iov); return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) goto out; file_start_write(file); if (file->f_op->write_iter) ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); out: kfree(iov); return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PREAD) ret = vfs_readv(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PWRITE) ret = vfs_writev(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ CLASS(fd, in)(in_fd); if (fd_empty(in)) return -EBADF; if (!(fd_file(in)->f_mode & FMODE_READ)) return -EBADF; if (!ppos) { pos = fd_file(in)->f_pos; } else { pos = *ppos; if (!(fd_file(in)->f_mode & FMODE_PREAD)) return -ESPIPE; } retval = rw_verify_area(READ, fd_file(in), &pos, count); if (retval < 0) return retval; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ CLASS(fd, out)(out_fd); if (fd_empty(out)) return -EBADF; if (!(fd_file(out)->f_mode & FMODE_WRITE)) return -EBADF; in_inode = file_inode(fd_file(in)); out_inode = file_inode(fd_file(out)); out_pos = fd_file(out)->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { if (pos >= max) return -EOVERFLOW; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (fd_file(in)->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(fd_file(out), true); if (!opipe) { retval = rw_verify_area(WRITE, fd_file(out), &out_pos, count); if (retval < 0) return retval; retval = do_splice_direct(fd_file(in), &pos, fd_file(out), &out_pos, count, fl); } else { if (fd_file(out)->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(fd_file(in), opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(fd_file(in)); fsnotify_modify(fd_file(out)); fd_file(out)->f_pos = out_pos; if (ppos) *ppos = pos; else fd_file(in)->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; /* * Make sure return value doesn't overflow in 32bit compat mode. Also * limit the size for all cases except when calling ->copy_file_range(). */ if (splice || !file_out->f_op->copy_file_range || in_compat_syscall()) len = min_t(size_t, MAX_RW_COUNT, len); file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); } else if (!splice && file_in->f_op->remap_file_range && samesb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, REMAP_FILE_CAN_SHORTEN); /* fallback to splice */ if (ret <= 0) splice = true; } else if (samesb) { /* Fallback to splice for same sb copy for backward compat */ splice = true; } file_end_write(file_out); if (!splice) goto done; /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE * for server-side-copy between any two sb. * * In any case, we call do_splice_direct() and not splice_file_range(), * without file_start_write() held, to avoid possible deadlocks related * to splicing from input file, while file_start_write() is held on * the output file on a different sb. */ ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, len, 0); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; ssize_t ret = -EBADF; CLASS(fd, f_in)(fd_in); if (fd_empty(f_in)) return -EBADF; CLASS(fd, f_out)(fd_out); if (fd_empty(f_out)) return -EBADF; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) return -EFAULT; } else { pos_in = fd_file(f_in)->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) return -EFAULT; } else { pos_out = fd_file(f_out)->f_pos; } if (flags != 0) return -EINVAL; ret = vfs_copy_file_range(fd_file(f_in), pos_in, fd_file(f_out), pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_in)->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_out)->f_pos = pos_out; } } return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } EXPORT_SYMBOL_GPL(generic_write_check_limits); /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_op->fop_flags & FOP_BUFFER_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter) { size_t len = iov_iter_count(iter); if (!iter_is_ubuf(iter)) return -EINVAL; if (!is_power_of_2(len)) return -EINVAL; if (!IS_ALIGNED(iocb->ki_pos, len)) return -EINVAL; if (!(iocb->ki_flags & IOCB_DIRECT)) return -EOPNOTSUPP; return 0; } EXPORT_SYMBOL_GPL(generic_atomic_write_valid); |
| 13 1 21 21 21 9 1 9 1 2 3 3 2 13 5 1 3 1 1 22 22 22 22 21 16 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Extension Header handling for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Andi Kleen <ak@muc.de> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ /* Changes: * yoshfuji : ensure not to overrun while parsing * tlv options. * Mitsuru KANDA @USAGI and: Remove ipv6_parse_exthdrs(). * YOSHIFUJI Hideaki @USAGI Register inbound extension header * handlers as inet6_protocol{}. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/dst.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/rawv6.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/calipso.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/xfrm.h> #endif #include <linux/seg6.h> #include <net/seg6.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif #include <net/rpl.h> #include <linux/ioam6.h> #include <linux/ioam6_genl.h> #include <net/ioam6.h> #include <net/dst_metadata.h> #include <linux/uaccess.h> /********************* Generic functions *********************/ /* An unknown option is detected, decide what to do */ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff, bool disallow_unknowns) { if (disallow_unknowns) { /* If unknown TLVs are disallowed by configuration * then always silently drop packet. Note this also * means no ICMP parameter problem is sent which * could be a good property to mitigate a reflection DOS * attack. */ goto drop; } switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ return true; case 1: /* drop packet */ break; case 3: /* Send ICMP if not a multicast address and drop packet */ /* Actually, it is redundant check. icmp_send will recheck in any case. */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; fallthrough; case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob_reason(skb, ICMPV6_UNK_OPTION, optoff, SKB_DROP_REASON_UNHANDLED_PROTO); return false; } drop: kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); return false; } static bool ipv6_hop_ra(struct sk_buff *skb, int optoff); static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff); static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff); static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff); #if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff); #endif /* Parse tlv encoded option header (hop-by-hop or destination) */ static bool ip6_parse_tlv(bool hopbyhop, struct sk_buff *skb, int max_count) { int len = (skb_transport_header(skb)[1] + 1) << 3; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); bool disallow_unknowns = false; int tlv_count = 0; int padlen = 0; if (unlikely(max_count < 0)) { disallow_unknowns = true; max_count = -max_count; } off += 2; len -= 2; while (len > 0) { int optlen, i; if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; off++; len--; continue; } if (len < 2) goto bad; optlen = nh[off + 1] + 2; if (optlen > len) goto bad; if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. * See also RFC 4942, Section 2.1.9.5. */ padlen += optlen; if (padlen > 7) goto bad; /* RFC 4942 recommends receiving hosts to * actively check PadN payload to contain * only zeroes. */ for (i = 2; i < optlen; i++) { if (nh[off + i] != 0) goto bad; } } else { tlv_count++; if (tlv_count > max_count) goto bad; if (hopbyhop) { switch (nh[off]) { case IPV6_TLV_ROUTERALERT: if (!ipv6_hop_ra(skb, off)) return false; break; case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) return false; break; case IPV6_TLV_CALIPSO: if (!ipv6_hop_calipso(skb, off)) return false; break; default: if (!ip6_tlvopt_unknown(skb, off, disallow_unknowns)) return false; break; } } else { switch (nh[off]) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_TLV_HAO: if (!ipv6_dest_hao(skb, off)) return false; break; #endif default: if (!ip6_tlvopt_unknown(skb, off, disallow_unknowns)) return false; break; } } padlen = 0; } off += optlen; len -= optlen; } if (len == 0) return true; bad: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /***************************** Destination options header. *****************************/ #if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); SKB_DR(reason); int ret; if (opt->dsthao) { net_dbg_ratelimited("hao duplicated\n"); goto discard; } opt->dsthao = opt->dst1; opt->dst1 = 0; hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); if (hao->length != 16) { net_dbg_ratelimited("hao invalid option length = %d\n", hao->length); SKB_DR_SET(reason, IP_INHDR); goto discard; } if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { net_dbg_ratelimited("hao is not an unicast addr: %pI6\n", &hao->addr); SKB_DR_SET(reason, INVALID_PROTO); goto discard; } ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr, (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS); if (unlikely(ret < 0)) { SKB_DR_SET(reason, XFRM_POLICY); goto discard; } if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) goto discard; /* update all variable using below by copied skbuff */ hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); ipv6h = ipv6_hdr(skb); } if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; swap(ipv6h->saddr, hao->addr); if (skb->tstamp == 0) __net_timestamp(skb); return true; discard: kfree_skb_reason(skb, reason); return false; } #endif static int ipv6_destopt_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); int extlen; if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(dev_net(dst_dev(dst)), idev, IPSTATS_MIB_INHDRERRORS); fail_and_free: kfree_skb(skb); return -1; } extlen = (skb_transport_header(skb)[1] + 1) << 3; if (extlen > READ_ONCE(net->ipv6.sysctl.max_dst_opts_len)) goto fail_and_free; opt->lastopt = opt->dst1 = skb_network_header_len(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif if (ip6_parse_tlv(false, skb, READ_ONCE(net->ipv6.sysctl.max_dst_opts_cnt))) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; #else opt->nhoff = opt->dst1; #endif return 1; } __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return -1; } static void seg6_update_csum(struct sk_buff *skb) { struct ipv6_sr_hdr *hdr; struct in6_addr *addr; __be32 from, to; /* srh is at transport offset and seg_left is already decremented * but daddr is not yet updated with next segment */ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); addr = hdr->segments + hdr->segments_left; hdr->segments_left++; from = *(__be32 *)hdr; hdr->segments_left--; to = *(__be32 *)hdr; /* update skb csum with diff resulting from seg_left decrement */ update_csum_diff4(skb, from, to); /* compute csum diff between current and next segment and update */ update_csum_diff16(skb, (__be32 *)(&ipv6_hdr(skb)->daddr), (__be32 *)addr); } static int ipv6_srh_rcv(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct ipv6_sr_hdr *hdr; struct inet6_dev *idev; struct in6_addr *addr; int accept_seg6; hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); idev = __in6_dev_get(skb->dev); accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled), READ_ONCE(idev->cnf.seg6_enabled)); if (!accept_seg6) { kfree_skb(skb); return -1; } #ifdef CONFIG_IPV6_SEG6_HMAC if (!seg6_hmac_validate_skb(skb)) { kfree_skb(skb); return -1; } #endif looped_back: if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6 || hdr->nexthdr == NEXTHDR_IPV4) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; if (hdr->nexthdr == NEXTHDR_IPV4) skb->protocol = htons(ETH_P_IP); __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); return -1; } opt->srcrt = skb_network_header_len(skb); opt->lastopt = opt->srcrt; skb->transport_header += (hdr->hdrlen + 1) << 3; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } if (hdr->segments_left >= (hdr->hdrlen >> 1)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; } hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); } hdr->segments_left--; addr = hdr->segments + hdr->segments_left; skb_push(skb, sizeof(struct ipv6hdr)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); ipv6_hdr(skb)->daddr = *addr; ip6_route_input(skb); if (skb_dst(skb)->error) { dst_input(skb); return -1; } if (skb_dst_dev(skb)->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; skb_pull(skb, sizeof(struct ipv6hdr)); goto looped_back; } dst_input(skb); return -1; } static int ipv6_rpl_srh_rcv(struct sk_buff *skb) { struct ipv6_rpl_sr_hdr *hdr, *ohdr, *chdr; struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct inet6_dev *idev; struct ipv6hdr *oldhdr; unsigned char *buf; int accept_rpl_seg; int i, err; u64 n = 0; u32 r; idev = __in6_dev_get(skb->dev); accept_rpl_seg = min(READ_ONCE(net->ipv6.devconf_all->rpl_seg_enabled), READ_ONCE(idev->cnf.rpl_seg_enabled)); if (!accept_rpl_seg) { kfree_skb(skb); return -1; } looped_back: hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); return -1; } opt->srcrt = skb_network_header_len(skb); opt->lastopt = opt->srcrt; skb->transport_header += (hdr->hdrlen + 1) << 3; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } n = (hdr->hdrlen << 3) - hdr->pad - (16 - hdr->cmpre); r = do_div(n, (16 - hdr->cmpri)); /* checks if calculation was without remainder and n fits into * unsigned char which is segments_left field. Should not be * higher than that. */ if (r || (n + 1) > 255) { kfree_skb(skb); return -1; } if (hdr->segments_left > n + 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } hdr->segments_left--; i = n - hdr->segments_left; buf = kcalloc(struct_size(hdr, segments.addr, n + 2), 2, GFP_ATOMIC); if (unlikely(!buf)) { kfree_skb(skb); return -1; } ohdr = (struct ipv6_rpl_sr_hdr *)buf; ipv6_rpl_srh_decompress(ohdr, hdr, &ipv6_hdr(skb)->daddr, n); chdr = (struct ipv6_rpl_sr_hdr *)(buf + ((ohdr->hdrlen + 1) << 3)); if (ipv6_addr_is_multicast(&ohdr->rpl_segaddr[i])) { kfree_skb(skb); kfree(buf); return -1; } err = ipv6_chk_rpl_srh_loop(net, ohdr->rpl_segaddr, n + 1); if (err) { icmpv6_send(skb, ICMPV6_PARAMPROB, 0, 0); kfree_skb(skb); kfree(buf); return -1; } swap(ipv6_hdr(skb)->daddr, ohdr->rpl_segaddr[i]); ipv6_rpl_srh_compress(chdr, ohdr, &ipv6_hdr(skb)->daddr, n); oldhdr = ipv6_hdr(skb); skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); if (unlikely(!hdr->segments_left)) { if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); kfree(buf); return -1; } oldhdr = ipv6_hdr(skb); } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); memmove(ipv6_hdr(skb), oldhdr, sizeof(struct ipv6hdr)); memcpy(skb_transport_header(skb), chdr, (chdr->hdrlen + 1) << 3); ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, ipv6_hdr(skb), sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3)); kfree(buf); ip6_route_input(skb); if (skb_dst(skb)->error) { dst_input(skb); return -1; } if (skb_dst_dev(skb)->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; skb_pull(skb, sizeof(struct ipv6hdr)); goto looped_back; } dst_input(skb); return -1; } /******************************** Routing header. ********************************/ /* called with rcu_read_lock() */ static int ipv6_rthdr_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); struct in6_addr *addr = NULL; int n, i; struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; struct net *net = dev_net(skb->dev); int accept_source_route; accept_source_route = READ_ONCE(net->ipv6.devconf_all->accept_source_route); if (idev) accept_source_route = min(accept_source_route, READ_ONCE(idev->cnf.accept_source_route)); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } switch (hdr->type) { case IPV6_SRCRT_TYPE_4: /* segment routing */ return ipv6_srh_rcv(skb); case IPV6_SRCRT_TYPE_3: /* rpl segment routing */ return ipv6_rpl_srh_rcv(skb); default: break; } looped_back: if (hdr->segments_left == 0) { switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: /* Silently discard type 2 header unless it was * processed by own */ if (!addr) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } break; #endif default: break; } opt->lastopt = opt->srcrt = skb_network_header_len(skb); skb->transport_header += (hdr->hdrlen + 1) << 3; opt->dst0 = opt->dst1; opt->dst1 = 0; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (accept_source_route < 0) goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } break; #endif default: goto unknown_rh; } /* * This is the routing header forwarding algorithm from * RFC 2460, page 16. */ n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } /* We are about to mangle packet header. Be careful! Do not damage packets queued somewhere. */ if (skb_cloned(skb)) { /* the copy is a forwarded packet */ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; } hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); } if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; i = n - --hdr->segments_left; rthdr = (struct rt0_hdr *) hdr; addr = rthdr->addr; addr += i - 1; switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } if (!ipv6_chk_home_addr(skb_dst_dev_net(skb), addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } break; #endif default: break; } if (ipv6_addr_is_multicast(addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } swap(*addr, ipv6_hdr(skb)->daddr); ip6_route_input(skb); if (skb_dst(skb)->error) { skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; } if (skb_dst_dev(skb)->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; goto looped_back; } skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; unknown_rh: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; } static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol nodata_protocol = { .handler = dst_discard, .flags = INET6_PROTO_NOPOLICY, }; int __init ipv6_exthdrs_init(void) { int ret; ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING); if (ret) goto out; ret = inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS); if (ret) goto out_rthdr; ret = inet6_add_protocol(&nodata_protocol, IPPROTO_NONE); if (ret) goto out_destopt; out: return ret; out_destopt: inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); out_rthdr: inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); goto out; }; void ipv6_exthdrs_exit(void) { inet6_del_protocol(&nodata_protocol, IPPROTO_NONE); inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); } /********************************** Hop-by-hop options. **********************************/ /* Router Alert as of RFC 2711 */ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] == 2) { IP6CB(skb)->flags |= IP6SKB_ROUTERALERT; memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); return true; } net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n", nh[optoff + 1]); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /* IOAM */ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) { struct ioam6_trace_hdr *trace; struct ioam6_namespace *ns; struct ioam6_hdr *hdr; /* Bad alignment (must be 4n-aligned) */ if (optoff & 3) goto drop; /* Ignore if IOAM is not enabled on ingress */ if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); if (hdr->opt_len < 2) goto drop; switch (hdr->type) { case IOAM6_TYPE_PREALLOC: /* Truncated Pre-allocated Trace header */ if (hdr->opt_len < 2 + sizeof(*trace)) goto drop; /* Malformed Pre-allocated Trace header */ trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); if (hdr->opt_len < 2 + sizeof(*trace) + trace->remlen * 4) goto drop; /* Inconsistent Pre-allocated Trace header */ if (trace->nodelen != ioam6_trace_compute_nodelen(be32_to_cpu(trace->type_be32))) goto drop; /* Ignore if the IOAM namespace is unknown */ ns = ioam6_namespace(dev_net(skb->dev), trace->namespace_id); if (!ns) goto ignore; if (!skb_valid_dst(skb)) ip6_route_input(skb); /* About to mangle packet header */ if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) goto drop; /* Trace pointer may have changed */ trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + optoff + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); ioam6_event(IOAM6_EVENT_TRACE, dev_net(skb->dev), GFP_ATOMIC, (void *)trace, hdr->opt_len - 2); break; default: break; } ignore: return true; drop: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /* Jumbo payload */ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); SKB_DR(reason); u32 pkt_len; if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", nh[optoff+1]); SKB_DR_SET(reason, IP_INHDR); goto drop; } pkt_len = ntohl(*(__be32 *)(nh + optoff + 2)); if (pkt_len <= IPV6_MAXPLEN) { icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff + 2, SKB_DROP_REASON_IP_INHDR); return false; } if (ipv6_hdr(skb)->payload_len) { icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff, SKB_DROP_REASON_IP_INHDR); return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { SKB_DR_SET(reason, PKT_TOO_SMALL); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto drop; IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM; return true; drop: kfree_skb_reason(skb, reason); return false; } /* CALIPSO RFC 5570 */ static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] < 8) goto drop; if (nh[optoff + 6] * 4 + 8 > nh[optoff + 1]) goto drop; if (!calipso_validate(skb, nh + optoff)) goto drop; return true; drop: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } int ipv6_parse_hopopts(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); int extlen; /* * skb_network_header(skb) is equal to skb->data, and * skb_network_header_len(skb) is always equal to * sizeof(struct ipv6hdr) by definition of * hop-by-hop options. */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) || !pskb_may_pull(skb, (sizeof(struct ipv6hdr) + ((skb_transport_header(skb)[1] + 1) << 3)))) { fail_and_free: kfree_skb(skb); return -1; } extlen = (skb_transport_header(skb)[1] + 1) << 3; if (extlen > READ_ONCE(net->ipv6.sysctl.max_hbh_opts_len)) goto fail_and_free; opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(true, skb, READ_ONCE(net->ipv6.sysctl.max_hbh_opts_cnt))) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); return 1; } return -1; } /* * Creating outbound headers. * * "build" functions work when skb is filled from head to tail (datagram) * "push" functions work when headers are added from tail to head (tcp) * * In both cases we assume, that caller reserved enough room * for headers. */ static u8 ipv6_push_rthdr0(struct sk_buff *skb, u8 proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { struct rt0_hdr *phdr, *ihdr; int hops; ihdr = (struct rt0_hdr *) opt; phdr = skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); memcpy(phdr, ihdr, sizeof(struct rt0_hdr)); hops = ihdr->rt_hdr.hdrlen >> 1; if (hops > 1) memcpy(phdr->addr, ihdr->addr + 1, (hops - 1) * sizeof(struct in6_addr)); phdr->addr[hops - 1] = **addr_p; *addr_p = ihdr->addr; phdr->rt_hdr.nexthdr = proto; return NEXTHDR_ROUTING; } static u8 ipv6_push_rthdr4(struct sk_buff *skb, u8 proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { struct ipv6_sr_hdr *sr_phdr, *sr_ihdr; int plen, hops; sr_ihdr = (struct ipv6_sr_hdr *)opt; plen = (sr_ihdr->hdrlen + 1) << 3; sr_phdr = skb_push(skb, plen); memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr)); hops = sr_ihdr->first_segment + 1; memcpy(sr_phdr->segments + 1, sr_ihdr->segments + 1, (hops - 1) * sizeof(struct in6_addr)); sr_phdr->segments[0] = **addr_p; *addr_p = &sr_ihdr->segments[sr_ihdr->segments_left]; if (sr_ihdr->hdrlen > hops * 2) { int tlvs_offset, tlvs_length; tlvs_offset = (1 + hops * 2) << 3; tlvs_length = (sr_ihdr->hdrlen - hops * 2) << 3; memcpy((char *)sr_phdr + tlvs_offset, (char *)sr_ihdr + tlvs_offset, tlvs_length); } #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(sr_phdr)) { struct net *net = NULL; if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); WARN_ON(!net); if (net) seg6_push_hmac(net, saddr, sr_phdr); } #endif sr_phdr->nexthdr = proto; return NEXTHDR_ROUTING; } static u8 ipv6_push_rthdr(struct sk_buff *skb, u8 proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { switch (opt->type) { case IPV6_SRCRT_TYPE_0: case IPV6_SRCRT_STRICT: case IPV6_SRCRT_TYPE_2: proto = ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr); break; case IPV6_SRCRT_TYPE_4: proto = ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr); break; default: break; } return proto; } static u8 ipv6_push_exthdr(struct sk_buff *skb, u8 proto, u8 type, struct ipv6_opt_hdr *opt) { struct ipv6_opt_hdr *h = skb_push(skb, ipv6_optlen(opt)); memcpy(h, opt, ipv6_optlen(opt)); h->nexthdr = proto; return type; } u8 ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 proto, struct in6_addr **daddr, struct in6_addr *saddr) { if (opt->srcrt) { proto = ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr); /* * IPV6_RTHDRDSTOPTS is ignored * unless IPV6_RTHDR is set (RFC3542). */ if (opt->dst0opt) proto = ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt); } if (opt->hopopt) proto = ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt); return proto; } u8 ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 proto) { if (opt->dst1opt) proto = ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt); return proto; } EXPORT_SYMBOL(ipv6_push_frag_opts); struct ipv6_txoptions * ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) { struct ipv6_txoptions *opt2; opt2 = sock_kmemdup(sk, opt, opt->tot_len, GFP_ATOMIC); if (opt2) { long dif = (char *)opt2 - (char *)opt; if (opt2->hopopt) *((char **)&opt2->hopopt) += dif; if (opt2->dst0opt) *((char **)&opt2->dst0opt) += dif; if (opt2->dst1opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; refcount_set(&opt2->refcnt, 1); } return opt2; } EXPORT_SYMBOL_GPL(ipv6_dup_options); static void ipv6_renew_option(int renewtype, struct ipv6_opt_hdr **dest, struct ipv6_opt_hdr *old, struct ipv6_opt_hdr *new, int newtype, char **p) { struct ipv6_opt_hdr *src; src = (renewtype == newtype ? new : old); if (!src) return; memcpy(*p, src, ipv6_optlen(src)); *dest = (struct ipv6_opt_hdr *)*p; *p += CMSG_ALIGN(ipv6_optlen(*dest)); } /** * ipv6_renew_options - replace a specific ext hdr with a new one. * * @sk: sock from which to allocate memory * @opt: original options * @newtype: option type to replace in @opt * @newopt: new option of type @newtype to replace (user-mem) * * Returns a new set of options which is a copy of @opt with the * option type @newtype replaced with @newopt. * * @opt may be NULL, in which case a new set of options is returned * containing just @newopt. * * @newopt may be NULL, in which case the specified option type is * not copied into the new set of options. * * The new set of options is allocated from the socket option memory * buffer of @sk. */ struct ipv6_txoptions * ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt) { int tot_len = 0; char *p; struct ipv6_txoptions *opt2; if (opt) { if (newtype != IPV6_HOPOPTS && opt->hopopt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt)); if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt)); if (newtype != IPV6_RTHDR && opt->srcrt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt)); if (newtype != IPV6_DSTOPTS && opt->dst1opt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); } if (newopt) tot_len += CMSG_ALIGN(ipv6_optlen(newopt)); if (!tot_len) return NULL; tot_len += sizeof(*opt2); opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC); if (!opt2) return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); refcount_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt, (opt ? opt->hopopt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt, (opt ? opt->dst0opt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_RTHDR, (struct ipv6_opt_hdr **)&opt2->srcrt, (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt, (opt ? opt->dst1opt : NULL), newopt, newtype, &p); opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) + (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) + (opt2->srcrt ? ipv6_optlen(opt2->srcrt) : 0); opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0); return opt2; } struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { /* * ignore the dest before srcrt unless srcrt is being included. * --yoshfuji */ if (opt->dst0opt && !opt->srcrt) { if (opt_space != opt) { memcpy(opt_space, opt, sizeof(*opt_space)); opt = opt_space; } opt->opt_nflen -= ipv6_optlen(opt->dst0opt); opt->dst0opt = NULL; } return opt; } EXPORT_SYMBOL_GPL(__ipv6_fixup_options); /** * __fl6_update_dst - update flowi destination address with info given * by srcrt option, if any. * * @fl6: flowi6 for which daddr is to be updated * @opt: struct ipv6_txoptions in which to look for srcrt opt * @orig: copy of original daddr address if modified * * Return: NULL if no srcrt or invalid srcrt type, otherwise returns orig * and initial value of fl6->daddr set in orig */ struct in6_addr *__fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig) { if (!opt->srcrt) return NULL; *orig = fl6->daddr; switch (opt->srcrt->type) { case IPV6_SRCRT_TYPE_0: case IPV6_SRCRT_STRICT: case IPV6_SRCRT_TYPE_2: fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; break; case IPV6_SRCRT_TYPE_4: { struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt; fl6->daddr = srh->segments[srh->segments_left]; break; } default: return NULL; } return orig; } EXPORT_SYMBOL_GPL(__fl6_update_dst); |
| 13 13 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ipi #if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IPI_H #include <linux/tracepoint.h> TRACE_EVENT(ipi_send_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), TP_ARGS(cpu, callsite, callback), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpu=%u callsite=%pS callback=%pS", __entry->cpu, __entry->callsite, __entry->callback) ); TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), TP_ARGS(cpumask, callsite, callback), TP_STRUCT__entry( __cpumask(cpumask) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __assign_cpumask(cpumask, cpumask_bits(cpumask)); __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpumask=%s callsite=%pS callback=%pS", __get_cpumask(cpumask), __entry->callsite, __entry->callback) ); #ifdef CONFIG_HAVE_EXTRA_IPI_TRACEPOINTS /** * ipi_raise - called when a smp cross call is made * * @mask: mask of recipient CPUs for the IPI * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string. */ TRACE_EVENT(ipi_raise, TP_PROTO(const struct cpumask *mask, const char *reason), TP_ARGS(mask, reason), TP_STRUCT__entry( __bitmask(target_cpus, nr_cpumask_bits) __field(const char *, reason) ), TP_fast_assign( __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); __entry->reason = reason; ), TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( __field(const char *, reason) ), TP_fast_assign( __entry->reason = reason; ), TP_printk("(%s)", __entry->reason) ); /** * ipi_entry - called immediately before the IPI handler * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise * for that IPI. */ DEFINE_EVENT(ipi_handler, ipi_entry, TP_PROTO(const char *reason), TP_ARGS(reason) ); /** * ipi_exit - called immediately after the IPI handler returns * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise for * that IPI. */ DEFINE_EVENT(ipi_handler, ipi_exit, TP_PROTO(const char *reason), TP_ARGS(reason) ); #endif /* CONFIG_HAVE_EXTRA_IPI_TRACEPOINTS */ #endif /* _TRACE_IPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Type definitions for the multi-level security (MLS) policy. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. */ #ifndef _SS_MLS_TYPES_H_ #define _SS_MLS_TYPES_H_ #include "security.h" #include "ebitmap.h" struct mls_level { u32 sens; /* sensitivity */ struct ebitmap cat; /* category set */ }; struct mls_range { struct mls_level level[2]; /* low == level[0], high == level[1] */ }; static inline int mls_level_eq(const struct mls_level *l1, const struct mls_level *l2) { return ((l1->sens == l2->sens) && ebitmap_equal(&l1->cat, &l2->cat)); } static inline int mls_level_dom(const struct mls_level *l1, const struct mls_level *l2) { return ((l1->sens >= l2->sens) && ebitmap_contains(&l1->cat, &l2->cat, 0)); } #define mls_level_incomp(l1, l2) \ (!mls_level_dom((l1), (l2)) && !mls_level_dom((l2), (l1))) #define mls_level_between(l1, l2, l3) \ (mls_level_dom((l1), (l2)) && mls_level_dom((l3), (l1))) #define mls_range_contains(r1, r2) \ (mls_level_dom(&(r2).level[0], &(r1).level[0]) && \ mls_level_dom(&(r1).level[1], &(r2).level[1])) #endif /* _SS_MLS_TYPES_H_ */ |
| 7 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_LE_H_ #define _ASM_GENERIC_BITOPS_LE_H_ #include <asm/types.h> #include <asm/byteorder.h> #if defined(__LITTLE_ENDIAN) #define BITOP_LE_SWIZZLE 0 #elif defined(__BIG_ENDIAN) #define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) #endif static inline int test_bit_le(int nr, const void *addr) { return test_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void set_bit_le(int nr, void *addr) { set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void clear_bit_le(int nr, void *addr) { clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __set_bit_le(int nr, void *addr) { __set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __clear_bit_le(int nr, void *addr) { __clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_set_bit_le(int nr, void *addr) { return test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_clear_bit_le(int nr, void *addr) { return test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_set_bit_le(int nr, void *addr) { return __test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_clear_bit_le(int nr, void *addr) { return __test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } #endif /* _ASM_GENERIC_BITOPS_LE_H_ */ |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Multicast support for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c */ /* Changes: * * yoshfuji : fix format of router-alert option * YOSHIFUJI Hideaki @USAGI: * Fixed source address for MLD message based on * <draft-ietf-magma-mld-source-05.txt>. * YOSHIFUJI Hideaki @USAGI: * - Ignore Queries for invalid addresses. * - MLD for link-local addresses. * David L Stevens <dlstevens@us.ibm.com>: * - MLDv2 support */ #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/jiffies.h> #include <linux/net.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/workqueue.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/inet_common.h> #include <net/ip6_checksum.h> /* Ensure that we have struct in6_addr aligned on 32bit word. */ static int __mld2_query_bugs[] __attribute__((__unused__)) = { BUILD_BUG_ON_ZERO(offsetof(struct mld2_query, mld2q_srcs) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_report, mld2r_grec) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct workqueue_struct *mld_wq; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); static void mld_mca_work(struct work_struct *work); static void mld_ifc_event(struct inet6_dev *idev); static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ #define MLD_QI_DEFAULT (125 * HZ) /* RFC3810, 9.3. Query Response Interval */ #define MLD_QRI_DEFAULT (10 * HZ) /* RFC3810, 8.1 Query Version Distinctions */ #define MLD_V1_QUERY_LEN 24 #define MLD_V2_QUERY_LEN_MIN 28 #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; #define mc_assert_locked(idev) \ lockdep_assert_held(&(idev)->mc_lock) #define mc_dereference(e, idev) \ rcu_dereference_protected(e, lockdep_is_held(&(idev)->mc_lock)) #define sock_dereference(e, sk) \ rcu_dereference_protected(e, lockdep_sock_is_held(sk)) #define for_each_pmc_socklock(np, sk, pmc) \ for (pmc = sock_dereference((np)->ipv6_mc_list, sk); \ pmc; \ pmc = sock_dereference(pmc->next, sk)) #define for_each_pmc_rcu(np, pmc) \ for (pmc = rcu_dereference((np)->ipv6_mc_list); \ pmc; \ pmc = rcu_dereference(pmc->next)) #define for_each_psf_mclock(mc, psf) \ for (psf = mc_dereference((mc)->mca_sources, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_psf_rcu(mc, psf) \ for (psf = rcu_dereference((mc)->mca_sources); \ psf; \ psf = rcu_dereference(psf->sf_next)) #define for_each_psf_tomb(mc, psf) \ for (psf = mc_dereference((mc)->mca_tomb, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_mc_mclock(idev, mc) \ for (mc = mc_dereference((idev)->mc_list, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) #define for_each_mc_rcu(idev, mc) \ for (mc = rcu_dereference((idev)->mc_list); \ mc; \ mc = rcu_dereference(mc->next)) #define for_each_mc_tomb(idev, mc) \ for (mc = mc_dereference((idev)->mc_tomb, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) static int unsolicited_report_interval(struct inet6_dev *idev) { int iv; if (mld_in_v1_mode(idev)) iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } static struct net_device *ip6_mc_find_dev(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; struct rt6_info *rt; if (ifindex == 0) { rcu_read_lock(); rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = dst_dev_rcu(&rt->dst); dev_hold(dev); ip6_rt_put(rt); } rcu_read_unlock(); } else { dev = dev_get_by_index(net, ifindex); } return dev; } /* * socket join on multicast group */ static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); struct net_device *dev = NULL; int err; if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for_each_pmc_socklock(np, sk, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) return -EADDRINUSE; } mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); if (!mc_lst) return -ENOMEM; mc_lst->next = NULL; mc_lst->addr = *addr; dev = ip6_mc_find_dev(net, addr, ifindex); if (!dev) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = mode; RCU_INIT_POINTER(mc_lst->sflist, NULL); /* now add/increase the group membership on the device */ err = __ipv6_dev_mc_inc(dev, addr, mode); dev_put(dev); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_sock_mc_join); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { return __ipv6_sock_mc_join(sk, ifindex, addr, mode); } /* * socket leave on multicast group */ static void __ipv6_sock_mc_drop(struct sock *sk, struct ipv6_mc_socklist *mc_lst) { struct net *net = sock_net(sk); struct net_device *dev; dev = dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) { __ipv6_dev_mc_dec(idev, &mc_lst->addr); in6_dev_put(idev); } dev_put(dev); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); } int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist __rcu **lnk; struct ipv6_mc_socklist *mc_lst; if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for (lnk = &np->ipv6_mc_list; (mc_lst = sock_dereference(*lnk, sk)) != NULL; lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { *lnk = mc_lst->next; __ipv6_sock_mc_drop(sk, mc_lst); return 0; } } return -EADDRNOTAVAIL; } EXPORT_SYMBOL(ipv6_sock_mc_drop); static struct inet6_dev *ip6_mc_find_idev(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev; struct inet6_dev *idev; dev = ip6_mc_find_dev(net, group, ifindex); if (!dev) return NULL; idev = in6_dev_get(dev); dev_put(dev); return idev; } void __ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { np->ipv6_mc_list = mc_lst->next; __ipv6_sock_mc_drop(sk, mc_lst); } } void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!rcu_access_pointer(np->ipv6_mc_list)) return; lock_sock(sk); __ipv6_sock_mc_close(sk); release_sock(sk); } int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr) { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct in6_addr *source, *group; struct net *net = sock_net(sk); struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; struct inet6_dev *idev; int leavegroup = 0; int i, j, rv; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; idev = ip6_mc_find_idev(net, group, pgsr->gsr_interface); if (!idev) return -ENODEV; mutex_lock(&idev->mc_lock); if (idev->dead) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_socklock(inet6, sk, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (rcu_access_pointer(pmc->sflist)) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip6_mc_add_src(idev, group, omode, 0, NULL, 0); ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = sock_dereference(pmc->sflist, sk); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= sysctl_mld_max_msf) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip6_sf_socklist *newpsl; int count = IP6_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP6_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) /* There is an error in the address. */ goto done; } for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; psl->sl_count++; err = 0; /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); if (leavegroup) err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list) { struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; int leavegroup = 0; int i, err; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; if (gsf->gf_fmode != MCAST_INCLUDE && gsf->gf_fmode != MCAST_EXCLUDE) return -EINVAL; idev = ip6_mc_find_idev(net, group, gsf->gf_interface); if (!idev) return -ENODEV; mutex_lock(&idev->mc_lock); if (idev->dead) { err = -ENODEV; goto done; } err = 0; if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (gsf->gf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, gsf->gf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc; for (i = 0; i < newpsl->sl_count; ++i, ++list) { struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)list; newpsl->sl_addr[i] = psin6->sin6_addr; } err = ip6_mc_add_src(idev, group, gsf->gf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); } psl = sock_dereference(pmc->sflist, sk); if (psl) { ip6_mc_del_src(idev, group, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: mutex_unlock(&idev->mc_lock); in6_dev_put(idev); if (leavegroup) err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; } int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { struct ipv6_pinfo *inet6 = inet6_sk(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; unsigned int count; int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; psin6 = (struct sockaddr_in6 *)&ss; memset(&ss, 0, sizeof(ss)); psin6->sin6_family = AF_INET6; psin6->sin6_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr) { const struct ipv6_pinfo *np = inet6_sk(sk); const struct ipv6_mc_socklist *mc; const struct ip6_sf_socklist *psl; bool rv = true; rcu_read_lock(); for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { rcu_read_unlock(); return inet6_test_bit(MC6_ALL, sk); } psl = rcu_dereference(mc->sflist); if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; } else { int i; for (i = 0; i < psl->sl_count; i++) { if (ipv6_addr_equal(&psl->sl_addr[i], src_addr)) break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) rv = false; } rcu_read_unlock(); return rv; } static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; mc_assert_locked(mc->idev); if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } /* else v2 */ /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we * should not send filter-mode change record as the mode * should be from IN() to IN(A). */ if (mc->mca_sfmode == MCAST_EXCLUDE) mc->mca_crcount = mc->idev->mc_qrv; mld_ifc_event(mc->idev); } static void igmp6_group_dropped(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; mc_assert_locked(mc->idev); if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) return; if (!mc->idev->dead) igmp6_leave_group(mc); if (cancel_delayed_work(&mc->mca_work)) refcount_dec(&mc->mca_refcnt); } /* deleted ifmcaddr6 manipulation */ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc; mc_assert_locked(idev); /* this is an "ifmcaddr6" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc_obj(*pmc); if (!pmc) return; pmc->idev = im->idev; in6_dev_hold(idev); pmc->mca_addr = im->mca_addr; pmc->mca_crcount = idev->mc_qrv; pmc->mca_sfmode = im->mca_sfmode; if (pmc->mca_sfmode == MCAST_INCLUDE) { struct ip6_sf_list *psf; rcu_assign_pointer(pmc->mca_tomb, mc_dereference(im->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_sources, mc_dereference(im->mca_sources, idev)); RCU_INIT_POINTER(im->mca_tomb, NULL); RCU_INIT_POINTER(im->mca_sources, NULL); for_each_psf_mclock(pmc, psf) psf->sf_crcount = pmc->mca_crcount; } rcu_assign_pointer(pmc->next, idev->mc_tomb); rcu_assign_pointer(idev->mc_tomb, pmc); } static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ip6_sf_list *psf, *sources, *tomb; struct in6_addr *pmca = &im->mca_addr; struct ifmcaddr6 *pmc, *pmc_prev; mc_assert_locked(idev); pmc_prev = NULL; for_each_mc_tomb(idev, pmc) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) break; pmc_prev = pmc; } if (!pmc) return; if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc->next); else rcu_assign_pointer(idev->mc_tomb, pmc->next); im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { tomb = rcu_replace_pointer(im->mca_tomb, mc_dereference(pmc->mca_tomb, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_tomb, tomb); sources = rcu_replace_pointer(im->mca_sources, mc_dereference(pmc->mca_sources, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_sources, sources); for_each_psf_mclock(im, psf) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; mc_assert_locked(idev); pmc = mc_dereference(idev->mc_tomb, idev); RCU_INIT_POINTER(idev->mc_tomb, NULL); for (; pmc; pmc = nextpmc) { nextpmc = mc_dereference(pmc->next, idev); ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } /* clear dead sources, too */ for_each_mc_mclock(idev, pmc) { struct ip6_sf_list *psf, *psf_next; psf = mc_dereference(pmc->mca_tomb, idev); RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (; psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); kfree_rcu(psf, rcu); } } } static void mld_clear_query(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); __skb_queue_purge(&idev->mc_query_queue); spin_unlock_bh(&idev->mc_query_lock); } static void mld_clear_report(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_report_lock); __skb_queue_purge(&idev->mc_report_queue); spin_unlock_bh(&idev->mc_report_lock); } static void ma_put(struct ifmcaddr6 *mc) { if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree_rcu(mc, rcu); } } static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; mc_assert_locked(idev); mc = kzalloc_obj(*mc); if (!mc) return NULL; INIT_DELAYED_WORK(&mc->mca_work, mld_mca_work); mc->mca_addr = *addr; mc->idev = idev; /* reference taken by caller */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; refcount_set(&mc->mca_refcnt, 1); mc->mca_sfmode = mode; mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) mc->mca_flags |= MAF_NOREPORT; return mc; } static void inet6_ifmcaddr_notify(struct net_device *dev, const struct ifmcaddr6 *ifmca, int event) { struct inet6_fill_args fillargs = { .portid = 0, .seq = 0, .event = event, .flags = 0, .netnsid = -1, .force_rt_scope_universe = true, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(struct in6_addr)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) goto error; err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); goto error; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MCADDR, NULL, GFP_KERNEL); return; error: rtnl_set_sk_err(net, RTNLGRP_IPV6_MCADDR, err); } /* * device multicast group inc (add if not found) */ static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode) { struct inet6_dev *idev; struct ifmcaddr6 *mc; /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (!idev) return -EINVAL; mutex_lock(&idev->mc_lock); if (READ_ONCE(idev->dead)) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENODEV; } for_each_mc_mclock(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return 0; } } mc = mca_alloc(idev, addr, mode); if (!mc) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENOMEM; } rcu_assign_pointer(mc->next, idev->mc_list); rcu_assign_pointer(idev->mc_list, mc); mld_del_delrec(idev, mc); igmp6_group_added(mc); inet6_ifmcaddr_notify(dev, mc, RTM_NEWMULTICAST); mutex_unlock(&idev->mc_lock); return 0; } int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del */ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, __rcu **map; mutex_lock(&idev->mc_lock); for (map = &idev->mc_list; (ma = mc_dereference(*map, idev)); map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { if (--ma->mca_users == 0) { *map = ma->next; igmp6_group_dropped(ma); inet6_ifmcaddr_notify(idev->dev, ma, RTM_DELMULTICAST); ip6_mc_clear_src(ma); mutex_unlock(&idev->mc_lock); ma_put(ma); return 0; } mutex_unlock(&idev->mc_lock); return 0; } } mutex_unlock(&idev->mc_lock); return -ENOENT; } int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; int err; idev = in6_dev_get(dev); if (!idev) return -ENODEV; err = __ipv6_dev_mc_dec(idev, addr); in6_dev_put(idev); return err; } EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; bool rv = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (!idev) goto unlock; for_each_mc_rcu(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, group)) break; } if (!mc) goto unlock; if (src_addr && !ipv6_addr_any(src_addr)) { struct ip6_sf_list *psf; for_each_psf_rcu(mc, psf) { if (ipv6_addr_equal(&psf->sf_addr, src_addr)) break; } if (psf) rv = READ_ONCE(psf->sf_count[MCAST_INCLUDE]) || READ_ONCE(psf->sf_count[MCAST_EXCLUDE]) != READ_ONCE(mc->mca_sfcount[MCAST_EXCLUDE]); else rv = READ_ONCE(mc->mca_sfcount[MCAST_EXCLUDE]) != 0; } else { rv = true; /* don't filter unspecified source */ } unlock: rcu_read_unlock(); return rv; } static void mld_gq_start_work(struct inet6_dev *idev) { unsigned long tv = get_random_u32_below(idev->mc_maxdelay); mc_assert_locked(idev); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) in6_dev_hold(idev); } static void mld_gq_stop_work(struct inet6_dev *idev) { mc_assert_locked(idev); idev->mc_gq_running = 0; if (cancel_delayed_work(&idev->mc_gq_work)) __in6_dev_put(idev); } static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); mc_assert_locked(idev); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); } static void mld_ifc_stop_work(struct inet6_dev *idev) { mc_assert_locked(idev); idev->mc_ifc_count = 0; if (cancel_delayed_work(&idev->mc_ifc_work)) __in6_dev_put(idev); } static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); mc_assert_locked(idev); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); } static void mld_dad_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work(&idev->mc_dad_work)) __in6_dev_put(idev); } static void mld_query_stop_work(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); if (cancel_delayed_work(&idev->mc_query_work)) __in6_dev_put(idev); spin_unlock_bh(&idev->mc_query_lock); } static void mld_report_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work_sync(&idev->mc_report_work)) __in6_dev_put(idev); } /* IGMP handling (alias multicast ICMPv6 messages) */ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) { unsigned long delay = resptime; mc_assert_locked(ma->idev); /* Do not start work for these addresses */ if (ipv6_addr_is_ll_all_nodes(&ma->mca_addr) || IPV6_ADDR_MC_SCOPE(&ma->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (delay >= resptime) delay = get_random_u32_below(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } /* mark EXCLUDE-mode sources */ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; mc_assert_locked(pmc->idev); scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { scount++; break; } } } pmc->mca_flags &= ~MAF_GSQUERY; if (scount == nsrcs) /* all sources excluded */ return false; return true; } static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; mc_assert_locked(pmc->idev); if (pmc->mca_sfmode == MCAST_EXCLUDE) return mld_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } } } if (!scount) { pmc->mca_flags &= ~MAF_GSQUERY; return false; } pmc->mca_flags |= MAF_GSQUERY; return true; } static int mld_force_mld_version(const struct inet6_dev *idev) { const struct net *net = dev_net(idev->dev); int all_force; all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 2; } static bool mld_in_v1_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 1; } static bool mld_in_v1_mode(const struct inet6_dev *idev) { if (mld_in_v2_mode_only(idev)) return false; if (mld_in_v1_mode_only(idev)) return true; if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) return true; return false; } static void mld_set_v1_mode(struct inet6_dev *idev) { /* RFC3810, relevant sections: * - 9.1. Robustness Variable * - 9.2. Query Interval * - 9.3. Query Response Interval * - 9.12. Older Version Querier Present Timeout */ unsigned long switchback; switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; idev->mc_v1_seen = jiffies + switchback; } static void mld_update_qrv(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.8. QRV (Querier's Robustness Variable) * - 9.1. Robustness Variable */ /* The value of the Robustness Variable MUST NOT be zero, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", idev->mc_qrv, min_qrv); idev->mc_qrv = min_qrv; } } static void mld_update_qi(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.9. QQIC (Querier's Query Interval Code) * - 9.2. Query Interval * - 9.12. Older Version Querier Present Timeout * (the [Query Interval] in the last Query received) */ unsigned long mc_qqi; if (mlh2->mld2q_qqic < 128) { mc_qqi = mlh2->mld2q_qqic; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); mc_qqi = (mc_man | 0x10) << (mc_exp + 3); } idev->mc_qi = mc_qqi * HZ; } static void mld_update_qri(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.3. Maximum Response Code * - 9.3. Query Response Interval */ idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); } static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, unsigned long *max_delay, bool v1_query) { unsigned long mldv1_md; /* Ignore v1 queries */ if (mld_in_v2_mode_only(idev)) return -EINVAL; mldv1_md = ntohs(mld->mld_maxdelay); /* When in MLDv1 fallback and a MLDv2 router start-up being * unaware of current MLDv1 operation, the MRC == MRD mapping * only works when the exponential algorithm is not being * used (as MLDv1 is unaware of such things). * * According to the RFC author, the MLDv2 implementations * he's aware of all use a MRC < 32768 on start up queries. * * Thus, should we *ever* encounter something else larger * than that, just assume the maximum possible within our * reach. */ if (!v1_query) mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT); *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); /* MLDv1 router present: we need to go into v1 mode *only* * when an MLDv1 query is received as per section 9.12. of * RFC3810! And we know from RFC2710 section 3.7 that MLDv1 * queries MUST be of exactly 24 octets. */ if (v1_query) mld_set_v1_mode(idev); /* cancel MLDv2 report work */ mld_gq_stop_work(idev); /* cancel the interface change work */ mld_ifc_stop_work(idev); /* clear deleted report items */ mld_clear_delrec(idev); return 0; } static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, unsigned long *max_delay) { *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); mld_update_qrv(idev, mld); mld_update_qi(idev, mld); mld_update_qri(idev, mld); idev->mc_maxdelay = *max_delay; return; } /* called with rcu_read_lock() */ void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_query_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); out: kfree_skb(skb); } static void __mld_query_work(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int group_type; int mark = 0; int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) goto kfree_skb; /* compute payload length excluding extension headers */ len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); len -= skb_network_header_len(skb); /* RFC3810 6.2 * Upon reception of an MLD message that contains a Query, the node * checks if the source address of the message is a valid link-local * address, if the Hop Limit is set to 1, and if the Router Alert * option is present in the Hop-By-Hop Options header of the IPv6 * packet. If any of these checks fails, the packet is dropped. */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || ipv6_hdr(skb)->hop_limit != 1 || !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && !(group_type&IPV6_ADDR_MULTICAST)) goto out; if (len < MLD_V1_QUERY_LEN) { goto out; } else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) { err = mld_process_v1(idev, mld, &max_delay, len == MLD_V1_QUERY_LEN); if (err < 0) goto out; } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); if (!pskb_may_pull(skb, srcs_offset)) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mld_process_v2(idev, mlh2, &max_delay); if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) goto out; /* no sources allowed */ mld_gq_start_work(idev); goto out; } /* mark sources to include, if group & source-specific */ if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } } else { goto out; } if (group_type == IPV6_ADDR_ANY) { for_each_mc_mclock(idev, ma) { igmp6_group_queried(ma, max_delay); } } else { for_each_mc_mclock(idev, ma) { if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; if (ma->mca_flags & MAF_TIMER_RUNNING) { /* gsquery <- gsquery && mark */ if (!mark) ma->mca_flags &= ~MAF_GSQUERY; } else { /* gsquery <- mark */ if (mark) ma->mca_flags |= MAF_GSQUERY; else ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); break; } } out: in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_query_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_query_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_query_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_query_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0)) return; in6_dev_put(idev); } /* called with rcu_read_lock() */ void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_report_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); out: kfree_skb(skb); } static void __mld_report_work(struct sk_buff *skb) { struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ if (skb->pkt_type == PACKET_LOOPBACK) goto kfree_skb; /* send our report if the MC router may not have heard this report */ if (skb->pkt_type != PACKET_MULTICAST && skb->pkt_type != PACKET_BROADCAST) goto kfree_skb; if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); if (addr_type != IPV6_ADDR_ANY && !(addr_type&IPV6_ADDR_LINKLOCAL)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; /* * Cancel the work for this group */ for_each_mc_mclock(idev, ma) { if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { if (cancel_delayed_work(&ma->mca_work)) refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER | MAF_TIMER_RUNNING); break; } } in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_report_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_report_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_report_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_report_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0)) return; in6_dev_put(idev); } static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return false; if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { if (pmc->mca_sfmode == MCAST_INCLUDE) return true; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return false; } static int mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { struct ip6_sf_list *psf; int scount = 0; for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, int proto, int len) { struct ipv6hdr *hdr; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reset_network_header(skb); skb_put(skb, sizeof(struct ipv6hdr)); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, 0, 0); hdr->payload_len = htons(len); hdr->nexthdr = proto; hdr->hop_limit = READ_ONCE(inet6_sk(sk)->hop_limit); hdr->saddr = *saddr; hdr->daddr = *daddr; } static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; struct net *net; /* we assume size > sizeof(ra) here * Also try to not allocate high-order pages for big MTU */ size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = alloc_skb(size, GFP_KERNEL); if (!skb) return NULL; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); rcu_read_lock(); net = dev_net_rcu(dev); sk = net->ipv6.igmp_sk; skb_set_owner_w(skb, sk); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); rcu_read_unlock(); skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_type = ICMPV6_MLD2_REPORT; pmr->mld2r_resv1 = 0; pmr->mld2r_cksum = 0; pmr->mld2r_resv2 = 0; pmr->mld2r_ngrec = 0; return skb; } static void mld_sendpack(struct sk_buff *skb) { struct ipv6hdr *pip6 = ipv6_hdr(skb); struct mld2_report *pmr = (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); int err; struct flowi6 fl6; struct dst_entry *dst; rcu_read_lock(); idev = __in6_dev_get(skb->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; } skb_dst_set(skb, dst); if (err) goto err_out; err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) { return sizeof(struct mld2_grec) + 16 * mld_scount(pmc,type,gdel,sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, struct mld2_grec **ppgr, unsigned int mtu) { struct mld2_report *pmr; struct mld2_grec *pgr; if (!skb) { skb = mld_newpack(pmc->idev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted, int crsend) { struct ip6_sf_list *psf, *psf_prev, *psf_next; int scount, stotal, first, isquery, truncate; struct ip6_sf_list __rcu **psf_list; struct inet6_dev *idev = pmc->idev; struct net_device *dev = idev->dev; struct mld2_grec *pgr = NULL; struct mld2_report *pmr; unsigned int mtu; mc_assert_locked(idev); if (pmc->mca_flags & MAF_NOREPORT) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV6_MIN_MTU) return skb; isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; if (!rcu_access_pointer(*psf_list)) goto empty_source; pmr = skb ? (struct mld2_report *)skb_transport_header(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); } } first = 1; psf_prev = NULL; for (psf = mc_dereference(*psf_list, idev); psf; psf = psf_next) { struct in6_addr *psrc; psf_next = mc_dereference(psf->sf_next, idev); if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } /* Based on RFC3810 6.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->mca_sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->mca_crcount)) && (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(*psrc) + first*sizeof(struct mld2_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*psf_list, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) return skb; if (pmc->mca_crcount || isquery || crsend) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->mca_flags &= ~MAF_GSQUERY; /* clear query state */ return skb; } static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) { struct sk_buff *skb = NULL; int type; mc_assert_locked(idev); if (!pmc) { for_each_mc_mclock(idev, pmc) { if (pmc->mca_flags & MAF_NOREPORT) continue; if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } } else { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } if (skb) mld_sendpack(skb); } /* remove zero-count source records from a source filter list */ static void mld_clear_zeros(struct ip6_sf_list __rcu **ppsf, struct inet6_dev *idev) { struct ip6_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = mc_dereference(*ppsf, idev); psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); if (psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*ppsf, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); } else { psf_prev = psf; } } } static void mld_send_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; /* deleted MCA's */ pmc_prev = NULL; for (pmc = mc_dereference(idev->mc_tomb, idev); pmc; pmc = pmc_next) { pmc_next = mc_dereference(pmc->next, idev); if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0, 0); skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0, 0); } pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb, idev); mld_clear_zeros(&pmc->mca_sources, idev); } } if (pmc->mca_crcount == 0 && !rcu_access_pointer(pmc->mca_tomb) && !rcu_access_pointer(pmc->mca_sources)) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc_next); else rcu_assign_pointer(idev->mc_tomb, pmc_next); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } else pmc_prev = pmc; } /* change recs */ for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_ALLOW_NEW_SOURCES; } else { type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); pmc->mca_crcount--; } } if (!skb) return; (void) mld_sendpack(skb); } static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { const struct in6_addr *snd_addr, *saddr; int err, len, payload_len, full_len; struct in6_addr addr_buf; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct dst_entry *dst; struct flowi6 fl6; struct net *net; struct sock *sk; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; else snd_addr = addr; len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; skb = alloc_skb(hlen + tlen + full_len, GFP_KERNEL); rcu_read_lock(); net = dev_net_rcu(dev); idev = __in6_dev_get(dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } sk = net->ipv6.igmp_sk; skb_set_owner_w(skb, sk); skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); skb_put_data(skb, ra, sizeof(ra)); hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; } skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static void mld_send_initial_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; struct sk_buff *skb; int type; mc_assert_locked(idev); if (mld_in_v1_mode(idev)) return; skb = NULL; for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); } if (skb) mld_sendpack(skb); } void ipv6_mc_dad_complete(struct inet6_dev *idev) { mutex_lock(&idev->mc_lock); idev->mc_dad_count = idev->mc_qrv; if (idev->mc_dad_count) { mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); } static void mld_dad_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_dad_work); mutex_lock(&idev->mc_lock); mld_send_initial_cr(idev); if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; mc_assert_locked(pmc->idev); psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] - 1); if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { struct inet6_dev *idev = pmc->idev; /* no more filters for this source */ if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(pmc->mca_sources, mc_dereference(psf->sf_next, idev)); if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; rcu_assign_pointer(psf->sf_next, mc_dereference(pmc->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_tomb, psf); rv = 1; } else { kfree_rcu(psf, rcu); } } return rv; } static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int changerec = 0; int i, err; if (!idev) return -ENODEV; mc_assert_locked(idev); for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); if (!delta) { if (!pmc->mca_sfcount[sfmode]) return -EINVAL; pmc->mca_sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->mca_sfmode == MCAST_EXCLUDE && pmc->mca_sfcount[MCAST_EXCLUDE] == 0 && pmc->mca_sfcount[MCAST_INCLUDE]) { struct ip6_sf_list *psf; /* filter mode change */ pmc->mca_sfmode = MCAST_INCLUDE; pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(pmc->idev); } else if (sf_setstate(pmc) || changerec) { mld_ifc_event(pmc->idev); } return err; } /* Add multicast single-source filter to the interface list */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; mc_assert_locked(pmc->idev); psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf) { psf = kzalloc_obj(*psf); if (!psf) return -ENOBUFS; psf->sf_addr = *psfsrc; if (psf_prev) { rcu_assign_pointer(psf_prev->sf_next, psf); } else { rcu_assign_pointer(pmc->mca_sources, psf); } } WRITE_ONCE(psf->sf_count[sfmode], psf->sf_count[sfmode] + 1); return 0; } static void sf_markstate(struct ifmcaddr6 *pmc) { int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; struct ip6_sf_list *psf; mc_assert_locked(pmc->idev); for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } } } static int sf_setstate(struct ifmcaddr6 *pmc) { int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; struct ip6_sf_list *psf, *dpsf; int qrv = pmc->idev->mc_qrv; int new_in, rv; mc_assert_locked(pmc->idev); rv = 0; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip6_sf_list *prev = NULL; for_each_psf_tomb(pmc, dpsf) { if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; prev = dpsf; } if (dpsf) { if (prev) rcu_assign_pointer(prev->sf_next, mc_dereference(dpsf->sf_next, pmc->idev)); else rcu_assign_pointer(pmc->mca_tomb, mc_dereference(dpsf->sf_next, pmc->idev)); kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for_each_psf_tomb(pmc, dpsf) if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; if (!dpsf) { dpsf = kmalloc_obj(*dpsf); if (!dpsf) continue; *dpsf = *psf; rcu_assign_pointer(dpsf->sf_next, mc_dereference(pmc->mca_tomb, pmc->idev)); rcu_assign_pointer(pmc->mca_tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; } } return rv; } /* Add multicast source filter list to the interface list */ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int isexclude; int i, err; if (!idev) return -ENODEV; mc_assert_locked(idev); for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); isexclude = pmc->mca_sfmode == MCAST_EXCLUDE; if (!delta) WRITE_ONCE(pmc->mca_sfcount[sfmode], pmc->mca_sfcount[sfmode] + 1); err = 0; for (i = 0; i < sfcount; i++) { err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) WRITE_ONCE(pmc->mca_sfcount[sfmode], pmc->mca_sfcount[sfmode] - 1); for (j = 0; j < i; j++) ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; /* filter mode change */ if (pmc->mca_sfcount[MCAST_EXCLUDE]) pmc->mca_sfmode = MCAST_EXCLUDE; else if (pmc->mca_sfcount[MCAST_INCLUDE]) pmc->mca_sfmode = MCAST_INCLUDE; /* else no filters; keep old mode for reports */ pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(idev); } else if (sf_setstate(pmc)) { mld_ifc_event(idev); } return err; } static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *nextpsf; mc_assert_locked(pmc->idev); for (psf = mc_dereference(pmc->mca_tomb, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (psf = mc_dereference(pmc->mca_sources, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_sources, NULL); pmc->mca_sfmode = MCAST_EXCLUDE; pmc->mca_sfcount[MCAST_INCLUDE] = 0; /* Paired with the READ_ONCE() from ipv6_chk_mcast_addr() */ WRITE_ONCE(pmc->mca_sfcount[MCAST_EXCLUDE], 1); } static void igmp6_join_group(struct ifmcaddr6 *ma) { unsigned long delay; mc_assert_locked(ma->idev); if (ma->mca_flags & MAF_NOREPORT) return; igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; } static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev) { struct ip6_sf_socklist *psl; int err; psl = sock_dereference(iml->sflist, sk); if (idev) mutex_lock(&idev->mc_lock); if (!psl) { /* any-source empty exclude case */ err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); } else { err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, psl->sl_count, psl->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } if (idev) mutex_unlock(&idev->mc_lock); return err; } static void igmp6_leave_group(struct ifmcaddr6 *ma) { mc_assert_locked(ma->idev); if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) { igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); } } else { mld_add_delrec(ma->idev, ma); mld_ifc_event(ma->idev); } } static void mld_gq_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_gq_work); mutex_lock(&idev->mc_lock); mld_send_report(idev, NULL); idev->mc_gq_running = 0; mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_ifc_work); mutex_lock(&idev->mc_lock); mld_send_cr(idev); if (idev->mc_ifc_count) { idev->mc_ifc_count--; if (idev->mc_ifc_count) mld_ifc_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_event(struct inet6_dev *idev) { mc_assert_locked(idev); if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_work(idev, 1); } static void mld_mca_work(struct work_struct *work) { struct ifmcaddr6 *ma = container_of(to_delayed_work(work), struct ifmcaddr6, mca_work); mutex_lock(&ma->idev->mc_lock); if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); ma->mca_flags |= MAF_LAST_REPORTER; ma->mca_flags &= ~MAF_TIMER_RUNNING; mutex_unlock(&ma->idev->mc_lock); ma_put(ma); } /* Device changing type */ void ipv6_mc_unmap(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); } void ipv6_mc_remap(struct inet6_dev *idev) { ipv6_mc_up(idev); } /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) { struct ifmcaddr6 *i; mutex_lock(&idev->mc_lock); /* Withdraw multicast list */ for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ mld_query_stop_work(idev); mld_report_stop_work(idev); mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); mutex_unlock(&idev->mc_lock); mld_dad_stop_work(idev); } static void ipv6_mc_reset(struct inet6_dev *idev) { idev->mc_qrv = sysctl_mld_qrv; idev->mc_qi = MLD_QI_DEFAULT; idev->mc_qri = MLD_QRI_DEFAULT; idev->mc_v1_seen = 0; idev->mc_maxdelay = unsolicited_report_interval(idev); } /* Device going up */ void ipv6_mc_up(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ ipv6_mc_reset(idev); mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) { mld_del_delrec(idev, i); igmp6_group_added(i); } mutex_unlock(&idev->mc_lock); } /* IPv6 device initialization. */ void ipv6_mc_init_dev(struct inet6_dev *idev) { idev->mc_gq_running = 0; INIT_DELAYED_WORK(&idev->mc_gq_work, mld_gq_work); RCU_INIT_POINTER(idev->mc_tomb, NULL); idev->mc_ifc_count = 0; INIT_DELAYED_WORK(&idev->mc_ifc_work, mld_ifc_work); INIT_DELAYED_WORK(&idev->mc_dad_work, mld_dad_work); INIT_DELAYED_WORK(&idev->mc_query_work, mld_query_work); INIT_DELAYED_WORK(&idev->mc_report_work, mld_report_work); skb_queue_head_init(&idev->mc_query_queue); skb_queue_head_init(&idev->mc_report_queue); spin_lock_init(&idev->mc_query_lock); spin_lock_init(&idev->mc_report_lock); mutex_init(&idev->mc_lock); ipv6_mc_reset(idev); } /* * Device is about to be destroyed: clean up. */ void ipv6_mc_destroy_dev(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Deactivate works */ ipv6_mc_down(idev); mutex_lock(&idev->mc_lock); mld_clear_delrec(idev); mutex_unlock(&idev->mc_lock); mld_clear_query(idev); mld_clear_report(idev); /* Delete all-nodes address. */ /* We cannot call ipv6_dev_mc_dec() directly, our caller in * addrconf.c has NULL'd out dev->ip6_ptr so in6_dev_get() will * fail. */ __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allnodes); if (idev->cnf.forwarding) __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allrouters); mutex_lock(&idev->mc_lock); while ((i = mc_dereference(idev->mc_list, idev))) { rcu_assign_pointer(idev->mc_list, mc_dereference(i->next, idev)); ip6_mc_clear_src(i); ma_put(i); } mutex_unlock(&idev->mc_lock); } static void ipv6_mc_rejoin_groups(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; mutex_lock(&idev->mc_lock); if (mld_in_v1_mode(idev)) { for_each_mc_mclock(idev, pmc) igmp6_join_group(pmc); } else { mld_send_report(idev, NULL); } mutex_unlock(&idev->mc_lock); } static int ipv6_mc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); switch (event) { case NETDEV_RESEND_IGMP: if (idev) ipv6_mc_rejoin_groups(idev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp6_netdev_notifier = { .notifier_call = ipv6_mc_netdev_event, }; #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; #define igmp6_mc_seq_private(seq) ((struct igmp6_mc_iter_state *)(seq)->private) static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) { struct ifmcaddr6 *im = NULL; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->mc_list); if (im) { state->idev = idev; break; } } return im; } static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr6 *im) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); im = rcu_dereference(im->next); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; im = rcu_dereference(state->idev->mc_list); } return im; } static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ifmcaddr6 *im = igmp6_mc_get_first(seq); if (im) while (pos && (im = igmp6_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) { struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags & MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_work.timer.expires - jiffies) : 0); return 0; } static const struct seq_operations igmp6_mc_seq_ops = { .start = igmp6_mc_seq_start, .next = igmp6_mc_seq_next, .stop = igmp6_mc_seq_stop, .show = igmp6_mc_seq_show, }; struct igmp6_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; struct ifmcaddr6 *im; }; #define igmp6_mcf_seq_private(seq) ((struct igmp6_mcf_iter_state *)(seq)->private) static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) { struct ip6_sf_list *psf = NULL; struct ifmcaddr6 *im = NULL; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { psf = rcu_dereference(im->mca_sources); if (likely(psf)) { state->im = im; state->idev = idev; break; } } } return psf; } static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_sf_list *psf) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); psf = rcu_dereference(psf->sf_next); while (!psf) { state->im = rcu_dereference(state->im->next); while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } psf = rcu_dereference(state->im->mca_sources); } out: return psf; } static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_sf_list *psf = igmp6_mcf_get_first(seq); if (psf) while (pos && (psf = igmp6_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp6_mcf_get_first(seq); else psf = igmp6_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im)) state->im = NULL; if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) { struct ip6_sf_list *psf = (struct ip6_sf_list *)v; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device Multicast Address Source Address INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, &state->im->mca_addr, &psf->sf_addr, READ_ONCE(psf->sf_count[MCAST_INCLUDE]), READ_ONCE(psf->sf_count[MCAST_EXCLUDE])); } return 0; } static const struct seq_operations igmp6_mcf_seq_ops = { .start = igmp6_mcf_seq_start, .next = igmp6_mcf_seq_next, .stop = igmp6_mcf_seq_stop, .show = igmp6_mcf_seq_show, }; static int __net_init igmp6_proc_init(struct net *net) { int err; err = -ENOMEM; if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops, sizeof(struct igmp6_mc_iter_state))) goto out; if (!proc_create_net("mcfilter6", 0444, net->proc_net, &igmp6_mcf_seq_ops, sizeof(struct igmp6_mcf_iter_state))) goto out_proc_net_igmp6; err = 0; out: return err; out_proc_net_igmp6: remove_proc_entry("igmp6", net->proc_net); goto out; } static void __net_exit igmp6_proc_exit(struct net *net) { remove_proc_entry("mcfilter6", net->proc_net); remove_proc_entry("igmp6", net->proc_net); } #else static inline int igmp6_proc_init(struct net *net) { return 0; } static inline void igmp6_proc_exit(struct net *net) { } #endif static int __net_init igmp6_net_init(struct net *net) { int err; err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); goto out; } inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; net->ipv6.igmp_sk->sk_allocation = GFP_KERNEL; err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", err); goto out_sock_create; } err = igmp6_proc_init(net); if (err) goto out_sock_create_autojoin; return 0; out_sock_create_autojoin: inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); out: return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, }; int __init igmp6_init(void) { int err; err = register_pernet_subsys(&igmp6_net_ops); if (err) return err; mld_wq = create_workqueue("mld"); if (!mld_wq) { unregister_pernet_subsys(&igmp6_net_ops); return -ENOMEM; } return err; } int __init igmp6_late_init(void) { return register_netdevice_notifier(&igmp6_netdev_notifier); } void igmp6_cleanup(void) { unregister_pernet_subsys(&igmp6_net_ops); destroy_workqueue(mld_wq); } void igmp6_late_cleanup(void) { unregister_netdevice_notifier(&igmp6_netdev_notifier); } |
| 43 43 43 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/ptrace.c * * By Ross Biro 1/23/92 * edited by Linus Torvalds * ARM modifications Copyright (C) 2000 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/audit.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/nospec.h> #include <linux/smp.h> #include <linux/ptrace.h> #include <linux/user.h> #include <linux/seccomp.h> #include <linux/security.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/regset.h> #include <linux/elf.h> #include <linux/rseq.h> #include <asm/compat.h> #include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/gcs.h> #include <asm/mte.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> #include <asm/syscall.h> #include <asm/traps.h> #include <asm/system_misc.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> struct pt_regs_offset { const char *name; int offset; }; #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} #define REG_OFFSET_END {.name = NULL, .offset = 0} #define GPR_OFFSET_NAME(r) \ {.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])} static const struct pt_regs_offset regoffset_table[] = { GPR_OFFSET_NAME(0), GPR_OFFSET_NAME(1), GPR_OFFSET_NAME(2), GPR_OFFSET_NAME(3), GPR_OFFSET_NAME(4), GPR_OFFSET_NAME(5), GPR_OFFSET_NAME(6), GPR_OFFSET_NAME(7), GPR_OFFSET_NAME(8), GPR_OFFSET_NAME(9), GPR_OFFSET_NAME(10), GPR_OFFSET_NAME(11), GPR_OFFSET_NAME(12), GPR_OFFSET_NAME(13), GPR_OFFSET_NAME(14), GPR_OFFSET_NAME(15), GPR_OFFSET_NAME(16), GPR_OFFSET_NAME(17), GPR_OFFSET_NAME(18), GPR_OFFSET_NAME(19), GPR_OFFSET_NAME(20), GPR_OFFSET_NAME(21), GPR_OFFSET_NAME(22), GPR_OFFSET_NAME(23), GPR_OFFSET_NAME(24), GPR_OFFSET_NAME(25), GPR_OFFSET_NAME(26), GPR_OFFSET_NAME(27), GPR_OFFSET_NAME(28), GPR_OFFSET_NAME(29), GPR_OFFSET_NAME(30), {.name = "lr", .offset = offsetof(struct pt_regs, regs[30])}, REG_OFFSET_NAME(sp), REG_OFFSET_NAME(pc), REG_OFFSET_NAME(pstate), REG_OFFSET_END, }; /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register * * regs_query_register_offset() returns the offset of a register in struct * pt_regs from its name. If the name is invalid, this returns -EINVAL; */ int regs_query_register_offset(const char *name) { const struct pt_regs_offset *roff; for (roff = regoffset_table; roff->name != NULL; roff++) if (!strcmp(roff->name, name)) return roff->offset; return -EINVAL; } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || on_irq_stack(addr, sizeof(unsigned long)); } /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack, * this returns 0. */ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return READ_ONCE_NOCHECK(*addr); else return 0; } /* * TODO: does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ /* * Called by kernel/ptrace.c when detaching.. */ void ptrace_disable(struct task_struct *child) { /* * This would be better off in core code, but PTRACE_DETACH has * grown its fair share of arch-specific worts and changing it * is likely to cause regressions on obscure architectures. */ user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * Handle hitting a HW-breakpoint. */ static void ptrace_hbptriggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); const char *desc = "Hardware breakpoint trap (ptrace)"; if (is_compat_task()) { int si_errno = 0; int i; for (i = 0; i < ARM_MAX_BRP; ++i) { if (current->thread.debug.hbp_break[i] == bp) { si_errno = (i << 1) + 1; break; } } for (i = 0; i < ARM_MAX_WRP; ++i) { if (current->thread.debug.hbp_watch[i] == bp) { si_errno = -((i << 1) + 1); break; } } arm64_force_sig_ptrace_errno_trap(si_errno, bkpt->trigger, desc); return; } arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } /* * Unregister breakpoints from this task and reset the pointers in * the thread_struct. */ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) { int i; struct thread_struct *t = &tsk->thread; for (i = 0; i < ARM_MAX_BRP; i++) { if (t->debug.hbp_break[i]) { unregister_hw_breakpoint(t->debug.hbp_break[i]); t->debug.hbp_break[i] = NULL; } } for (i = 0; i < ARM_MAX_WRP; i++) { if (t->debug.hbp_watch[i]) { unregister_hw_breakpoint(t->debug.hbp_watch[i]); t->debug.hbp_watch[i] = NULL; } } } void ptrace_hw_copy_thread(struct task_struct *tsk) { memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); } static struct perf_event *ptrace_hbp_get_event(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp = ERR_PTR(-EINVAL); switch (note_type) { case NT_ARM_HW_BREAK: if (idx >= ARM_MAX_BRP) goto out; idx = array_index_nospec(idx, ARM_MAX_BRP); bp = tsk->thread.debug.hbp_break[idx]; break; case NT_ARM_HW_WATCH: if (idx >= ARM_MAX_WRP) goto out; idx = array_index_nospec(idx, ARM_MAX_WRP); bp = tsk->thread.debug.hbp_watch[idx]; break; } out: return bp; } static int ptrace_hbp_set_event(unsigned int note_type, struct task_struct *tsk, unsigned long idx, struct perf_event *bp) { int err = -EINVAL; switch (note_type) { case NT_ARM_HW_BREAK: if (idx >= ARM_MAX_BRP) goto out; idx = array_index_nospec(idx, ARM_MAX_BRP); tsk->thread.debug.hbp_break[idx] = bp; err = 0; break; case NT_ARM_HW_WATCH: if (idx >= ARM_MAX_WRP) goto out; idx = array_index_nospec(idx, ARM_MAX_WRP); tsk->thread.debug.hbp_watch[idx] = bp; err = 0; break; } out: return err; } static struct perf_event *ptrace_hbp_create(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp; struct perf_event_attr attr; int err, type; switch (note_type) { case NT_ARM_HW_BREAK: type = HW_BREAKPOINT_X; break; case NT_ARM_HW_WATCH: type = HW_BREAKPOINT_RW; break; default: return ERR_PTR(-EINVAL); } ptrace_breakpoint_init(&attr); /* * Initialise fields to sane defaults * (i.e. values that will pass validation). */ attr.bp_addr = 0; attr.bp_len = HW_BREAKPOINT_LEN_4; attr.bp_type = type; attr.disabled = 1; bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk); if (IS_ERR(bp)) return bp; err = ptrace_hbp_set_event(note_type, tsk, idx, bp); if (err) return ERR_PTR(err); return bp; } static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { int err, len, type, offset, disabled = !ctrl.enabled; attr->disabled = disabled; if (disabled) return 0; err = arch_bp_generic_fields(ctrl, &len, &type, &offset); if (err) return err; switch (note_type) { case NT_ARM_HW_BREAK: if ((type & HW_BREAKPOINT_X) != type) return -EINVAL; break; case NT_ARM_HW_WATCH: if ((type & HW_BREAKPOINT_RW) != type) return -EINVAL; break; default: return -EINVAL; } attr->bp_len = len; attr->bp_type = type; attr->bp_addr += offset; return 0; } static int ptrace_hbp_get_resource_info(unsigned int note_type, u32 *info) { u8 num; u32 reg = 0; switch (note_type) { case NT_ARM_HW_BREAK: num = hw_breakpoint_slots(TYPE_INST); break; case NT_ARM_HW_WATCH: num = hw_breakpoint_slots(TYPE_DATA); break; default: return -EINVAL; } reg |= debug_monitors_arch(); reg <<= 8; reg |= num; *info = reg; return 0; } static int ptrace_hbp_get_ctrl(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u32 *ctrl) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); *ctrl = bp ? encode_ctrl_reg(counter_arch_bp(bp)->ctrl) : 0; return 0; } static int ptrace_hbp_get_addr(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u64 *addr) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); *addr = bp ? counter_arch_bp(bp)->address : 0; return 0; } static struct perf_event *ptrace_hbp_get_initialised_bp(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (!bp) bp = ptrace_hbp_create(note_type, tsk, idx); return bp; } static int ptrace_hbp_set_ctrl(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u32 uctrl) { int err; struct perf_event *bp; struct perf_event_attr attr; struct arch_hw_breakpoint_ctrl ctrl; bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) { err = PTR_ERR(bp); return err; } attr = bp->attr; decode_ctrl_reg(uctrl, &ctrl); err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); if (err) return err; return modify_user_hw_breakpoint(bp, &attr); } static int ptrace_hbp_set_addr(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u64 addr) { int err; struct perf_event *bp; struct perf_event_attr attr; bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) { err = PTR_ERR(bp); return err; } attr = bp->attr; attr.bp_addr = addr; err = modify_user_hw_breakpoint(bp, &attr); return err; } #define PTRACE_HBP_ADDR_SZ sizeof(u64) #define PTRACE_HBP_CTRL_SZ sizeof(u32) #define PTRACE_HBP_PAD_SZ sizeof(u32) static int hw_break_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { unsigned int note_type = regset->core_note_type; int ret, idx = 0; u32 info, ctrl; u64 addr; /* Resource info */ ret = ptrace_hbp_get_resource_info(note_type, &info); if (ret) return ret; membuf_write(&to, &info, sizeof(info)); membuf_zero(&to, sizeof(u32)); /* (address, ctrl) registers */ while (to.left) { ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); if (ret) return ret; ret = ptrace_hbp_get_ctrl(note_type, target, idx, &ctrl); if (ret) return ret; membuf_store(&to, addr); membuf_store(&to, ctrl); membuf_zero(&to, sizeof(u32)); idx++; } return 0; } static int hw_break_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { unsigned int note_type = regset->core_note_type; int ret, idx = 0, offset, limit; u32 ctrl; u64 addr; /* Resource info and pad */ offset = offsetof(struct user_hwdebug_state, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); /* (address, ctrl) registers */ limit = regset->n * regset->size; while (count && offset < limit) { if (count < PTRACE_HBP_ADDR_SZ) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, offset, offset + PTRACE_HBP_ADDR_SZ); if (ret) return ret; ret = ptrace_hbp_set_addr(note_type, target, idx, addr); if (ret) return ret; offset += PTRACE_HBP_ADDR_SZ; if (!count) break; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, offset, offset + PTRACE_HBP_CTRL_SZ); if (ret) return ret; ret = ptrace_hbp_set_ctrl(note_type, target, idx, ctrl); if (ret) return ret; offset += PTRACE_HBP_CTRL_SZ; user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, offset, offset + PTRACE_HBP_PAD_SZ); offset += PTRACE_HBP_PAD_SZ; idx++; } return 0; } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ static int gpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_pt_regs *uregs = &task_pt_regs(target)->user_regs; return membuf_write(&to, uregs, sizeof(*uregs)); } static int gpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_pt_regs newregs = task_pt_regs(target)->user_regs; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1); if (ret) return ret; if (!valid_user_regs(&newregs, target)) return -EINVAL; task_pt_regs(target)->user_regs = newregs; return 0; } static int fpr_active(struct task_struct *target, const struct user_regset *regset) { if (!system_supports_fpsimd()) return -ENODEV; return regset->n; } /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ static int __fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_fpsimd_state *uregs; fpsimd_sync_from_effective_state(target); uregs = &target->thread.uw.fpsimd_state; return membuf_write(&to, uregs, sizeof(*uregs)); } static int fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_fpsimd()) return -EINVAL; if (target == current) fpsimd_preserve_current_state(); return __fpr_get(target, regset, to); } static int __fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf, unsigned int start_pos) { int ret; struct user_fpsimd_state newstate; /* * Ensure target->thread.uw.fpsimd_state is up to date, so that a * short copyin can't resurrect stale data. */ fpsimd_sync_from_effective_state(target); newstate = target->thread.uw.fpsimd_state; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, start_pos, start_pos + sizeof(newstate)); if (ret) return ret; target->thread.uw.fpsimd_state = newstate; return ret; } static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; if (!system_supports_fpsimd()) return -EINVAL; ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; fpsimd_sync_to_effective_state_zeropad(target); fpsimd_flush_task_state(target); return ret; } static int tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int ret; if (target == current) tls_preserve_current_state(); ret = membuf_store(&to, target->thread.uw.tp_value); if (system_supports_tpidr2()) ret = membuf_store(&to, target->thread.tpidr2_el0); else ret = membuf_zero(&to, sizeof(u64)); return ret; } static int tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; unsigned long tls[2]; tls[0] = target->thread.uw.tp_value; if (system_supports_tpidr2()) tls[1] = target->thread.tpidr2_el0; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count); if (ret) return ret; target->thread.uw.tp_value = tls[0]; if (system_supports_tpidr2()) target->thread.tpidr2_el0 = tls[1]; return ret; } static int fpmr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_fpmr()) return -EINVAL; if (target == current) fpsimd_preserve_current_state(); return membuf_store(&to, target->thread.uw.fpmr); } static int fpmr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; unsigned long fpmr; if (!system_supports_fpmr()) return -EINVAL; fpmr = target->thread.uw.fpmr; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); if (ret) return ret; target->thread.uw.fpmr = fpmr; fpsimd_flush_task_state(target); return 0; } static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { return membuf_store(&to, task_pt_regs(target)->syscallno); } static int system_call_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int syscallno = task_pt_regs(target)->syscallno; int ret; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1); if (ret) return ret; task_pt_regs(target)->syscallno = syscallno; return ret; } #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, struct task_struct *target, enum vec_type type) { unsigned int vq; bool active; enum vec_type task_type; memset(header, 0, sizeof(*header)); /* Check if the requested registers are active for the task */ if (thread_sm_enabled(&target->thread)) task_type = ARM64_VEC_SME; else task_type = ARM64_VEC_SVE; active = (task_type == type); if (active && target->thread.fp_type == FP_STATE_SVE) header->flags = SVE_PT_REGS_SVE; else header->flags = SVE_PT_REGS_FPSIMD; switch (type) { case ARM64_VEC_SVE: if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; break; case ARM64_VEC_SME: if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; break; default: WARN_ON_ONCE(1); return; } header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); header->max_vl = vec_max_vl(type); if (active) header->size = SVE_PT_SIZE(vq, header->flags); else header->size = sizeof(header); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); } static unsigned int sve_size_from_header(struct user_sve_header const *header) { return ALIGN(header->size, SVE_VQ_BYTES); } static int sve_get_common(struct task_struct *target, const struct user_regset *regset, struct membuf to, enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end; if (target == current) fpsimd_preserve_current_state(); /* Header */ sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); /* * When the requested vector type is not active, do not present data * from the other mode to userspace. */ if (header.size == sizeof(header)) return 0; switch ((header.flags & SVE_PT_REGS_MASK)) { case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); case SVE_PT_REGS_SVE: start = SVE_PT_SVE_OFFSET; end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); membuf_write(&to, target->thread.sve_state, end - start); start = end; end = SVE_PT_SVE_FPSR_OFFSET(vq); membuf_zero(&to, end - start); /* * Copy fpsr, and fpcr which must follow contiguously in * struct fpsimd_state: */ start = end; end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); start = end; end = sve_size_from_header(&header); return membuf_zero(&to, end - start); default: BUILD_BUG(); } } static int sve_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sve()) return -EINVAL; return sve_get_common(target, regset, to, ARM64_VEC_SVE); } static int sve_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf, enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end; bool fpsimd; fpsimd_flush_task_state(target); /* Header */ if (count < sizeof(header)) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, 0, sizeof(header)); if (ret) return ret; /* * Streaming SVE data is always stored and presented in SVE format. * Require the user to provide SVE formatted data for consistency, and * to avoid the risk that we configure the task into an invalid state. */ fpsimd = (header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD; if (fpsimd && type == ARM64_VEC_SME) return -EINVAL; /* * On systems without SVE we accept FPSIMD format writes with * a VL of 0 to allow exiting streaming mode, otherwise a VL * is required. */ if (header.vl) { /* * If the system does not support SVE we can't * configure a SVE VL. */ if (!system_supports_sve() && type == ARM64_VEC_SVE) return -EINVAL; /* * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are * consumed by vec_set_vector_length(), which will * also validate them for us: */ ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) return ret; } else { /* If the system supports SVE we require a VL. */ if (system_supports_sve()) return -EINVAL; /* * Only FPSIMD formatted data with no flags set is * supported. */ if (header.flags != SVE_PT_REGS_FPSIMD) return -EINVAL; } /* Allocate SME storage if necessary, preserving any existing ZA/ZT state */ if (type == ARM64_VEC_SME) { sme_alloc(target, false); if (!target->thread.sme_state) return -ENOMEM; } /* Allocate SVE storage if necessary, zeroing any existing SVE state */ if (!fpsimd) { sve_alloc(target, true); if (!target->thread.sve_state) return -ENOMEM; } /* * Actual VL set may be different from what the user asked * for, or we may have configured the _ONEXEC VL not the * current VL: */ vq = sve_vq_from_vl(task_get_vl(target, type)); /* Enter/exit streaming mode */ switch (type) { case ARM64_VEC_SVE: target->thread.svcr &= ~SVCR_SM_MASK; set_tsk_thread_flag(target, TIF_SVE); break; case ARM64_VEC_SME: target->thread.svcr |= SVCR_SM_MASK; set_tsk_thread_flag(target, TIF_SME); break; default: WARN_ON_ONCE(1); return -EINVAL; } /* Always zero V regs, FPSR, and FPCR */ memset(¤t->thread.uw.fpsimd_state, 0, sizeof(current->thread.uw.fpsimd_state)); /* Registers: FPSIMD-only case */ BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); if (fpsimd) { clear_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_FPSIMD; ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); return ret; } /* Otherwise: no registers or full SVE case. */ target->thread.fp_type = FP_STATE_SVE; /* * If setting a different VL from the requested VL and there is * register data, the data layout will be wrong: don't even * try to set the registers in this case. */ if (count && vq != sve_vq_from_vl(header.vl)) return -EIO; BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); start = SVE_PT_SVE_OFFSET; end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, target->thread.sve_state, start, end); if (ret) return ret; start = end; end = SVE_PT_SVE_FPSR_OFFSET(vq); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, start, end); /* * Copy fpsr, and fpcr which must follow contiguously in * struct fpsimd_state: */ start = end; end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.uw.fpsimd_state.fpsr, start, end); return ret; } static int sve_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { if (!system_supports_sve() && !system_supports_sme()) return -EINVAL; return sve_set_common(target, regset, pos, count, kbuf, ubuf, ARM64_VEC_SVE); } #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int ssve_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sme()) return -EINVAL; return sve_get_common(target, regset, to, ARM64_VEC_SME); } static int ssve_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { if (!system_supports_sme()) return -EINVAL; return sve_set_common(target, regset, pos, count, kbuf, ubuf, ARM64_VEC_SME); } static int za_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_za_header header; unsigned int vq; unsigned long start, end; if (!system_supports_sme()) return -EINVAL; /* Header */ memset(&header, 0, sizeof(header)); if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header.flags |= ZA_PT_VL_INHERIT; header.vl = task_get_sme_vl(target); vq = sve_vq_from_vl(header.vl); header.max_vl = sme_max_vl(); header.max_size = ZA_PT_SIZE(vq); /* If ZA is not active there is only the header */ if (thread_za_enabled(&target->thread)) header.size = ZA_PT_SIZE(vq); else header.size = ZA_PT_ZA_OFFSET; membuf_write(&to, &header, sizeof(header)); BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); end = ZA_PT_ZA_OFFSET; if (target == current) fpsimd_preserve_current_state(); /* Any register data to include? */ if (thread_za_enabled(&target->thread)) { start = end; end = ZA_PT_SIZE(vq); membuf_write(&to, target->thread.sme_state, end - start); } /* Zero any trailing padding */ start = end; end = ALIGN(header.size, SVE_VQ_BYTES); return membuf_zero(&to, end - start); } static int za_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_za_header header; unsigned int vq; unsigned long start, end; if (!system_supports_sme()) return -EINVAL; /* Header */ if (count < sizeof(header)) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, 0, sizeof(header)); if (ret) goto out; /* * All current ZA_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for * us: */ ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, ((unsigned long)header.flags) << 16); if (ret) goto out; /* * Actual VL set may be different from what the user asked * for, or we may have configured the _ONEXEC rather than * current VL: */ vq = sve_vq_from_vl(task_get_sme_vl(target)); /* Ensure there is some SVE storage for streaming mode */ if (!target->thread.sve_state) { sve_alloc(target, false); if (!target->thread.sve_state) { ret = -ENOMEM; goto out; } } /* * Only flush the storage if PSTATE.ZA was not already set, * otherwise preserve any existing data. */ sme_alloc(target, !thread_za_enabled(&target->thread)); if (!target->thread.sme_state) return -ENOMEM; /* If there is no data then disable ZA */ if (!count) { target->thread.svcr &= ~SVCR_ZA_MASK; goto out; } /* * If setting a different VL from the requested VL and there is * register data, the data layout will be wrong: don't even * try to set the registers in this case. */ if (vq != sve_vq_from_vl(header.vl)) { ret = -EIO; goto out; } BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); start = ZA_PT_ZA_OFFSET; end = ZA_PT_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, target->thread.sme_state, start, end); if (ret) goto out; /* Mark ZA as active and let userspace use it */ set_tsk_thread_flag(target, TIF_SME); target->thread.svcr |= SVCR_ZA_MASK; out: fpsimd_flush_task_state(target); return ret; } static int zt_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sme2()) return -EINVAL; /* * If PSTATE.ZA is not set then ZT will be zeroed when it is * enabled so report the current register value as zero. */ if (thread_za_enabled(&target->thread)) membuf_write(&to, thread_zt_state(&target->thread), ZT_SIG_REG_BYTES); else membuf_zero(&to, ZT_SIG_REG_BYTES); return 0; } static int zt_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; if (!system_supports_sme2()) return -EINVAL; /* Ensure SVE storage in case this is first use of SME */ sve_alloc(target, false); if (!target->thread.sve_state) return -ENOMEM; if (!thread_za_enabled(&target->thread)) { sme_alloc(target, true); if (!target->thread.sme_state) return -ENOMEM; } ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, thread_zt_state(&target->thread), 0, ZT_SIG_REG_BYTES); if (ret == 0) { target->thread.svcr |= SVCR_ZA_MASK; set_tsk_thread_flag(target, TIF_SME); } fpsimd_flush_task_state(target); return ret; } #endif /* CONFIG_ARM64_SME */ #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { /* * The PAC bits can differ across data and instruction pointers * depending on TCR_EL1.TBID*, which we may make use of in future, so * we expose separate masks. */ unsigned long mask = ptrauth_user_pac_mask(); struct user_pac_mask uregs = { .data_mask = mask, .insn_mask = mask, }; if (!system_supports_address_auth()) return -EINVAL; return membuf_write(&to, &uregs, sizeof(uregs)); } static int pac_enabled_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { long enabled_keys = ptrauth_get_enabled_keys(target); if (IS_ERR_VALUE(enabled_keys)) return enabled_keys; return membuf_write(&to, &enabled_keys, sizeof(enabled_keys)); } static int pac_enabled_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long enabled_keys = ptrauth_get_enabled_keys(target); if (IS_ERR_VALUE(enabled_keys)) return enabled_keys; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &enabled_keys, 0, sizeof(long)); if (ret) return ret; return ptrauth_set_enabled_keys(target, PR_PAC_ENABLED_KEYS_MASK, enabled_keys); } #ifdef CONFIG_CHECKPOINT_RESTORE static __uint128_t pac_key_to_user(const struct ptrauth_key *key) { return (__uint128_t)key->hi << 64 | key->lo; } static struct ptrauth_key pac_key_from_user(__uint128_t ukey) { struct ptrauth_key key = { .lo = (unsigned long)ukey, .hi = (unsigned long)(ukey >> 64), }; return key; } static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, const struct ptrauth_keys_user *keys) { ukeys->apiakey = pac_key_to_user(&keys->apia); ukeys->apibkey = pac_key_to_user(&keys->apib); ukeys->apdakey = pac_key_to_user(&keys->apda); ukeys->apdbkey = pac_key_to_user(&keys->apdb); } static void pac_address_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_address_keys *ukeys) { keys->apia = pac_key_from_user(ukeys->apiakey); keys->apib = pac_key_from_user(ukeys->apibkey); keys->apda = pac_key_from_user(ukeys->apdakey); keys->apdb = pac_key_from_user(ukeys->apdbkey); } static int pac_address_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; if (!system_supports_address_auth()) return -EINVAL; pac_address_keys_to_user(&user_keys, keys); return membuf_write(&to, &user_keys, sizeof(user_keys)); } static int pac_address_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; int ret; if (!system_supports_address_auth()) return -EINVAL; pac_address_keys_to_user(&user_keys, keys); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_keys, 0, -1); if (ret) return ret; pac_address_keys_from_user(keys, &user_keys); return 0; } static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, const struct ptrauth_keys_user *keys) { ukeys->apgakey = pac_key_to_user(&keys->apga); } static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_generic_keys *ukeys) { keys->apga = pac_key_from_user(ukeys->apgakey); } static int pac_generic_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; if (!system_supports_generic_auth()) return -EINVAL; pac_generic_keys_to_user(&user_keys, keys); return membuf_write(&to, &user_keys, sizeof(user_keys)); } static int pac_generic_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; int ret; if (!system_supports_generic_auth()) return -EINVAL; pac_generic_keys_to_user(&user_keys, keys); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_keys, 0, -1); if (ret) return ret; pac_generic_keys_from_user(keys, &user_keys); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI static int tagged_addr_ctrl_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { long ctrl = get_tagged_addr_ctrl(target); if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl))) return ctrl; return membuf_write(&to, &ctrl, sizeof(ctrl)); } static int tagged_addr_ctrl_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long ctrl; ctrl = get_tagged_addr_ctrl(target); if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl))) return ctrl; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); if (ret) return ret; return set_tagged_addr_ctrl(target, ctrl); } #endif #ifdef CONFIG_ARM64_POE static int poe_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_poe()) return -EINVAL; if (target == current) current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0); return membuf_write(&to, &target->thread.por_el0, sizeof(target->thread.por_el0)); } static int poe_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long ctrl; if (!system_supports_poe()) return -EINVAL; ctrl = target->thread.por_el0; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); if (ret) return ret; target->thread.por_el0 = ctrl; return 0; } #endif #ifdef CONFIG_ARM64_GCS static void task_gcs_to_user(struct user_gcs *user_gcs, const struct task_struct *target) { user_gcs->features_enabled = target->thread.gcs_el0_mode; user_gcs->features_locked = target->thread.gcs_el0_locked; user_gcs->gcspr_el0 = target->thread.gcspr_el0; } static void task_gcs_from_user(struct task_struct *target, const struct user_gcs *user_gcs) { target->thread.gcs_el0_mode = user_gcs->features_enabled; target->thread.gcs_el0_locked = user_gcs->features_locked; target->thread.gcspr_el0 = user_gcs->gcspr_el0; } static int gcs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_gcs user_gcs; if (!system_supports_gcs()) return -EINVAL; if (target == current) gcs_preserve_current_state(); task_gcs_to_user(&user_gcs, target); return membuf_write(&to, &user_gcs, sizeof(user_gcs)); } static int gcs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_gcs user_gcs; if (!system_supports_gcs()) return -EINVAL; task_gcs_to_user(&user_gcs, target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1); if (ret) return ret; if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) return -EINVAL; task_gcs_from_user(target, &user_gcs); return 0; } #endif enum aarch64_regset { REGSET_GPR, REGSET_FPR, REGSET_TLS, #ifdef CONFIG_HAVE_HW_BREAKPOINT REGSET_HW_BREAK, REGSET_HW_WATCH, #endif REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif #ifdef CONFIG_ARM64_SME REGSET_SSVE, REGSET_ZA, REGSET_ZT, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, #ifdef CONFIG_CHECKPOINT_RESTORE REGSET_PACA_KEYS, REGSET_PACG_KEYS, #endif #endif #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif #ifdef CONFIG_ARM64_POE REGSET_POE, #endif #ifdef CONFIG_ARM64_GCS REGSET_GCS, #endif }; static const struct user_regset aarch64_regsets[] = { [REGSET_GPR] = { USER_REGSET_NOTE_TYPE(PRSTATUS), .n = sizeof(struct user_pt_regs) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = gpr_get, .set = gpr_set }, [REGSET_FPR] = { USER_REGSET_NOTE_TYPE(PRFPREG), .n = sizeof(struct user_fpsimd_state) / sizeof(u32), /* * We pretend we have 32-bit registers because the fpsr and * fpcr are 32-bits wide. */ .size = sizeof(u32), .align = sizeof(u32), .active = fpr_active, .regset_get = fpr_get, .set = fpr_set }, [REGSET_TLS] = { USER_REGSET_NOTE_TYPE(ARM_TLS), .n = 2, .size = sizeof(void *), .align = sizeof(void *), .regset_get = tls_get, .set = tls_set, }, #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { USER_REGSET_NOTE_TYPE(ARM_HW_BREAK), .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { USER_REGSET_NOTE_TYPE(ARM_HW_WATCH), .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, #endif [REGSET_SYSTEM_CALL] = { USER_REGSET_NOTE_TYPE(ARM_SYSTEM_CALL), .n = 1, .size = sizeof(int), .align = sizeof(int), .regset_get = system_call_get, .set = system_call_set, }, [REGSET_FPMR] = { USER_REGSET_NOTE_TYPE(ARM_FPMR), .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = fpmr_get, .set = fpmr_set, }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ USER_REGSET_NOTE_TYPE(ARM_SVE), .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX, SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = sve_get, .set = sve_set, }, #endif #ifdef CONFIG_ARM64_SME [REGSET_SSVE] = { /* Streaming mode SVE */ USER_REGSET_NOTE_TYPE(ARM_SSVE), .n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = ssve_get, .set = ssve_set, }, [REGSET_ZA] = { /* SME ZA */ USER_REGSET_NOTE_TYPE(ARM_ZA), /* * ZA is a single register but it's variably sized and * the ptrace core requires that the size of any data * be an exact multiple of the configured register * size so report as though we had SVE_VQ_BYTES * registers. These values aren't exposed to * userspace. */ .n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = za_get, .set = za_set, }, [REGSET_ZT] = { /* SME ZT */ USER_REGSET_NOTE_TYPE(ARM_ZT), .n = 1, .size = ZT_SIG_REG_BYTES, .align = sizeof(u64), .regset_get = zt_get, .set = zt_set, }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { USER_REGSET_NOTE_TYPE(ARM_PAC_MASK), .n = sizeof(struct user_pac_mask) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = pac_mask_get, /* this cannot be set dynamically */ }, [REGSET_PAC_ENABLED_KEYS] = { USER_REGSET_NOTE_TYPE(ARM_PAC_ENABLED_KEYS), .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = pac_enabled_keys_get, .set = pac_enabled_keys_set, }, #ifdef CONFIG_CHECKPOINT_RESTORE [REGSET_PACA_KEYS] = { USER_REGSET_NOTE_TYPE(ARM_PACA_KEYS), .n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t), .size = sizeof(__uint128_t), .align = sizeof(__uint128_t), .regset_get = pac_address_keys_get, .set = pac_address_keys_set, }, [REGSET_PACG_KEYS] = { USER_REGSET_NOTE_TYPE(ARM_PACG_KEYS), .n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t), .size = sizeof(__uint128_t), .align = sizeof(__uint128_t), .regset_get = pac_generic_keys_get, .set = pac_generic_keys_set, }, #endif #endif #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI [REGSET_TAGGED_ADDR_CTRL] = { USER_REGSET_NOTE_TYPE(ARM_TAGGED_ADDR_CTRL), .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = tagged_addr_ctrl_get, .set = tagged_addr_ctrl_set, }, #endif #ifdef CONFIG_ARM64_POE [REGSET_POE] = { USER_REGSET_NOTE_TYPE(ARM_POE), .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = poe_get, .set = poe_set, }, #endif #ifdef CONFIG_ARM64_GCS [REGSET_GCS] = { USER_REGSET_NOTE_TYPE(ARM_GCS), .n = sizeof(struct user_gcs) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = gcs_get, .set = gcs_set, }, #endif }; static const struct user_regset_view user_aarch64_view = { .name = "aarch64", .e_machine = EM_AARCH64, .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; enum compat_regset { REGSET_COMPAT_GPR, REGSET_COMPAT_VFP, }; static inline compat_ulong_t compat_get_user_reg(struct task_struct *task, int idx) { struct pt_regs *regs = task_pt_regs(task); switch (idx) { case 15: return regs->pc; case 16: return pstate_to_compat_psr(regs->pstate); case 17: return regs->orig_x0; default: return regs->regs[idx]; } } static int compat_gpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int i = 0; while (to.left) membuf_store(&to, compat_get_user_reg(target, i++)); return 0; } static int compat_gpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct pt_regs newregs; int ret = 0; unsigned int i, start, num_regs; /* Calculate the number of AArch32 registers contained in count */ num_regs = count / regset->size; /* Convert pos into an register number */ start = pos / regset->size; if (start + num_regs > regset->n) return -EIO; newregs = *task_pt_regs(target); for (i = 0; i < num_regs; ++i) { unsigned int idx = start + i; compat_ulong_t reg; if (kbuf) { memcpy(®, kbuf, sizeof(reg)); kbuf += sizeof(reg); } else { ret = copy_from_user(®, ubuf, sizeof(reg)); if (ret) { ret = -EFAULT; break; } ubuf += sizeof(reg); } switch (idx) { case 15: newregs.pc = reg; break; case 16: reg = compat_psr_to_pstate(reg); newregs.pstate = reg; break; case 17: newregs.orig_x0 = reg; break; default: newregs.regs[idx] = reg; } } if (valid_user_regs(&newregs.user_regs, target)) *task_pt_regs(target) = newregs; else ret = -EINVAL; return ret; } static int compat_vfp_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_fpsimd_state *uregs; compat_ulong_t fpscr; if (!system_supports_fpsimd()) return -EINVAL; uregs = &target->thread.uw.fpsimd_state; if (target == current) fpsimd_preserve_current_state(); /* * The VFP registers are packed into the fpsimd_state, so they all sit * nicely together for us. We just need to create the fpscr separately. */ membuf_write(&to, uregs, VFP_STATE_SIZE - sizeof(compat_ulong_t)); fpscr = (uregs->fpsr & VFP_FPSCR_STAT_MASK) | (uregs->fpcr & VFP_FPSCR_CTRL_MASK); return membuf_store(&to, fpscr); } static int compat_vfp_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct user_fpsimd_state *uregs; compat_ulong_t fpscr; int ret, vregs_end_pos; if (!system_supports_fpsimd()) return -EINVAL; uregs = &target->thread.uw.fpsimd_state; vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, vregs_end_pos); if (count && !ret) { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpscr, vregs_end_pos, VFP_STATE_SIZE); if (!ret) { uregs->fpsr = fpscr & VFP_FPSCR_STAT_MASK; uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK; } } fpsimd_flush_task_state(target); return ret; } static int compat_tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { return membuf_store(&to, (compat_ulong_t)target->thread.uw.tp_value); } static int compat_tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; compat_ulong_t tls = target->thread.uw.tp_value; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); if (ret) return ret; target->thread.uw.tp_value = tls; return ret; } static const struct user_regset aarch32_regsets[] = { [REGSET_COMPAT_GPR] = { USER_REGSET_NOTE_TYPE(PRSTATUS), .n = COMPAT_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .regset_get = compat_gpr_get, .set = compat_gpr_set }, [REGSET_COMPAT_VFP] = { USER_REGSET_NOTE_TYPE(ARM_VFP), .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .active = fpr_active, .regset_get = compat_vfp_get, .set = compat_vfp_set }, }; static const struct user_regset_view user_aarch32_view = { .name = "aarch32", .e_machine = EM_ARM, .regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets) }; static const struct user_regset aarch32_ptrace_regsets[] = { [REGSET_GPR] = { USER_REGSET_NOTE_TYPE(PRSTATUS), .n = COMPAT_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .regset_get = compat_gpr_get, .set = compat_gpr_set }, [REGSET_FPR] = { USER_REGSET_NOTE_TYPE(ARM_VFP), .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .regset_get = compat_vfp_get, .set = compat_vfp_set }, [REGSET_TLS] = { USER_REGSET_NOTE_TYPE(ARM_TLS), .n = 1, .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .regset_get = compat_tls_get, .set = compat_tls_set, }, #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { USER_REGSET_NOTE_TYPE(ARM_HW_BREAK), .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { USER_REGSET_NOTE_TYPE(ARM_HW_WATCH), .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, #endif [REGSET_SYSTEM_CALL] = { USER_REGSET_NOTE_TYPE(ARM_SYSTEM_CALL), .n = 1, .size = sizeof(int), .align = sizeof(int), .regset_get = system_call_get, .set = system_call_set, }, }; static const struct user_regset_view user_aarch32_ptrace_view = { .name = "aarch32", .e_machine = EM_ARM, .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) }; #ifdef CONFIG_COMPAT static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { compat_ulong_t tmp; if (off & 3) return -EIO; if (off == COMPAT_PT_TEXT_ADDR) tmp = tsk->mm->start_code; else if (off == COMPAT_PT_DATA_ADDR) tmp = tsk->mm->start_data; else if (off == COMPAT_PT_TEXT_END_ADDR) tmp = tsk->mm->end_code; else if (off < sizeof(compat_elf_gregset_t)) tmp = compat_get_user_reg(tsk, off >> 2); else if (off >= COMPAT_USER_SZ) return -EIO; else tmp = 0; return put_user(tmp, ret); } static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t val) { struct pt_regs newregs = *task_pt_regs(tsk); unsigned int idx = off / 4; if (off & 3 || off >= COMPAT_USER_SZ) return -EIO; if (off >= sizeof(compat_elf_gregset_t)) return 0; switch (idx) { case 15: newregs.pc = val; break; case 16: newregs.pstate = compat_psr_to_pstate(val); break; case 17: newregs.orig_x0 = val; break; default: newregs.regs[idx] = val; } if (!valid_user_regs(&newregs.user_regs, tsk)) return -EINVAL; *task_pt_regs(tsk) = newregs; return 0; } #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * Convert a virtual register number into an index for a thread_info * breakpoint array. Breakpoints are identified using positive numbers * whilst watchpoints are negative. The registers are laid out as pairs * of (address, control), each pair mapping to a unique hw_breakpoint struct. * Register 0 is reserved for describing resource information. */ static int compat_ptrace_hbp_num_to_idx(compat_long_t num) { return (abs(num) - 1) >> 1; } static int compat_ptrace_hbp_get_resource_info(u32 *kdata) { u8 num_brps, num_wrps, debug_arch, wp_len; u32 reg = 0; num_brps = hw_breakpoint_slots(TYPE_INST); num_wrps = hw_breakpoint_slots(TYPE_DATA); debug_arch = debug_monitors_arch(); wp_len = 8; reg |= debug_arch; reg <<= 8; reg |= wp_len; reg <<= 8; reg |= num_wrps; reg <<= 8; reg |= num_brps; *kdata = reg; return 0; } static int compat_ptrace_hbp_get(unsigned int note_type, struct task_struct *tsk, compat_long_t num, u32 *kdata) { u64 addr = 0; u32 ctrl = 0; int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { err = ptrace_hbp_get_addr(note_type, tsk, idx, &addr); *kdata = (u32)addr; } else { err = ptrace_hbp_get_ctrl(note_type, tsk, idx, &ctrl); *kdata = ctrl; } return err; } static int compat_ptrace_hbp_set(unsigned int note_type, struct task_struct *tsk, compat_long_t num, u32 *kdata) { u64 addr; u32 ctrl; int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { addr = *kdata; err = ptrace_hbp_set_addr(note_type, tsk, idx, addr); } else { ctrl = *kdata; err = ptrace_hbp_set_ctrl(note_type, tsk, idx, ctrl); } return err; } static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num, compat_ulong_t __user *data) { int ret; u32 kdata; /* Watchpoint */ if (num < 0) { ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata); /* Resource info */ } else if (num == 0) { ret = compat_ptrace_hbp_get_resource_info(&kdata); /* Breakpoint */ } else { ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata); } if (!ret) ret = put_user(kdata, data); return ret; } static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num, compat_ulong_t __user *data) { int ret; u32 kdata = 0; if (num == 0) return 0; ret = get_user(kdata, data); if (ret) return ret; if (num < 0) ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata); else ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata); return ret; } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { unsigned long addr = caddr; unsigned long data = cdata; void __user *datap = compat_ptr(data); int ret; switch (request) { case PTRACE_PEEKUSR: ret = compat_ptrace_read_user(child, addr, datap); break; case PTRACE_POKEUSR: ret = compat_ptrace_write_user(child, addr, data); break; case COMPAT_PTRACE_GETREGS: ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, 0, sizeof(compat_elf_gregset_t), datap); break; case COMPAT_PTRACE_SETREGS: ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, 0, sizeof(compat_elf_gregset_t), datap); break; case COMPAT_PTRACE_GET_THREAD_AREA: ret = put_user((compat_ulong_t)child->thread.uw.tp_value, (compat_ulong_t __user *)datap); break; case COMPAT_PTRACE_SET_SYSCALL: task_pt_regs(child)->syscallno = data; ret = 0; break; case COMPAT_PTRACE_GETVFPREGS: ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_VFP, 0, VFP_STATE_SIZE, datap); break; case COMPAT_PTRACE_SETVFPREGS: ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_VFP, 0, VFP_STATE_SIZE, datap); break; #ifdef CONFIG_HAVE_HW_BREAKPOINT case COMPAT_PTRACE_GETHBPREGS: ret = compat_ptrace_gethbpregs(child, addr, datap); break; case COMPAT_PTRACE_SETHBPREGS: ret = compat_ptrace_sethbpregs(child, addr, datap); break; #endif default: ret = compat_ptrace_request(child, request, addr, data); break; } return ret; } #endif /* CONFIG_COMPAT */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on * 32-bit children use an extended user_aarch32_ptrace_view to allow * access to the TLS register. */ if (is_compat_task()) return &user_aarch32_view; else if (is_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; return &user_aarch64_view; } long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { switch (request) { case PTRACE_PEEKMTETAGS: case PTRACE_POKEMTETAGS: return mte_ptrace_copy_tags(child, request, addr, data); } return ptrace_request(child, request, addr, data); } enum ptrace_syscall_dir { PTRACE_SYSCALL_ENTER = 0, PTRACE_SYSCALL_EXIT, }; static __always_inline unsigned long ptrace_save_reg(struct pt_regs *regs, enum ptrace_syscall_dir dir, int *regno) { unsigned long saved_reg; /* * We have some ABI weirdness here in the way that we handle syscall * exit stops because we indicate whether or not the stop has been * signalled from syscall entry or syscall exit by clobbering a general * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee * and restoring its old value after the stop. This means that: * * - Any writes by the tracer to this register during the stop are * ignored/discarded. * * - The actual value of the register is not available during the stop, * so the tracer cannot save it and restore it later. * * - Syscall stops behave differently to seccomp and pseudo-step traps * (the latter do not nobble any registers). */ *regno = (is_compat_task() ? 12 : 7); saved_reg = regs->regs[*regno]; regs->regs[*regno] = dir; return saved_reg; } static int report_syscall_entry(struct pt_regs *regs) { unsigned long saved_reg; int regno, ret; saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, ®no); ret = ptrace_report_syscall_entry(regs); if (ret) forget_syscall(regs); regs->regs[regno] = saved_reg; return ret; } static void report_syscall_exit(struct pt_regs *regs) { unsigned long saved_reg; int regno; saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_EXIT, ®no); if (!test_thread_flag(TIF_SINGLESTEP)) { ptrace_report_syscall_exit(regs, 0); regs->regs[regno] = saved_reg; } else { regs->regs[regno] = saved_reg; /* * Signal a pseudo-step exception since we are stepping but * tracer modifications to the registers may have rewound the * state machine. */ ptrace_report_syscall_exit(regs, 1); } } int syscall_trace_enter(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); int ret; if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { ret = report_syscall_entry(regs); if (ret || (flags & _TIF_SYSCALL_EMU)) return NO_SYSCALL; } /* Do the secure computing after ptrace; failures should be fast. */ if (secure_computing() == -1) return NO_SYSCALL; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, regs->syscallno); audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]); return regs->syscallno; } void syscall_trace_exit(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); audit_syscall_exit(regs); if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, syscall_get_return_value(current, regs)); if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) report_syscall_exit(regs); rseq_syscall(regs); } /* * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is * not described in ARM DDI 0487D.a. * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may * be allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 26) | GENMASK_ULL(23, 22) | \ GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) static int valid_compat_regs(struct user_pt_regs *regs) { regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS; if (!system_supports_mixed_endian_el0()) { if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) regs->pstate |= PSR_AA32_E_BIT; else regs->pstate &= ~PSR_AA32_E_BIT; } if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) && (regs->pstate & PSR_AA32_A_BIT) == 0 && (regs->pstate & PSR_AA32_I_BIT) == 0 && (regs->pstate & PSR_AA32_F_BIT) == 0) { return 1; } /* * Force PSR to a valid 32-bit EL0t, preserving the same bits as * arch/arm. */ regs->pstate &= PSR_AA32_N_BIT | PSR_AA32_Z_BIT | PSR_AA32_C_BIT | PSR_AA32_V_BIT | PSR_AA32_Q_BIT | PSR_AA32_IT_MASK | PSR_AA32_GE_MASK | PSR_AA32_E_BIT | PSR_AA32_T_BIT; regs->pstate |= PSR_MODE32_BIT; return 0; } static int valid_native_regs(struct user_pt_regs *regs) { regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS; if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) && (regs->pstate & PSR_D_BIT) == 0 && (regs->pstate & PSR_A_BIT) == 0 && (regs->pstate & PSR_I_BIT) == 0 && (regs->pstate & PSR_F_BIT) == 0) { return 1; } /* Force PSR to a valid 64-bit EL0t */ regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT; return 0; } /* * Are the current registers suitable for user mode? (used to maintain * security in signal handlers) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); else return valid_native_regs(regs); } |
| 8 8 8 8 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IRQ offload/bypass manager * * Copyright (C) 2015 Red Hat, Inc. * Copyright (c) 2015 Linaro Ltd. * * Various virtualization hardware acceleration techniques allow bypassing or * offloading interrupts received from devices around the host kernel. Posted * Interrupts on Intel VT-d systems can allow interrupts to be received * directly by a virtual machine. ARM IRQ Forwarding allows forwarded physical * interrupts to be directly deactivated by the guest. This manager allows * interrupt producers and consumers to find each other to enable this sort of * bypass. */ #include <linux/irqbypass.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("IRQ bypass manager utility module"); static DEFINE_XARRAY(producers); static DEFINE_XARRAY(consumers); static DEFINE_MUTEX(lock); /* @lock must be held when calling connect */ static int __connect(struct irq_bypass_producer *prod, struct irq_bypass_consumer *cons) { int ret = 0; if (prod->stop) prod->stop(prod); if (cons->stop) cons->stop(cons); if (prod->add_consumer) ret = prod->add_consumer(prod, cons); if (!ret) { ret = cons->add_producer(cons, prod); if (ret && prod->del_consumer) prod->del_consumer(prod, cons); } if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); if (!ret) { prod->consumer = cons; cons->producer = prod; } return ret; } /* @lock must be held when calling disconnect */ static void __disconnect(struct irq_bypass_producer *prod, struct irq_bypass_consumer *cons) { if (prod->stop) prod->stop(prod); if (cons->stop) cons->stop(cons); cons->del_producer(cons, prod); if (prod->del_consumer) prod->del_consumer(prod, cons); if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); prod->consumer = NULL; cons->producer = NULL; } /** * irq_bypass_register_producer - register IRQ bypass producer * @producer: pointer to producer structure * @eventfd: pointer to the eventfd context associated with the producer * @irq: Linux IRQ number of the underlying producer device * * Add the provided IRQ producer to the set of producers and connect with the * consumer with a matching eventfd, if one exists. */ int irq_bypass_register_producer(struct irq_bypass_producer *producer, struct eventfd_ctx *eventfd, int irq) { unsigned long index = (unsigned long)eventfd; struct irq_bypass_consumer *consumer; int ret; if (WARN_ON_ONCE(producer->eventfd)) return -EINVAL; producer->irq = irq; guard(mutex)(&lock); ret = xa_insert(&producers, index, producer, GFP_KERNEL); if (ret) return ret; consumer = xa_load(&consumers, index); if (consumer) { ret = __connect(producer, consumer); if (ret) { WARN_ON_ONCE(xa_erase(&producers, index) != producer); return ret; } } producer->eventfd = eventfd; return 0; } EXPORT_SYMBOL_GPL(irq_bypass_register_producer); /** * irq_bypass_unregister_producer - unregister IRQ bypass producer * @producer: pointer to producer structure * * Remove a previously registered IRQ producer (note, it's safe to call this * even if registration was unsuccessful). Disconnect from the associated * consumer, if one exists. */ void irq_bypass_unregister_producer(struct irq_bypass_producer *producer) { unsigned long index = (unsigned long)producer->eventfd; if (!producer->eventfd) return; guard(mutex)(&lock); if (producer->consumer) __disconnect(producer, producer->consumer); WARN_ON_ONCE(xa_erase(&producers, index) != producer); producer->eventfd = NULL; } EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer); /** * irq_bypass_register_consumer - register IRQ bypass consumer * @consumer: pointer to consumer structure * @eventfd: pointer to the eventfd context associated with the consumer * * Add the provided IRQ consumer to the set of consumers and connect with the * producer with a matching eventfd, if one exists. */ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer, struct eventfd_ctx *eventfd) { unsigned long index = (unsigned long)eventfd; struct irq_bypass_producer *producer; int ret; if (WARN_ON_ONCE(consumer->eventfd)) return -EINVAL; if (!consumer->add_producer || !consumer->del_producer) return -EINVAL; guard(mutex)(&lock); ret = xa_insert(&consumers, index, consumer, GFP_KERNEL); if (ret) return ret; producer = xa_load(&producers, index); if (producer) { ret = __connect(producer, consumer); if (ret) { WARN_ON_ONCE(xa_erase(&consumers, index) != consumer); return ret; } } consumer->eventfd = eventfd; return 0; } EXPORT_SYMBOL_GPL(irq_bypass_register_consumer); /** * irq_bypass_unregister_consumer - unregister IRQ bypass consumer * @consumer: pointer to consumer structure * * Remove a previously registered IRQ consumer (note, it's safe to call this * even if registration was unsuccessful). Disconnect from the associated * producer, if one exists. */ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer) { unsigned long index = (unsigned long)consumer->eventfd; if (!consumer->eventfd) return; guard(mutex)(&lock); if (consumer->producer) __disconnect(consumer->producer, consumer); WARN_ON_ONCE(xa_erase(&consumers, index) != consumer); consumer->eventfd = NULL; } EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer); |
| 295 9 135 90 228 253 160 215 22 115 4 34 124 9 121 263 264 257 46 148 232 255 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 84 2 71 13 84 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. NET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Ethernet handlers. * * Version: @(#)eth.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Relocated to include/linux where it belongs by Alan Cox * <gw4pts@gw4pts.ampr.org> */ #ifndef _LINUX_ETHERDEVICE_H #define _LINUX_ETHERDEVICE_H #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> #include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { __be16 *a = (__be16 *)addr; static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif } /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; #else return (*(const u16 *)(addr + 0) | *(const u16 *)(addr + 2) | *(const u16 *)(addr + 4)) == 0; #endif } /** * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 a = *(const u32 *)addr; #else u16 a = *(const u16 *)addr; #endif #ifdef __BIG_ENDIAN return 0x01 & (a >> ((sizeof(a) * 8) - 8)); #else return 0x01 & a; #endif } static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN return 0x01 & ((*(const u64 *)addr) >> 56); #else return 0x01 & (*(const u64 *)addr); #endif #else return is_multicast_ether_addr(addr); #endif } /** * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { return 0x02 & addr[0]; } /** * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { return (*(const u16 *)(addr + 0) & *(const u16 *)(addr + 2) & *(const u16 *)(addr + 4)) == 0xffff; } /** * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { return !is_multicast_ether_addr(addr); } /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return: true if the address is valid. * * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { /* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to * explicitly check for it here. */ return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr); } /** * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol * @proto: Ethertype/length value to be tested * * Check that the value from the Ethertype/length field is a valid Ethertype. * * Return: true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { #ifndef __BIG_ENDIAN /* if CPU is little endian mask off bits representing LSB */ proto &= htons(0xFF00); #endif /* cast both to u16 and compare since LSB can be ignored */ return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); } /** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ static inline void eth_random_addr(u8 *addr) { get_random_bytes(addr, ETH_ALEN); addr[0] &= 0xfe; /* clear multicast bit */ addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the broadcast address to the given address array. */ static inline void eth_broadcast_addr(u8 *addr) { memset(addr, 0xff, ETH_ALEN); } /** * eth_zero_addr - Assign zero address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the zero address to the given address array. */ static inline void eth_zero_addr(u8 *addr) { memset(addr, 0x00, ETH_ALEN); } /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag * @dev: pointer to net_device structure * * Generate a random Ethernet address (MAC) to be used by a net device * and set addr_assign_type so the state can be read by sysfs and be * used by userspace. */ static inline void eth_hw_addr_random(struct net_device *dev) { u8 addr[ETH_ALEN]; eth_random_addr(addr); __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; } /** * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr * @ha: pointer to hardware address * * Calculate CRC from a hardware address as basis for filter hashes. */ static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) { return ether_crc(ETH_ALEN, ha->addr); } /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination * @src: Pointer to a six-byte array Ethernet address source * * Please note: dst & src must both be aligned to u16. */ static inline void ether_addr_copy(u8 *dst, const u8 *src) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) *(u32 *)dst = *(const u32 *)src; *(u16 *)(dst + 4) = *(const u16 *)(src + 4); #else u16 *a = (u16 *)dst; const u16 *b = (const u16 *)src; a[0] = b[0]; a[1] = b[1]; a[2] = b[2]; #endif } /** * eth_hw_addr_set - Assign Ethernet address to a net_device * @dev: pointer to net_device structure * @addr: address to assign * * Assign given address to the net_device, addr_assign_type is not changed. */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, ETH_ALEN); } /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to * @src: pointer to net_device to copy dev_addr from * * Copy the Ethernet address from one net_device to another along with * the address attributes (addr_assign_type). */ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; eth_hw_addr_set(dst, src->dev_addr); } /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); return fold == 0; #else const u16 *a = (const u16 *)addr1; const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } /** * ether_addr_equal_64bits - Compare two Ethernet addresses * @addr1: Pointer to an array of 8 bytes * @addr2: Pointer to an other array of 8 bytes * * Compare two Ethernet addresses, returns true if equal, false otherwise. * * The function doesn't need any conditional branches and possibly uses * word memory accesses on CPU allowing cheap unaligned memory reads. * arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 } * * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); #ifdef __BIG_ENDIAN return (fold >> 16) == 0; #else return (fold << 16) == 0; #endif #else return ether_addr_equal(addr1, addr2); #endif } /** * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: Use only when any Ethernet address may not be u16 aligned. */ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ether_addr_equal(addr1, addr2); #else return memcmp(addr1, addr2, ETH_ALEN) == 0; #endif } /** * ether_addr_equal_masked - Compare two Ethernet addresses with a mask * @addr1: Pointer to a six-byte array containing the 1st Ethernet address * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address * @mask: Pointer to a six-byte array containing the Ethernet address bitmask * * Compare two Ethernet addresses with a mask, returns true if for every bit * set in the bitmask the equivalent bits in the ethernet addresses are equal. * Using a mask with all bits set is a slower ether_addr_equal. */ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, const u8 *mask) { int i; for (i = 0; i < ETH_ALEN; i++) { if ((addr1[i] ^ addr2[i]) & mask[i]) return false; } return true; } static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) { return ether_addr_is_ipv4_mcast(addr) || ether_addr_is_ipv6_mcast(addr); } /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return: a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { u64 u = 0; int i; for (i = 0; i < ETH_ALEN; i++) u = u << 8 | addr[i]; return u; } /** * u64_to_ether_addr - Convert a u64 to an Ethernet address. * @u: u64 to convert to an Ethernet MAC address * @addr: Pointer to a six-byte array to contain the Ethernet address */ static inline void u64_to_ether_addr(u64 u, u8 *addr) { int i; for (i = ETH_ALEN - 1; i >= 0; i--) { addr[i] = u & 0xff; u = u >> 8; } } /** * eth_addr_dec - Decrement the given MAC address * * @addr: Pointer to a six-byte array containing Ethernet address to decrement */ static inline void eth_addr_dec(u8 *addr) { u64 u = ether_addr_to_u64(addr); u--; u64_to_ether_addr(u, addr); } /** * eth_addr_inc() - Increment the given MAC address. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_inc(u8 *addr) { u64 u = ether_addr_to_u64(addr); u++; u64_to_ether_addr(u, addr); } /** * eth_addr_add() - Add (or subtract) an offset to/from the given MAC address. * * @offset: Offset to add. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_add(u8 *addr, long offset) { u64 u = ether_addr_to_u64(addr); u += offset; u64_to_ether_addr(u, addr); } /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address * * Compare passed address with all addresses of the device. Return true if the * address if one of the device addresses. * * Note that this function calls ether_addr_equal_64bits() so take care of * the right padding. */ static inline bool is_etherdev_addr(const struct net_device *dev, const u8 addr[6 + 2]) { struct netdev_hw_addr *ha; bool res = false; rcu_read_lock(); for_each_dev_addr(dev, ha) { res = ether_addr_equal_64bits(addr, ha->addr); if (res) break; } rcu_read_unlock(); return res; } #endif /* __KERNEL__ */ /** * compare_ether_header - Compare two Ethernet headers * @a: Pointer to Ethernet header * @b: Pointer to Ethernet header * * Compare two Ethernet headers, returns 0 if equal. * This assumes that the network header (i.e., IP header) is 4-byte * aligned OR the platform can handle unaligned access. This is the * case for all packets coming into netif_receive_skb or similar * entry points. */ static inline unsigned long compare_ether_header(const void *a, const void *b) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 unsigned long fold; /* * We want to compare 14 bytes: * [a0 ... a13] ^ [b0 ... b13] * Use two long XOR, ORed together, with an overlap of two bytes. * [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] | * [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13] * This means the [a6 a7] ^ [b6 b7] part is done two times. */ fold = *(unsigned long *)a ^ *(unsigned long *)b; fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6); return fold; #else u32 *a32 = (u32 *)((u8 *)a + 2); u32 *b32 = (u32 *)((u8 *)b + 2); return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); #endif } /** * eth_hw_addr_gen - Generate and assign Ethernet address to a port * @dev: pointer to port's net_device structure * @base_addr: base Ethernet address * @id: offset to add to the base address * * Generate a MAC address using a base address and an offset and assign it * to a net_device. Commonly used by switch drivers which need to compute * addresses for all their ports. addr_assign_type is not changed. */ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, unsigned int id) { u64 u = ether_addr_to_u64(base_addr); u8 addr[ETH_ALEN]; u += id; u64_to_ether_addr(u, addr); eth_hw_addr_set(dev, addr); } /** * eth_skb_pkt_type - Assign packet type if destination address does not match * @skb: Assigned a packet type if address does not match @dev address * @dev: Network device used to compare packet address against * * If the destination MAC address of the packet does not match the network * device address, assign an appropriate packet type. */ static inline void eth_skb_pkt_type(struct sk_buff *skb, const struct net_device *dev) { const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } else { skb->pkt_type = PACKET_OTHERHOST; } } } static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) { struct ethhdr *eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); return eth; } /** * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function * takes short frames and pads them with zeros up to the 60 byte limit. */ static inline int eth_skb_pad(struct sk_buff *skb) { return skb_put_padto(skb, ETH_ZLEN); } #endif /* _LINUX_ETHERDEVICE_H */ |
| 2 1 1 1 1 1 1 3 2 2 1 7 1 6 3 1 2 1 1 1 4 4 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VFIO-KVM bridge pseudo device * * Copyright (C) 2013 Red Hat, Inc. All rights reserved. * Author: Alex Williamson <alex.williamson@redhat.com> */ #include <linux/errno.h> #include <linux/file.h> #include <linux/kvm_host.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/vfio.h> #include "vfio.h" #ifdef CONFIG_SPAPR_TCE_IOMMU #include <asm/kvm_ppc.h> #endif struct kvm_vfio_file { struct list_head node; struct file *file; #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *iommu_group; #endif }; struct kvm_vfio { struct list_head file_list; struct mutex lock; bool noncoherent; }; static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm) { void (*fn)(struct file *file, struct kvm *kvm); fn = symbol_get(vfio_file_set_kvm); if (!fn) return; fn(file, kvm); symbol_put(vfio_file_set_kvm); } static bool kvm_vfio_file_enforced_coherent(struct file *file) { bool (*fn)(struct file *file); bool ret; fn = symbol_get(vfio_file_enforced_coherent); if (!fn) return false; ret = fn(file); symbol_put(vfio_file_enforced_coherent); return ret; } static bool kvm_vfio_file_is_valid(struct file *file) { bool (*fn)(struct file *file); bool ret; fn = symbol_get(vfio_file_is_valid); if (!fn) return false; ret = fn(file); symbol_put(vfio_file_is_valid); return ret; } #ifdef CONFIG_SPAPR_TCE_IOMMU static struct iommu_group *kvm_vfio_file_iommu_group(struct file *file) { struct iommu_group *(*fn)(struct file *file); struct iommu_group *ret; fn = symbol_get(vfio_file_iommu_group); if (!fn) return NULL; ret = fn(file); symbol_put(vfio_file_iommu_group); return ret; } static void kvm_spapr_tce_release_vfio_group(struct kvm *kvm, struct kvm_vfio_file *kvf) { if (WARN_ON_ONCE(!kvf->iommu_group)) return; kvm_spapr_tce_release_iommu_group(kvm, kvf->iommu_group); iommu_group_put(kvf->iommu_group); kvf->iommu_group = NULL; } #endif /* * Groups/devices can use the same or different IOMMU domains. If the same * then adding a new group/device may change the coherency of groups/devices * we've previously been told about. We don't want to care about any of * that so we retest each group/device and bail as soon as we find one that's * noncoherent. This means we only ever [un]register_noncoherent_dma once * for the whole device. */ static void kvm_vfio_update_coherency(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; bool noncoherent = false; struct kvm_vfio_file *kvf; list_for_each_entry(kvf, &kv->file_list, node) { if (!kvm_vfio_file_enforced_coherent(kvf->file)) { noncoherent = true; break; } } if (noncoherent != kv->noncoherent) { kv->noncoherent = noncoherent; if (kv->noncoherent) kvm_arch_register_noncoherent_dma(dev->kvm); else kvm_arch_unregister_noncoherent_dma(dev->kvm); } } static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; struct file *filp; int ret = 0; filp = fget(fd); if (!filp) return -EBADF; /* Ensure the FD is a vfio FD. */ if (!kvm_vfio_file_is_valid(filp)) { ret = -EINVAL; goto out_fput; } mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file == filp) { ret = -EEXIST; goto out_unlock; } } kvf = kzalloc_obj(*kvf, GFP_KERNEL_ACCOUNT); if (!kvf) { ret = -ENOMEM; goto out_unlock; } kvf->file = get_file(filp); list_add_tail(&kvf->node, &kv->file_list); kvm_vfio_file_set_kvm(kvf->file, dev->kvm); kvm_vfio_update_coherency(dev); out_unlock: mutex_unlock(&kv->lock); out_fput: fput(filp); return ret; } static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; CLASS(fd, f)(fd); int ret; if (fd_empty(f)) return -EBADF; ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != fd_file(f)) continue; list_del(&kvf->node); #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif kvm_vfio_file_set_kvm(kvf->file, NULL); fput(kvf->file); kfree(kvf); ret = 0; break; } kvm_vfio_update_coherency(dev); mutex_unlock(&kv->lock); return ret; } #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvm_vfio_file_set_spapr_tce(struct kvm_device *dev, void __user *arg) { struct kvm_vfio_spapr_tce param; struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; int ret; if (copy_from_user(¶m, arg, sizeof(struct kvm_vfio_spapr_tce))) return -EFAULT; CLASS(fd, f)(param.groupfd); if (fd_empty(f)) return -EBADF; ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { if (kvf->file != fd_file(f)) continue; if (!kvf->iommu_group) { kvf->iommu_group = kvm_vfio_file_iommu_group(kvf->file); if (WARN_ON_ONCE(!kvf->iommu_group)) { ret = -EIO; goto err_fdput; } } ret = kvm_spapr_tce_attach_iommu_group(dev->kvm, param.tablefd, kvf->iommu_group); break; } err_fdput: mutex_unlock(&kv->lock); return ret; } #endif static int kvm_vfio_set_file(struct kvm_device *dev, long attr, void __user *arg) { int32_t __user *argp = arg; int32_t fd; switch (attr) { case KVM_DEV_VFIO_FILE_ADD: if (get_user(fd, argp)) return -EFAULT; return kvm_vfio_file_add(dev, fd); case KVM_DEV_VFIO_FILE_DEL: if (get_user(fd, argp)) return -EFAULT; return kvm_vfio_file_del(dev, fd); #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: return kvm_vfio_file_set_spapr_tce(dev, arg); #endif } return -ENXIO; } static int kvm_vfio_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_VFIO_FILE: return kvm_vfio_set_file(dev, attr->attr, u64_to_user_ptr(attr->addr)); } return -ENXIO; } static int kvm_vfio_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_VFIO_FILE: switch (attr->attr) { case KVM_DEV_VFIO_FILE_ADD: case KVM_DEV_VFIO_FILE_DEL: #ifdef CONFIG_SPAPR_TCE_IOMMU case KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: #endif return 0; } break; } return -ENXIO; } static void kvm_vfio_release(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf, *tmp; list_for_each_entry_safe(kvf, tmp, &kv->file_list, node) { #ifdef CONFIG_SPAPR_TCE_IOMMU kvm_spapr_tce_release_vfio_group(dev->kvm, kvf); #endif kvm_vfio_file_set_kvm(kvf->file, NULL); fput(kvf->file); list_del(&kvf->node); kfree(kvf); } kvm_vfio_update_coherency(dev); kfree(kv); kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */ } static int kvm_vfio_create(struct kvm_device *dev, u32 type); static const struct kvm_device_ops kvm_vfio_ops = { .name = "kvm-vfio", .create = kvm_vfio_create, .release = kvm_vfio_release, .set_attr = kvm_vfio_set_attr, .has_attr = kvm_vfio_has_attr, }; static int kvm_vfio_create(struct kvm_device *dev, u32 type) { struct kvm_device *tmp; struct kvm_vfio *kv; lockdep_assert_held(&dev->kvm->lock); /* Only one VFIO "device" per VM */ list_for_each_entry(tmp, &dev->kvm->devices, vm_node) if (tmp->ops == &kvm_vfio_ops) return -EBUSY; kv = kzalloc_obj(*kv, GFP_KERNEL_ACCOUNT); if (!kv) return -ENOMEM; INIT_LIST_HEAD(&kv->file_list); mutex_init(&kv->lock); dev->private = kv; return 0; } int kvm_vfio_ops_init(void) { return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO); } void kvm_vfio_ops_exit(void) { kvm_unregister_device_ops(KVM_DEV_TYPE_VFIO); } |
| 189 58 156 156 156 60 60 60 61 61 61 230 231 231 231 231 36 36 36 231 231 231 228 230 231 231 230 442 444 444 93 443 443 165 28 355 45 42 8 287 385 386 444 443 21 430 405 26 389 165 85 162 165 165 165 165 165 165 165 277 243 277 277 277 156 147 60 241 155 243 156 43 9 43 40 20 40 40 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; static const int page_cluster_max = 31; struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_frozen_pages(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; /* block memcg migration while the folio moves between lru */ if (move_fn != lru_add && !folio_test_clear_lru(folio)) continue; folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ offsetof(struct cpu_fbatches, op) >= \ offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_move_tail); } void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) __releases(lruvec->lru_lock) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; if (!cost) { spin_unlock_irq(&lruvec->lru_lock); return; } for (;;) { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += cost; else lruvec->anon_cost += cost; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); lruvec = parent_lruvec(lruvec); if (!lruvec) break; spin_lock_irq(&lruvec->lru_lock); } } void lru_note_cost_refault(struct folio *folio) { struct lruvec *lruvec; lruvec = folio_lruvec_lock_irq(folio); lru_note_cost_unlock_irq(lruvec, folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio) || !folio_test_lru(folio)) return; folio_batch_add_and_move(folio, lru_activate); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void lru_gen_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags.f); if (folio_test_unevictable(folio)) return; /* see the comment on LRU_REFS_FLAGS */ if (!folio_test_referenced(folio)) { set_mask_bits(&folio->flags.f, LRU_REFS_MASK, BIT(PG_referenced)); return; } do { if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) { if (!folio_test_workingset(folio)) folio_set_workingset(folio); return; } new_flags = old_flags + BIT(LRU_REFS_PGOFF); } while (!try_cmpxchg(&folio->flags.f, &old_flags, new_flags)); } static bool lru_gen_clear_refs(struct folio *folio) { struct lru_gen_folio *lrugen; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); if (gen < 0) return true; set_mask_bits(&folio->flags.f, LRU_REFS_FLAGS | BIT(PG_workingset), 0); lrugen = &folio_lruvec(folio)->lrugen; /* whether can do without shuffling under the LRU lock */ return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type])); } #else /* !CONFIG_LRU_GEN */ static void lru_gen_inc_refs(struct folio *folio) { } static bool lru_gen_clear_refs(struct folio *folio) { return false; } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (folio_test_dropbehind(folio)) return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_folio_seq() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropriate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio) || lru_gen_enabled(); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); if (lru_gen_enabled()) lru_gen_clear_refs(folio); else folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add); fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; folio_batch_add_and_move(folio, lru_deactivate); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); /* It helps everyone if we do our own local drain immediately. */ lru_add_drain(); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[PAGEVEC_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } static const struct ctl_table swap_sysctl_table[] = { { .procname = "page-cluster", .data = &page_cluster, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = (void *)&page_cluster_max, } }; /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = PAGES_TO_MB(totalram_pages()); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ register_sysctl_init("vm", swap_sysctl_table); } |
| 84 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the Ethernet IEEE 802.3 interface. * * Version: @(#)if_ether.h 1.0.1a 02/08/94 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Steve Whitehouse, <gw7rrm@eeshack3.swan.ac.uk> */ #ifndef _LINUX_IF_ETHER_H #define _LINUX_IF_ETHER_H #include <linux/skbuff.h> #include <uapi/linux/if_ether.h> /* XX:XX:XX:XX:XX:XX */ #define MAC_ADDR_STR_LEN (3 * ETH_ALEN - 1) static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + eth_hdr() */ static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb->data; } static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); } int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); #endif /* _LINUX_IF_ETHER_H */ |
| 222 125 125 125 70 70 70 29 29 216 215 49 50 51 51 264 264 261 260 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 - Columbia University and Linaro Ltd. * Author: Jintack Lim <jintack.lim@linaro.org> */ #include <linux/bitfield.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/fixmap.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/sysreg.h> #include "sys_regs.h" struct vncr_tlb { /* The guest's VNCR_EL2 */ u64 gva; struct s1_walk_info wi; struct s1_walk_result wr; u64 hpa; /* -1 when not mapped on a CPU */ int cpu; /* * true if the TLB is valid. Can only be changed with the * mmu_lock held. */ bool valid; }; /* * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between * memory usage and potential number of different sets of S2 PTs in * the guests. Running out of S2 MMUs only affects performance (we * will invalidate them more often). */ #define S2_MMU_PER_VCPU 2 void kvm_init_nested(struct kvm *kvm) { kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; atomic_set(&kvm->arch.vncr_map_count, 0); } static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) { /* * We only initialise the IPA range on the canonical MMU, which * defines the contract between KVM and userspace on where the * "hardware" is in the IPA space. This affects the validity of MMIO * exits forwarded to userspace, for example. * * For nested S2s, we use the PARange as exposed to the guest, as it * is allowed to use it at will to expose whatever memory map it * wants to its own guests as it would be on real HW. */ return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm)); } int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_s2_mmu *tmp; int num_mmus, ret = 0; if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features) && !cpus_have_final_cap(ARM64_HAS_HCR_NV1)) return -EINVAL; if (!vcpu->arch.ctxt.vncr_array) vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vcpu->arch.ctxt.vncr_array) return -ENOMEM; /* * Let's treat memory allocation failures as benign: If we fail to * allocate anything, return an error and keep the allocated array * alive. Userspace may try to recover by initializing the vcpu * again, and there is no reason to affect the whole VM for this. */ num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU; tmp = kvrealloc(kvm->arch.nested_mmus, size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tmp) return -ENOMEM; swap(kvm->arch.nested_mmus, tmp); /* * If we went through a realocation, adjust the MMU back-pointers in * the previously initialised kvm_pgtable structures. */ if (kvm->arch.nested_mmus != tmp) for (int i = 0; i < kvm->arch.nested_mmus_size; i++) kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i]; for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++) ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]); if (ret) { for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++) kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]); free_page((unsigned long)vcpu->arch.ctxt.vncr_array); vcpu->arch.ctxt.vncr_array = NULL; return ret; } kvm->arch.nested_mmus_size = num_mmus; return 0; } struct s2_walk_info { u64 baddr; unsigned int max_oa_bits; unsigned int pgshift; unsigned int sl; unsigned int t0sz; bool be; bool ha; }; static u32 compute_fsc(int level, u32 fsc) { return fsc | (level & 0x3); } static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc) { u32 esr; esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC; esr |= compute_fsc(level, fsc); return esr; } static int get_ia_size(struct s2_walk_info *wi) { return 64 - wi->t0sz; } static int check_base_s2_limits(struct kvm_vcpu *vcpu, struct s2_walk_info *wi, int level, int input_size, int stride) { int start_size, pa_max; pa_max = kvm_get_pa_bits(vcpu->kvm); /* Check translation limits */ switch (BIT(wi->pgshift)) { case SZ_64K: if (level == 0 || (level == 1 && pa_max <= 42)) return -EFAULT; break; case SZ_16K: if (level == 0 || (level == 1 && pa_max <= 40)) return -EFAULT; break; case SZ_4K: if (level < 0 || (level == 0 && pa_max <= 42)) return -EFAULT; break; } /* Check input size limits */ if (input_size > pa_max) return -EFAULT; /* Check number of entries in starting level table */ start_size = input_size - ((3 - level) * stride + wi->pgshift); if (start_size < 1 || start_size > stride + 4) return -EFAULT; return 0; } /* Check if output is within boundaries */ static int check_output_size(struct s2_walk_info *wi, phys_addr_t output) { unsigned int output_size = wi->max_oa_bits; if (output_size != 48 && (output & GENMASK_ULL(47, output_size))) return -1; return 0; } static int read_guest_s2_desc(struct kvm_vcpu *vcpu, phys_addr_t pa, u64 *desc, struct s2_walk_info *wi) { u64 val; int r; r = kvm_read_guest(vcpu->kvm, pa, &val, sizeof(val)); if (r) return r; /* * Handle reversedescriptors if endianness differs between the * host and the guest hypervisor. */ if (wi->be) *desc = be64_to_cpu((__force __be64)val); else *desc = le64_to_cpu((__force __le64)val); return 0; } static int swap_guest_s2_desc(struct kvm_vcpu *vcpu, phys_addr_t pa, u64 old, u64 new, struct s2_walk_info *wi) { if (wi->be) { old = (__force u64)cpu_to_be64(old); new = (__force u64)cpu_to_be64(new); } else { old = (__force u64)cpu_to_le64(old); new = (__force u64)cpu_to_le64(new); } return __kvm_at_swap_desc(vcpu->kvm, pa, old, new); } /* * This is essentially a C-version of the pseudo code from the ARM ARM * AArch64.TranslationTableWalk function. I strongly recommend looking at * that pseudocode in trying to understand this. * * Must be called with the kvm->srcu read lock held */ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, struct s2_walk_info *wi, struct kvm_s2_trans *out) { int first_block_level, level, stride, input_size, base_lower_bound; phys_addr_t base_addr; unsigned int addr_top, addr_bottom; u64 desc, new_desc; /* page table entry */ int ret; phys_addr_t paddr; switch (BIT(wi->pgshift)) { default: case SZ_64K: case SZ_16K: level = 3 - wi->sl; first_block_level = 2; break; case SZ_4K: level = 2 - wi->sl; first_block_level = 1; break; } stride = wi->pgshift - 3; input_size = get_ia_size(wi); if (input_size > 48 || input_size < 25) return -EFAULT; ret = check_base_s2_limits(vcpu, wi, level, input_size, stride); if (WARN_ON(ret)) { out->esr = compute_fsc(0, ESR_ELx_FSC_FAULT); return ret; } base_lower_bound = 3 + input_size - ((3 - level) * stride + wi->pgshift); base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound); if (check_output_size(wi, base_addr)) { /* R_BFHQH */ out->esr = compute_fsc(0, ESR_ELx_FSC_ADDRSZ); return 1; } addr_top = input_size - 1; while (1) { phys_addr_t index; addr_bottom = (3 - level) * stride + wi->pgshift; index = (ipa & GENMASK_ULL(addr_top, addr_bottom)) >> (addr_bottom - 3); paddr = base_addr | index; ret = read_guest_s2_desc(vcpu, paddr, &desc, wi); if (ret < 0) { out->esr = ESR_ELx_FSC_SEA_TTW(level); return ret; } new_desc = desc; /* Check for valid descriptor at this point */ if (!(desc & KVM_PTE_VALID)) { out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } if (FIELD_GET(KVM_PTE_TYPE, desc) == KVM_PTE_TYPE_BLOCK) { if (level < 3) break; out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } /* We're at the final level */ if (level == 3) break; if (check_output_size(wi, desc)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); out->desc = desc; return 1; } base_addr = desc & GENMASK_ULL(47, wi->pgshift); level += 1; addr_top = addr_bottom - 1; } if (level < first_block_level) { out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } if (check_output_size(wi, desc)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); out->desc = desc; return 1; } if (wi->ha) new_desc |= KVM_PTE_LEAF_ATTR_LO_S2_AF; if (new_desc != desc) { ret = swap_guest_s2_desc(vcpu, paddr, desc, new_desc, wi); if (ret) return ret; desc = new_desc; } if (!(desc & KVM_PTE_LEAF_ATTR_LO_S2_AF)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS); out->desc = desc; return 1; } addr_bottom += contiguous_bit_shift(desc, wi, level); /* Calculate and return the result */ paddr = (desc & GENMASK_ULL(47, addr_bottom)) | (ipa & GENMASK_ULL(addr_bottom - 1, 0)); out->output = paddr; out->block_size = 1UL << ((3 - level) * stride + wi->pgshift); out->readable = desc & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; out->writable = desc & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; out->level = level; out->desc = desc; return 0; } static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi) { wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK; switch (FIELD_GET(VTCR_EL2_TG0_MASK, vtcr)) { case VTCR_EL2_TG0_4K: wi->pgshift = 12; break; case VTCR_EL2_TG0_16K: wi->pgshift = 14; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ wi->pgshift = 16; break; } wi->sl = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); /* Global limit for now, should eventually be per-VM */ wi->max_oa_bits = min(get_kvm_ipa_limit(), ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr), false)); wi->ha = vtcr & VTCR_EL2_HA; } int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa, struct kvm_s2_trans *result) { u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); struct s2_walk_info wi; int ret; result->esr = 0; if (!vcpu_has_nv(vcpu)) return 0; wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); vtcr_to_walk_info(vtcr, &wi); wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE; ret = walk_nested_s2_pgd(vcpu, gipa, &wi, result); if (ret) result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC); return ret; } static unsigned int ttl_to_size(u8 ttl) { int level = ttl & 3; int gran = (ttl >> 2) & 3; unsigned int max_size = 0; switch (gran) { case TLBI_TTL_TG_4K: switch (level) { case 0: break; case 1: max_size = SZ_1G; break; case 2: max_size = SZ_2M; break; case 3: max_size = SZ_4K; break; } break; case TLBI_TTL_TG_16K: switch (level) { case 0: case 1: break; case 2: max_size = SZ_32M; break; case 3: max_size = SZ_16K; break; } break; case TLBI_TTL_TG_64K: switch (level) { case 0: case 1: /* No 52bit IPA support */ break; case 2: max_size = SZ_512M; break; case 3: max_size = SZ_64K; break; } break; default: /* No size information */ break; } return max_size; } static u8 pgshift_level_to_ttl(u16 shift, u8 level) { u8 ttl; switch(shift) { case 12: ttl = TLBI_TTL_TG_4K; break; case 14: ttl = TLBI_TTL_TG_16K; break; case 16: ttl = TLBI_TTL_TG_64K; break; default: BUG(); } ttl <<= 2; ttl |= level & 3; return ttl; } /* * Compute the equivalent of the TTL field by parsing the shadow PT. The * granule size is extracted from the cached VTCR_EL2.TG0 while the level is * retrieved from first entry carrying the level as a tag. */ static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr) { u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr; kvm_pte_t pte; u8 ttl, level; lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(mmu)->mmu_lock); switch (FIELD_GET(VTCR_EL2_TG0_MASK, vtcr)) { case VTCR_EL2_TG0_4K: ttl = (TLBI_TTL_TG_4K << 2); break; case VTCR_EL2_TG0_16K: ttl = (TLBI_TTL_TG_16K << 2); break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ ttl = (TLBI_TTL_TG_64K << 2); break; } tmp = addr; again: /* Iteratively compute the block sizes for a particular granule size */ switch (FIELD_GET(VTCR_EL2_TG0_MASK, vtcr)) { case VTCR_EL2_TG0_4K: if (sz < SZ_4K) sz = SZ_4K; else if (sz < SZ_2M) sz = SZ_2M; else if (sz < SZ_1G) sz = SZ_1G; else sz = 0; break; case VTCR_EL2_TG0_16K: if (sz < SZ_16K) sz = SZ_16K; else if (sz < SZ_32M) sz = SZ_32M; else sz = 0; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ if (sz < SZ_64K) sz = SZ_64K; else if (sz < SZ_512M) sz = SZ_512M; else sz = 0; break; } if (sz == 0) return 0; tmp &= ~(sz - 1); if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL)) goto again; if (!(pte & PTE_VALID)) goto again; level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte); if (!level) goto again; ttl |= level; /* * We now have found some level information in the shadow S2. Check * that the resulting range is actually including the original IPA. */ sz = ttl_to_size(ttl); if (addr < (tmp + sz)) return ttl; return 0; } unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); unsigned long max_size; u8 ttl; ttl = FIELD_GET(TLBI_TTL_MASK, val); if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) { /* No TTL, check the shadow S2 for a hint */ u64 addr = (val & GENMASK_ULL(35, 0)) << 12; ttl = get_guest_mapping_ttl(mmu, addr); } max_size = ttl_to_size(ttl); if (!max_size) { /* Compute the maximum extent of the invalidation */ switch (FIELD_GET(VTCR_EL2_TG0_MASK, mmu->tlb_vtcr)) { case VTCR_EL2_TG0_4K: max_size = SZ_1G; break; case VTCR_EL2_TG0_16K: max_size = SZ_32M; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ /* * No, we do not support 52bit IPA in nested yet. Once * we do, this should be 4TB. */ max_size = SZ_512M; break; } } WARN_ON(!max_size); return max_size; } /* * We can have multiple *different* MMU contexts with the same VMID: * * - S2 being enabled or not, hence differing by the HCR_EL2.VM bit * * - Multiple vcpus using private S2s (huh huh...), hence differing by the * VBBTR_EL2.BADDR address * * - A combination of the above... * * We can always identify which MMU context to pick at run-time. However, * TLB invalidation involving a VMID must take action on all the TLBs using * this particular VMID. This translates into applying the same invalidation * operation to all the contexts that are using this VMID. Moar phun! */ void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid, const union tlbi_info *info, void (*tlbi_callback)(struct kvm_s2_mmu *, const union tlbi_info *)) { write_lock(&kvm->mmu_lock); for (int i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!kvm_s2_mmu_valid(mmu)) continue; if (vmid == get_vmid(mmu->tlb_vttbr)) tlbi_callback(mmu, info); } write_unlock(&kvm->mmu_lock); } struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; bool nested_stage2_enabled; u64 vttbr, vtcr, hcr; lockdep_assert_held_write(&kvm->mmu_lock); vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); hcr = vcpu_read_sys_reg(vcpu, HCR_EL2); nested_stage2_enabled = hcr & HCR_VM; /* Don't consider the CnP bit for the vttbr match */ vttbr &= ~VTTBR_CNP_BIT; /* * Two possibilities when looking up a S2 MMU context: * * - either S2 is enabled in the guest, and we need a context that is * S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR, * which makes it safe from a TLB conflict perspective (a broken * guest won't be able to generate them), * * - or S2 is disabled, and we need a context that is S2-disabled * and matches the VMID only, as all TLBs are tagged by VMID even * if S2 translation is disabled. */ for (int i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!kvm_s2_mmu_valid(mmu)) continue; if (nested_stage2_enabled && mmu->nested_stage2_enabled && vttbr == mmu->tlb_vttbr && vtcr == mmu->tlb_vtcr) return mmu; if (!nested_stage2_enabled && !mmu->nested_stage2_enabled && get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr)) return mmu; } return NULL; } static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_s2_mmu *s2_mmu; int i; lockdep_assert_held_write(&vcpu->kvm->mmu_lock); s2_mmu = lookup_s2_mmu(vcpu); if (s2_mmu) goto out; /* * Make sure we don't always search from the same point, or we * will always reuse a potentially active context, leaving * free contexts unused. */ for (i = kvm->arch.nested_mmus_next; i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next); i++) { s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size]; if (atomic_read(&s2_mmu->refcnt) == 0) break; } BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */ /* Set the scene for the next search */ kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size; /* Make sure we don't forget to do the laundry */ if (kvm_s2_mmu_valid(s2_mmu)) { kvm_nested_s2_ptdump_remove_debugfs(s2_mmu); s2_mmu->pending_unmap = true; } /* * The virtual VMID (modulo CnP) will be used as a key when matching * an existing kvm_s2_mmu. * * We cache VTCR at allocation time, once and for all. It'd be great * if the guest didn't screw that one up, as this is not very * forgiving... */ s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT; s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM; kvm_nested_s2_ptdump_create_debugfs(s2_mmu); out: atomic_inc(&s2_mmu->refcnt); /* * Set the vCPU request to perform an unmap, even if the pending unmap * originates from another vCPU. This guarantees that the MMU has been * completely unmapped before any vCPU actually uses it, and allows * multiple vCPUs to lend a hand with completing the unmap. */ if (s2_mmu->pending_unmap) kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu); return s2_mmu; } void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu) { /* CnP being set denotes an invalid entry */ mmu->tlb_vttbr = VTTBR_CNP_BIT; mmu->nested_stage2_enabled = false; atomic_set(&mmu->refcnt, 0); } void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu) { /* * If the vCPU kept its reference on the MMU after the last put, * keep rolling with it. */ if (is_hyp_ctxt(vcpu)) { if (!vcpu->arch.hw_mmu) vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; } else { if (!vcpu->arch.hw_mmu) { scoped_guard(write_lock, &vcpu->kvm->mmu_lock) vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu); } if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); } } void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu) { /* Unconditionally drop the VNCR mapping if we have one */ if (host_data_test_flag(L1_VNCR_MAPPED)) { BUG_ON(vcpu->arch.vncr_tlb->cpu != smp_processor_id()); BUG_ON(is_hyp_ctxt(vcpu)); clear_fixmap(vncr_fixmap(vcpu->arch.vncr_tlb->cpu)); vcpu->arch.vncr_tlb->cpu = -1; host_data_clear_flag(L1_VNCR_MAPPED); atomic_dec(&vcpu->kvm->arch.vncr_map_count); } /* * Keep a reference on the associated stage-2 MMU if the vCPU is * scheduling out and not in WFI emulation, suggesting it is likely to * reuse the MMU sometime soon. */ if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI)) return; if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) atomic_dec(&vcpu->arch.hw_mmu->refcnt); vcpu->arch.hw_mmu = NULL; } /* * Returns non-zero if permission fault is handled by injecting it to the next * level hypervisor. */ int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans) { bool forward_fault = false; trans->esr = 0; if (!kvm_vcpu_trap_is_permission_fault(vcpu)) return 0; if (kvm_vcpu_trap_is_iabt(vcpu)) { if (vcpu_mode_priv(vcpu)) forward_fault = !kvm_s2_trans_exec_el1(vcpu->kvm, trans); else forward_fault = !kvm_s2_trans_exec_el0(vcpu->kvm, trans); } else { bool write_fault = kvm_is_write_fault(vcpu); forward_fault = ((write_fault && !trans->writable) || (!write_fault && !trans->readable)); } if (forward_fault) trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM); return forward_fault; } int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2) { vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2); vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2); return kvm_inject_nested_sync(vcpu, esr_el2); } u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime) { enum vcpu_sysreg ttbr_elx; u64 tcr; u16 asid; switch (regime) { case TR_EL10: tcr = vcpu_read_sys_reg(vcpu, TCR_EL1); ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL1 : TTBR0_EL1; break; case TR_EL20: tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL2 : TTBR0_EL2; break; default: BUG(); } asid = FIELD_GET(TTBRx_EL1_ASID, vcpu_read_sys_reg(vcpu, ttbr_elx)); if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || !(tcr & TCR_ASID16)) asid &= GENMASK(7, 0); return asid; } static void invalidate_vncr(struct vncr_tlb *vt) { vt->valid = false; if (vt->cpu != -1) clear_fixmap(vncr_fixmap(vt->cpu)); } static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end) { struct kvm_vcpu *vcpu; unsigned long i; lockdep_assert_held_write(&kvm->mmu_lock); if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) return; kvm_for_each_vcpu(i, vcpu, kvm) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 ipa_start, ipa_end, ipa_size; /* * Careful here: We end-up here from an MMU notifier, * and this can race against a vcpu not being onlined * yet, without the pseudo-TLB being allocated. * * Skip those, as they obviously don't participate in * the invalidation at this stage. */ if (!vt) continue; if (!vt->valid) continue; ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); ipa_start = vt->wr.pa & ~(ipa_size - 1); ipa_end = ipa_start + ipa_size; if (ipa_end <= start || ipa_start >= end) continue; invalidate_vncr(vt); } } struct s1e2_tlbi_scope { enum { TLBI_ALL, TLBI_VA, TLBI_VAA, TLBI_ASID, } type; u16 asid; u64 va; u64 size; }; static void invalidate_vncr_va(struct kvm *kvm, struct s1e2_tlbi_scope *scope) { struct kvm_vcpu *vcpu; unsigned long i; lockdep_assert_held_write(&kvm->mmu_lock); kvm_for_each_vcpu(i, vcpu, kvm) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 va_start, va_end, va_size; if (!vt->valid) continue; va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); va_start = vt->gva & ~(va_size - 1); va_end = va_start + va_size; switch (scope->type) { case TLBI_ALL: break; case TLBI_VA: if (va_end <= scope->va || va_start >= (scope->va + scope->size)) continue; if (vt->wr.nG && vt->wr.asid != scope->asid) continue; break; case TLBI_VAA: if (va_end <= scope->va || va_start >= (scope->va + scope->size)) continue; break; case TLBI_ASID: if (!vt->wr.nG || vt->wr.asid != scope->asid) continue; break; } invalidate_vncr(vt); } } #define tlbi_va_s1_to_va(v) (u64)sign_extend64((v) << 12, 48) static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val, struct s1e2_tlbi_scope *scope) { switch (inst) { case OP_TLBI_ALLE2: case OP_TLBI_ALLE2IS: case OP_TLBI_ALLE2OS: case OP_TLBI_VMALLE1: case OP_TLBI_VMALLE1IS: case OP_TLBI_VMALLE1OS: case OP_TLBI_ALLE2NXS: case OP_TLBI_ALLE2ISNXS: case OP_TLBI_ALLE2OSNXS: case OP_TLBI_VMALLE1NXS: case OP_TLBI_VMALLE1ISNXS: case OP_TLBI_VMALLE1OSNXS: scope->type = TLBI_ALL; break; case OP_TLBI_VAE2: case OP_TLBI_VAE2IS: case OP_TLBI_VAE2OS: case OP_TLBI_VAE1: case OP_TLBI_VAE1IS: case OP_TLBI_VAE1OS: case OP_TLBI_VAE2NXS: case OP_TLBI_VAE2ISNXS: case OP_TLBI_VAE2OSNXS: case OP_TLBI_VAE1NXS: case OP_TLBI_VAE1ISNXS: case OP_TLBI_VAE1OSNXS: case OP_TLBI_VALE2: case OP_TLBI_VALE2IS: case OP_TLBI_VALE2OS: case OP_TLBI_VALE1: case OP_TLBI_VALE1IS: case OP_TLBI_VALE1OS: case OP_TLBI_VALE2NXS: case OP_TLBI_VALE2ISNXS: case OP_TLBI_VALE2OSNXS: case OP_TLBI_VALE1NXS: case OP_TLBI_VALE1ISNXS: case OP_TLBI_VALE1OSNXS: scope->type = TLBI_VA; scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val)); if (!scope->size) scope->size = SZ_1G; scope->va = tlbi_va_s1_to_va(val) & ~(scope->size - 1); scope->asid = FIELD_GET(TLBIR_ASID_MASK, val); break; case OP_TLBI_ASIDE1: case OP_TLBI_ASIDE1IS: case OP_TLBI_ASIDE1OS: case OP_TLBI_ASIDE1NXS: case OP_TLBI_ASIDE1ISNXS: case OP_TLBI_ASIDE1OSNXS: scope->type = TLBI_ASID; scope->asid = FIELD_GET(TLBIR_ASID_MASK, val); break; case OP_TLBI_VAAE1: case OP_TLBI_VAAE1IS: case OP_TLBI_VAAE1OS: case OP_TLBI_VAAE1NXS: case OP_TLBI_VAAE1ISNXS: case OP_TLBI_VAAE1OSNXS: case OP_TLBI_VAALE1: case OP_TLBI_VAALE1IS: case OP_TLBI_VAALE1OS: case OP_TLBI_VAALE1NXS: case OP_TLBI_VAALE1ISNXS: case OP_TLBI_VAALE1OSNXS: scope->type = TLBI_VAA; scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val)); if (!scope->size) scope->size = SZ_1G; scope->va = tlbi_va_s1_to_va(val) & ~(scope->size - 1); break; case OP_TLBI_RVAE2: case OP_TLBI_RVAE2IS: case OP_TLBI_RVAE2OS: case OP_TLBI_RVAE1: case OP_TLBI_RVAE1IS: case OP_TLBI_RVAE1OS: case OP_TLBI_RVAE2NXS: case OP_TLBI_RVAE2ISNXS: case OP_TLBI_RVAE2OSNXS: case OP_TLBI_RVAE1NXS: case OP_TLBI_RVAE1ISNXS: case OP_TLBI_RVAE1OSNXS: case OP_TLBI_RVALE2: case OP_TLBI_RVALE2IS: case OP_TLBI_RVALE2OS: case OP_TLBI_RVALE1: case OP_TLBI_RVALE1IS: case OP_TLBI_RVALE1OS: case OP_TLBI_RVALE2NXS: case OP_TLBI_RVALE2ISNXS: case OP_TLBI_RVALE2OSNXS: case OP_TLBI_RVALE1NXS: case OP_TLBI_RVALE1ISNXS: case OP_TLBI_RVALE1OSNXS: scope->type = TLBI_VA; scope->va = decode_range_tlbi(val, &scope->size, &scope->asid); break; case OP_TLBI_RVAAE1: case OP_TLBI_RVAAE1IS: case OP_TLBI_RVAAE1OS: case OP_TLBI_RVAAE1NXS: case OP_TLBI_RVAAE1ISNXS: case OP_TLBI_RVAAE1OSNXS: case OP_TLBI_RVAALE1: case OP_TLBI_RVAALE1IS: case OP_TLBI_RVAALE1OS: case OP_TLBI_RVAALE1NXS: case OP_TLBI_RVAALE1ISNXS: case OP_TLBI_RVAALE1OSNXS: scope->type = TLBI_VAA; scope->va = decode_range_tlbi(val, &scope->size, NULL); break; } } void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val) { struct s1e2_tlbi_scope scope = {}; compute_s1_tlbi_range(vcpu, inst, val, &scope); guard(write_lock)(&vcpu->kvm->mmu_lock); invalidate_vncr_va(vcpu->kvm, &scope); } void kvm_nested_s2_wp(struct kvm *kvm) { int i; lockdep_assert_held_write(&kvm->mmu_lock); if (!kvm->arch.nested_mmus_size) return; for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu)); } kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits)); } void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block) { int i; lockdep_assert_held_write(&kvm->mmu_lock); if (!kvm->arch.nested_mmus_size) return; for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block); } kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits)); } void kvm_nested_s2_flush(struct kvm *kvm) { int i; lockdep_assert_held_write(&kvm->mmu_lock); if (!kvm->arch.nested_mmus_size) return; for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu)); } } void kvm_arch_flush_shadow_all(struct kvm *kvm) { int i; for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!WARN_ON(atomic_read(&mmu->refcnt))) kvm_free_stage2_pgd(mmu); } kvfree(kvm->arch.nested_mmus); kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; kvm_uninit_stage2_mmu(kvm); } /* * Dealing with VNCR_EL2 exposed by the *guest* is a complicated matter: * * - We introduce an internal representation of a vcpu-private TLB, * representing the mapping between the guest VA contained in VNCR_EL2, * the IPA the guest's EL2 PTs point to, and the actual PA this lives at. * * - On translation fault from a nested VNCR access, we create such a TLB. * If there is no mapping to describe, the guest inherits the fault. * Crucially, no actual mapping is done at this stage. * * - On vcpu_load() in a non-HYP context with HCR_EL2.NV==1, if the above * TLB exists, we map it in the fixmap for this CPU, and run with it. We * have to respect the permissions dictated by the guest, but not the * memory type (FWB is a must). * * - Note that we usually don't do a vcpu_load() on the back of a fault * (unless we are preempted), so the resolution of a translation fault * must go via a request that will map the VNCR page in the fixmap. * vcpu_load() might as well use the same mechanism. * * - On vcpu_put() in a non-HYP context with HCR_EL2.NV==1, if the TLB was * mapped, we unmap it. Yes it is that simple. The TLB still exists * though, and may be reused at a later load. * * - On permission fault, we simply forward the fault to the guest's EL2. * Get out of my way. * * - On any TLBI for the EL2&0 translation regime, we must find any TLB that * intersects with the TLBI request, invalidate it, and unmap the page * from the fixmap. Because we need to look at all the vcpu-private TLBs, * this requires some wide-ranging locking to ensure that nothing races * against it. This may require some refcounting to avoid the search when * no such TLB is present. * * - On MMU notifiers, we must invalidate our TLB in a similar way, but * looking at the IPA instead. The funny part is that there may not be a * stage-2 mapping for this page if L1 hasn't accessed it using LD/ST * instructions. */ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu) { if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) return 0; vcpu->arch.vncr_tlb = kzalloc_obj(*vcpu->arch.vncr_tlb, GFP_KERNEL_ACCOUNT); if (!vcpu->arch.vncr_tlb) return -ENOMEM; return 0; } static u64 read_vncr_el2(struct kvm_vcpu *vcpu) { return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48); } static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem) { struct kvm_memory_slot *memslot; bool write_fault, writable; unsigned long mmu_seq; struct vncr_tlb *vt; struct page *page; u64 va, pfn, gfn; int ret; vt = vcpu->arch.vncr_tlb; /* * If we're about to walk the EL2 S1 PTs, we must invalidate the * current TLB, as it could be sampled from another vcpu doing a * TLBI *IS. A real CPU wouldn't do that, but we only keep a single * translation, so not much of a choice. * * We also prepare the next walk wilst we're at it. */ scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { invalidate_vncr(vt); vt->wi = (struct s1_walk_info) { .regime = TR_EL20, .as_el0 = false, .pan = false, }; vt->wr = (struct s1_walk_result){}; } guard(srcu)(&vcpu->kvm->srcu); va = read_vncr_el2(vcpu); ret = __kvm_translate_va(vcpu, &vt->wi, &vt->wr, va); if (ret) return ret; write_fault = kvm_is_write_fault(vcpu); mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); gfn = vt->wr.pa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); if (!memslot) return -EFAULT; *is_gmem = kvm_slot_has_gmem(memslot); if (!*is_gmem) { pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0, &writable, &page); if (is_error_noslot_pfn(pfn) || (write_fault && !writable)) return -EFAULT; } else { ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL); if (ret) { kvm_prepare_memory_fault_exit(vcpu, vt->wr.pa, PAGE_SIZE, write_fault, false, false); return ret; } } scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) return -EAGAIN; vt->gva = va; vt->hpa = pfn << PAGE_SHIFT; vt->valid = true; vt->cpu = -1; kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw); } if (vt->wr.pw) mark_page_dirty(vcpu->kvm, gfn); return 0; } static void inject_vncr_perm(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 esr = kvm_vcpu_get_esr(vcpu); /* Adjust the fault level to reflect that of the guest's */ esr &= ~ESR_ELx_FSC; esr |= FIELD_PREP(ESR_ELx_FSC, ESR_ELx_FSC_PERM_L(vt->wr.level)); kvm_inject_nested_sync(vcpu, esr); } static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; lockdep_assert_held_read(&vcpu->kvm->mmu_lock); if (!vt->valid) return false; if (read_vncr_el2(vcpu) != vt->gva) return false; if (vt->wr.nG) return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid; return true; } int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 esr = kvm_vcpu_get_esr(vcpu); WARN_ON_ONCE(!(esr & ESR_ELx_VNCR)); if (kvm_vcpu_abt_issea(vcpu)) return kvm_handle_guest_sea(vcpu); if (esr_fsc_is_permission_fault(esr)) { inject_vncr_perm(vcpu); } else if (esr_fsc_is_translation_fault(esr)) { bool valid, is_gmem = false; int ret; scoped_guard(read_lock, &vcpu->kvm->mmu_lock) valid = kvm_vncr_tlb_lookup(vcpu); if (!valid) ret = kvm_translate_vncr(vcpu, &is_gmem); else ret = -EPERM; switch (ret) { case -EAGAIN: /* Let's try again... */ break; case -ENOMEM: /* * For guest_memfd, this indicates that it failed to * create a folio to back the memory. Inform userspace. */ if (is_gmem) return 0; /* Otherwise, let's try again... */ break; case -EFAULT: case -EIO: case -EHWPOISON: if (is_gmem) return 0; fallthrough; case -EINVAL: case -ENOENT: case -EACCES: /* * Translation failed, inject the corresponding * exception back to EL2. */ BUG_ON(!vt->wr.failed); esr &= ~ESR_ELx_FSC; esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst); kvm_inject_nested_sync(vcpu, esr); break; case -EPERM: /* Hack to deal with POE until we get kernel support */ inject_vncr_perm(vcpu); break; case 0: break; } } else { WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr); } return 1; } static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; pgprot_t prot; guard(preempt)(); guard(read_lock)(&vcpu->kvm->mmu_lock); /* * The request to map VNCR may have raced against some other * event, such as an interrupt, and may not be valid anymore. */ if (is_hyp_ctxt(vcpu)) return; /* * Check that the pseudo-TLB is valid and that VNCR_EL2 still * contains the expected value. If it doesn't, we simply bail out * without a mapping -- a transformed MSR/MRS will generate the * fault and allows us to populate the pseudo-TLB. */ if (!vt->valid) return; if (read_vncr_el2(vcpu) != vt->gva) return; if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid) return; vt->cpu = smp_processor_id(); if (vt->wr.pw && vt->wr.pr) prot = PAGE_KERNEL; else if (vt->wr.pr) prot = PAGE_KERNEL_RO; else prot = PAGE_NONE; /* * We can't map write-only (or no permission at all) in the kernel, * but the guest can do it if using POE, so we'll have to turn a * translation fault into a permission fault at runtime. * FIXME: WO doesn't work at all, need POE support in the kernel. */ if (pgprot_val(prot) != pgprot_val(PAGE_NONE)) { __set_fixmap(vncr_fixmap(vt->cpu), vt->hpa, prot); host_data_set_flag(L1_VNCR_MAPPED); atomic_inc(&vcpu->kvm->arch.vncr_map_count); } } #define has_tgran_2(__r, __sz) \ ({ \ u64 _s1, _s2, _mmfr0 = __r; \ \ _s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \ TGRAN##__sz##_2, _mmfr0); \ \ _s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \ TGRAN##__sz, _mmfr0); \ \ ((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI && \ _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \ (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \ _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI)); \ }) /* * Our emulated CPU doesn't support all the possible features. For the * sake of simplicity (and probably mental sanity), wipe out a number * of feature bits we don't intend to support for the time being. * This list should get updated as new features get added to the NV * support, and new extension to the architecture. */ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val) { u64 orig_val = val; switch (reg) { case SYS_ID_AA64ISAR1_EL1: /* Support everything but LS64 and Spec Invalidation */ val &= ~(ID_AA64ISAR1_EL1_LS64 | ID_AA64ISAR1_EL1_SPECRES); break; case SYS_ID_AA64PFR0_EL1: /* No RME, AMU, MPAM, or S-EL2 */ val &= ~(ID_AA64PFR0_EL1_RME | ID_AA64PFR0_EL1_AMU | ID_AA64PFR0_EL1_MPAM | ID_AA64PFR0_EL1_SEL2 | ID_AA64PFR0_EL1_EL3 | ID_AA64PFR0_EL1_EL2 | ID_AA64PFR0_EL1_EL1 | ID_AA64PFR0_EL1_EL0); /* 64bit only at any EL */ val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP); val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP); val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP); val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP); break; case SYS_ID_AA64PFR1_EL1: /* Only support BTI, SSBS, CSV2_frac */ val &= ~(ID_AA64PFR1_EL1_PFAR | ID_AA64PFR1_EL1_MTEX | ID_AA64PFR1_EL1_THE | ID_AA64PFR1_EL1_GCS | ID_AA64PFR1_EL1_MTE_frac | ID_AA64PFR1_EL1_NMI | ID_AA64PFR1_EL1_SME | ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_MTE); break; case SYS_ID_AA64PFR2_EL1: /* GICv5 is not yet supported for NV */ val &= ~ID_AA64PFR2_EL1_GCIE; break; case SYS_ID_AA64MMFR0_EL1: /* Hide ExS, Secure Memory */ val &= ~(ID_AA64MMFR0_EL1_EXS | ID_AA64MMFR0_EL1_TGRAN4_2 | ID_AA64MMFR0_EL1_TGRAN16_2 | ID_AA64MMFR0_EL1_TGRAN64_2 | ID_AA64MMFR0_EL1_SNSMEM); /* Hide CNTPOFF if present */ val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, ECV, IMP); /* Disallow unsupported S2 page sizes */ switch (PAGE_SIZE) { case SZ_64K: val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, NI); fallthrough; case SZ_16K: val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, NI); fallthrough; case SZ_4K: /* Support everything */ break; } /* * Since we can't support a guest S2 page size smaller * than the host's own page size (due to KVM only * populating its own S2 using the kernel's page * size), advertise the limitation using FEAT_GTG. */ switch (PAGE_SIZE) { case SZ_4K: if (has_tgran_2(orig_val, 4)) val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP); fallthrough; case SZ_16K: if (has_tgran_2(orig_val, 16)) val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP); fallthrough; case SZ_64K: if (has_tgran_2(orig_val, 64)) val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP); break; } /* Cap PARange to 48bits */ val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, PARANGE, 48); break; case SYS_ID_AA64MMFR1_EL1: val &= ~(ID_AA64MMFR1_EL1_CMOW | ID_AA64MMFR1_EL1_nTLBPA | ID_AA64MMFR1_EL1_ETS); /* FEAT_E2H0 implies no VHE */ if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) val &= ~ID_AA64MMFR1_EL1_VH; val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR1_EL1, HAFDBS, AF); break; case SYS_ID_AA64MMFR2_EL1: val &= ~(ID_AA64MMFR2_EL1_BBM | ID_AA64MMFR2_EL1_TTL | GENMASK_ULL(47, 44) | ID_AA64MMFR2_EL1_ST | ID_AA64MMFR2_EL1_CCIDX | ID_AA64MMFR2_EL1_VARange); /* Force TTL support */ val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR2_EL1, TTL, IMP); break; case SYS_ID_AA64MMFR4_EL1: /* * You get EITHER * * - FEAT_VHE without FEAT_E2H0 * - FEAT_NV limited to FEAT_NV2 * - HCR_EL2.NV1 being RES0 * * OR * * - FEAT_E2H0 without FEAT_VHE nor FEAT_NV * * Life is too short for anything else. */ if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) { val = 0; } else { val = SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY); val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI_NV1); } break; case SYS_ID_AA64DFR0_EL1: /* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */ val &= ~(ID_AA64DFR0_EL1_ExtTrcBuff | ID_AA64DFR0_EL1_BRBE | ID_AA64DFR0_EL1_MTPMU | ID_AA64DFR0_EL1_TraceBuffer | ID_AA64DFR0_EL1_TraceFilt | ID_AA64DFR0_EL1_PMSVer | ID_AA64DFR0_EL1_CTX_CMPs | ID_AA64DFR0_EL1_SEBEP | ID_AA64DFR0_EL1_PMSS | ID_AA64DFR0_EL1_TraceVer); /* * FEAT_Debugv8p9 requires support for extended breakpoints / * watchpoints. */ val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8); break; } return val; } u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr, u64 v) { struct resx resx; resx = kvm_get_sysreg_resx(vcpu->kvm, sr); v &= ~resx.res0; v |= resx.res1; return v; } static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, struct resx resx) { BUILD_BUG_ON(!__builtin_constant_p(sr)); BUILD_BUG_ON(sr < __SANITISED_REG_START__); BUILD_BUG_ON(sr >= NR_SYS_REGS); kvm_set_sysreg_resx(kvm, sr, resx); } int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct resx resx; lockdep_assert_held(&kvm->arch.config_lock); if (kvm->arch.sysreg_masks) goto out; kvm->arch.sysreg_masks = kzalloc_obj(*(kvm->arch.sysreg_masks), GFP_KERNEL_ACCOUNT); if (!kvm->arch.sysreg_masks) return -ENOMEM; /* VTTBR_EL2 */ resx = (typeof(resx)){}; if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16)) resx.res0 |= GENMASK(63, 56); if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, CnP, IMP)) resx.res0 |= VTTBR_CNP_BIT; set_sysreg_masks(kvm, VTTBR_EL2, resx); /* VTCR_EL2 */ resx = get_reg_fixed_bits(kvm, VTCR_EL2); set_sysreg_masks(kvm, VTCR_EL2, resx); /* VMPIDR_EL2 */ resx.res0 = GENMASK(63, 40) | GENMASK(30, 24); resx.res1 = BIT(31); set_sysreg_masks(kvm, VMPIDR_EL2, resx); /* HCR_EL2 */ resx = get_reg_fixed_bits(kvm, HCR_EL2); set_sysreg_masks(kvm, HCR_EL2, resx); /* HCRX_EL2 */ resx = get_reg_fixed_bits(kvm, HCRX_EL2); set_sysreg_masks(kvm, HCRX_EL2, resx); /* HFG[RW]TR_EL2 */ resx = get_reg_fixed_bits(kvm, HFGRTR_EL2); set_sysreg_masks(kvm, HFGRTR_EL2, resx); resx = get_reg_fixed_bits(kvm, HFGWTR_EL2); set_sysreg_masks(kvm, HFGWTR_EL2, resx); /* HDFG[RW]TR_EL2 */ resx = get_reg_fixed_bits(kvm, HDFGRTR_EL2); set_sysreg_masks(kvm, HDFGRTR_EL2, resx); resx = get_reg_fixed_bits(kvm, HDFGWTR_EL2); set_sysreg_masks(kvm, HDFGWTR_EL2, resx); /* HFGITR_EL2 */ resx = get_reg_fixed_bits(kvm, HFGITR_EL2); set_sysreg_masks(kvm, HFGITR_EL2, resx); /* HAFGRTR_EL2 - not a lot to see here */ resx = get_reg_fixed_bits(kvm, HAFGRTR_EL2); set_sysreg_masks(kvm, HAFGRTR_EL2, resx); /* HFG[RW]TR2_EL2 */ resx = get_reg_fixed_bits(kvm, HFGRTR2_EL2); set_sysreg_masks(kvm, HFGRTR2_EL2, resx); resx = get_reg_fixed_bits(kvm, HFGWTR2_EL2); set_sysreg_masks(kvm, HFGWTR2_EL2, resx); /* HDFG[RW]TR2_EL2 */ resx = get_reg_fixed_bits(kvm, HDFGRTR2_EL2); set_sysreg_masks(kvm, HDFGRTR2_EL2, resx); resx = get_reg_fixed_bits(kvm, HDFGWTR2_EL2); set_sysreg_masks(kvm, HDFGWTR2_EL2, resx); /* HFGITR2_EL2 */ resx = get_reg_fixed_bits(kvm, HFGITR2_EL2); set_sysreg_masks(kvm, HFGITR2_EL2, resx); /* TCR2_EL2 */ resx = get_reg_fixed_bits(kvm, TCR2_EL2); set_sysreg_masks(kvm, TCR2_EL2, resx); /* SCTLR_EL1 */ resx = get_reg_fixed_bits(kvm, SCTLR_EL1); set_sysreg_masks(kvm, SCTLR_EL1, resx); /* SCTLR_EL2 */ resx = get_reg_fixed_bits(kvm, SCTLR_EL2); set_sysreg_masks(kvm, SCTLR_EL2, resx); /* SCTLR2_ELx */ resx = get_reg_fixed_bits(kvm, SCTLR2_EL1); set_sysreg_masks(kvm, SCTLR2_EL1, resx); resx = get_reg_fixed_bits(kvm, SCTLR2_EL2); set_sysreg_masks(kvm, SCTLR2_EL2, resx); /* MDCR_EL2 */ resx = get_reg_fixed_bits(kvm, MDCR_EL2); set_sysreg_masks(kvm, MDCR_EL2, resx); /* CNTHCTL_EL2 */ resx.res0 = GENMASK(63, 20); resx.res1 = 0; if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RME, IMP)) resx.res0 |= CNTHCTL_CNTPMASK | CNTHCTL_CNTVMASK; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, CNTPOFF)) { resx.res0 |= CNTHCTL_ECV; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, IMP)) resx.res0 |= (CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT | CNTHCTL_EL1NVPCT | CNTHCTL_EL1NVVCT); } if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP)) resx.res0 |= GENMASK(11, 8); set_sysreg_masks(kvm, CNTHCTL_EL2, resx); /* ICH_HCR_EL2 */ resx.res0 = ICH_HCR_EL2_RES0; resx.res1 = ICH_HCR_EL2_RES1; if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS)) resx.res0 |= ICH_HCR_EL2_TDIR; /* No GICv4 is presented to the guest */ resx.res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount; set_sysreg_masks(kvm, ICH_HCR_EL2, resx); /* VNCR_EL2 */ resx.res0 = VNCR_EL2_RES0; resx.res1 = VNCR_EL2_RES1; set_sysreg_masks(kvm, VNCR_EL2, resx); out: for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++) __vcpu_rmw_sys_reg(vcpu, sr, |=, 0); return 0; } void check_nested_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) { struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu; write_lock(&vcpu->kvm->mmu_lock); if (mmu->pending_unmap) { kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true); mmu->pending_unmap = false; } write_unlock(&vcpu->kvm->mmu_lock); } if (kvm_check_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu)) kvm_map_l1_vncr(vcpu); /* Must be last, as may switch context! */ if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu)) kvm_inject_nested_irq(vcpu); } /* * One of the many architectural bugs in FEAT_NV2 is that the guest hypervisor * can write to HCR_EL2 behind our back, potentially changing the exception * routing / masking for even the host context. * * What follows is some slop to (1) react to exception routing / masking and (2) * preserve the pending SError state across translation regimes. */ void kvm_nested_flush_hwstate(struct kvm_vcpu *vcpu) { if (!vcpu_has_nv(vcpu)) return; if (unlikely(vcpu_test_and_clear_flag(vcpu, NESTED_SERROR_PENDING))) kvm_inject_serror_esr(vcpu, vcpu_get_vsesr(vcpu)); } void kvm_nested_sync_hwstate(struct kvm_vcpu *vcpu) { unsigned long *hcr = vcpu_hcr(vcpu); if (!vcpu_has_nv(vcpu)) return; /* * We previously decided that an SError was deliverable to the guest. * Reap the pending state from HCR_EL2 and... */ if (unlikely(__test_and_clear_bit(__ffs(HCR_VSE), hcr))) vcpu_set_flag(vcpu, NESTED_SERROR_PENDING); /* * Re-attempt SError injection in case the deliverability has changed, * which is necessary to faithfully emulate WFI the case of a pending * SError being a wakeup condition. */ if (unlikely(vcpu_test_and_clear_flag(vcpu, NESTED_SERROR_PENDING))) kvm_inject_serror_esr(vcpu, vcpu_get_vsesr(vcpu)); } /* * KVM unconditionally sets most of these traps anyway but use an allowlist * to document the guest hypervisor traps that may take precedence and guard * against future changes to the non-nested trap configuration. */ #define NV_MDCR_GUEST_INCLUDE (MDCR_EL2_TDE | \ MDCR_EL2_TDA | \ MDCR_EL2_TDRA | \ MDCR_EL2_TTRF | \ MDCR_EL2_TPMS | \ MDCR_EL2_TPM | \ MDCR_EL2_TPMCR | \ MDCR_EL2_TDCC | \ MDCR_EL2_TDOSA) void kvm_nested_setup_mdcr_el2(struct kvm_vcpu *vcpu) { u64 guest_mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (is_nested_ctxt(vcpu)) vcpu->arch.mdcr_el2 |= (guest_mdcr & NV_MDCR_GUEST_INCLUDE); /* * In yet another example where FEAT_NV2 is fscking broken, accesses * to MDSCR_EL1 are redirected to the VNCR despite having an effect * at EL2. Use a big hammer to apply sanity. * * Unless of course we have FEAT_FGT, in which case we can precisely * trap MDSCR_EL1. */ else if (!cpus_have_final_cap(ARM64_HAS_FGT)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; } |
| 30 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_H #define _IPV6_H #include <uapi/linux/ipv6.h> #include <linux/cache.h> #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) #define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ struct ipv6_devconf { /* RX & TX fastpath fields. */ __cacheline_group_begin(ipv6_devconf_read_txrx); __s32 disable_ipv6; __s32 hop_limit; __s32 mtu6; __s32 forwarding; __s32 force_forwarding; __s32 disable_policy; __s32 proxy_ndp; __cacheline_group_end(ipv6_devconf_read_txrx); __s32 accept_ra; __s32 accept_redirects; __s32 autoconf; __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; __s32 mldv2_unsolicited_report_interval; __s32 use_tempaddr; __s32 temp_valid_lft; __s32 temp_prefered_lft; __s32 regen_min_advance; __s32 regen_max_retry; __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif __s32 accept_source_route; __s32 accept_ra_from_local; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD __s32 optimistic_dad; __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE atomic_t mc_forwarding; #endif __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; __s32 keep_addr_on_down; __s32 seg6_enabled; #ifdef CONFIG_IPV6_SEG6_HMAC __s32 seg6_require_hmac; #endif __u32 enhanced_dad; __u32 addr_gen_mode; __s32 ndisc_tclass; __s32 rpl_seg_enabled; __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; struct ipv6_params { __s32 disable_ipv6; __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; #include <linux/tcp.h> #include <linux/udp.h> #include <net/inet_sock.h> static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_network_header(skb); } static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_inner_network_header(skb); } static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_transport_header(skb); } static inline unsigned int ipv6_transport_len(const struct sk_buff *skb) { return ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr) - skb_network_header_len(skb); } static inline unsigned int ipv6_payload_len(const struct sk_buff *skb, const struct ipv6hdr *ip6) { u32 len = ntohs(ip6->payload_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb) - sizeof(struct ipv6hdr); } static inline unsigned int skb_ipv6_payload_len(const struct sk_buff *skb) { return ipv6_payload_len(skb, ipv6_hdr(skb)); } #define IPV6_MAXPLEN 65535 static inline void ipv6_set_payload_len(struct ipv6hdr *ip6, unsigned int len) { ip6->payload_len = len <= IPV6_MAXPLEN ? htons(len) : 0; } /* This structure contains results of exthdrs parsing as offsets from skb->nh. */ struct inet6_skb_parm { int iif; __be16 ra; __u16 dst0; __u16 srcrt; __u16 dst1; __u16 lastopt; __u16 nhoff; __u16 flags; #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dsthao; #endif __u16 frag_max_size; __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 #define IP6SKB_MULTIPATH 1024 #define IP6SKB_MCROUTE 2048 }; #if defined(CONFIG_NET_L3_MASTER_DEV) static inline bool ipv6_l3mdev_skb(__u16 flags) { return flags & IP6SKB_L3SLAVE; } #else static inline bool ipv6_l3mdev_skb(__u16 flags) { return false; } #endif #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) #define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb)) static inline int inet6_iif(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags); return l3_slave ? skb->skb_iif : IP6CB(skb)->iif; } static inline bool inet6_is_jumbogram(const struct sk_buff *skb) { return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); } /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline int inet6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) return IP6CB(skb)->iif; #endif return 0; } struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; /* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { /* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */ struct in6_addr saddr; union { struct in6_addr daddr; struct in6_addr final; }; __be32 flow_label; u32 dst_cookie; struct ipv6_txoptions __rcu *opt; s16 hop_limit; u8 pmtudisc; u8 tclass; #ifdef CONFIG_IPV6_SUBTREES bool saddr_cache; #endif bool daddr_cache; u8 mcast_hops; u32 frag_size; int ucast_oif; int mcast_oif; /* pktoption flags */ union { struct { u16 srcrt:1, osrcrt:1, rxinfo:1, rxoinfo:1, rxhlim:1, rxohlim:1, hopopts:1, ohopopts:1, dstopts:1, odstopts:1, rxflow:1, rxtclass:1, rxpmtu:1, rxorigdstaddr:1, recvfragsize:1; /* 1 bits hole */ } bits; u16 all; } rxopt; /* sockopt flags */ u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ u8 min_hopcount; __be32 rcv_flowinfo; struct in6_pktinfo sticky_pktinfo; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; }; /* We currently use available bits from inet_sk(sk)->inet_flags, * this could change in the future. */ #define inet6_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_set_bit(nr, sk) \ set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_clear_bit(nr, sk) \ clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ struct raw6_sock { /* inet_sock has to be the first member of raw6_sock */ struct inet_sock inet; __u32 checksum; /* perform checksum */ __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; struct numa_drop_counters drop_counters; struct ipv6_pinfo inet6; }; struct udp6_sock { struct udp_sock udp; struct ipv6_pinfo inet6; }; struct tcp6_sock { struct tcp_sock tcp; struct ipv6_pinfo inet6; }; extern int inet6_sk_rebuild_header(struct sock *sk); struct tcp6_timewait_sock { struct tcp_timewait_sock tcp6tw_tcp; }; #if IS_ENABLED(CONFIG_IPV6) extern int disable_ipv6_mod; static inline bool ipv6_mod_enabled(void) { return disable_ipv6_mod == 0; } static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } #define raw6_sk(ptr) container_of_const(ptr, struct raw6_sock, inet.sk) #define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk) { if (sk->sk_family == AF_INET6) return &sk->sk_v6_rcv_saddr; return NULL; } static inline int inet_v6_ipv6only(const struct sock *sk) { /* ipv6only field is at same position for timewait and other sockets */ return ipv6_only_sock(sk); } #else #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 static inline bool ipv6_mod_enabled(void) { return false; } static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { return NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ |
| 119 | 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 | /* * 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/nodemask.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 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 */ #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif #if defined(topology_book_id) && defined(topology_book_cpumask) #define TOPOLOGY_BOOK_SYSFS #endif #if defined(topology_drawer_id) && defined(topology_drawer_cpumask) #define TOPOLOGY_DRAWER_SYSFS #endif #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_cluster_id #define topology_cluster_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_book_id #define topology_book_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_ppin #define topology_ppin(cpu) ((void)(cpu), 0ull) #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_cluster_cpumask #define topology_cluster_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_book_cpumask #define topology_book_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_drawer_cpumask #define topology_drawer_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 #ifndef topology_is_primary_thread static inline bool topology_is_primary_thread(unsigned int cpu) { /* * When disabling SMT, the primary thread of the SMT will remain * enabled/active. Architectures that have a special primary thread * (e.g. x86) need to override this function. Otherwise the first * thread in the SMT can be made the primary thread. * * The sibling cpumask of an offline CPU always contains the CPU * itself on architectures using the implementation of * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology. * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for * building their topology have to check whether to use this default * implementation or to override it. */ return cpu == cpumask_first(topology_sibling_cpumask(cpu)); } #define topology_is_primary_thread topology_is_primary_thread #endif static inline const struct cpumask *cpu_node_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #ifdef CONFIG_NUMA int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * sched_numa_hop_mask(unsigned int node, unsigned int hops) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NUMA */ /** * for_each_node_numadist() - iterate over nodes in increasing distance * order, starting from a given node * @node: the iteration variable and the starting node. * @unvisited: a nodemask to keep track of the unvisited nodes. * * This macro iterates over NUMA node IDs in increasing distance from the * starting @node and yields MAX_NUMNODES when all the nodes have been * visited. * * Note that by the time the loop completes, the @unvisited nodemask will * be fully cleared, unless the loop exits early. * * The difference between for_each_node() and for_each_node_numadist() is * that the former allows to iterate over nodes in numerical order, whereas * the latter iterates over nodes in increasing order of distance. * * This complexity of this iterator is O(N^2), where N represents the * number of nodes, as each iteration involves scanning all nodes to * find the one with the shortest distance. * * Requires rcu_lock to be held. */ #define for_each_node_numadist(node, unvisited) \ for (int __start = (node), \ (node) = nearest_node_nodemask((__start), &(unvisited)); \ (node) < MAX_NUMNODES; \ node_clear((node), (unvisited)), \ (node) = nearest_node_nodemask((__start), &(unvisited))) /** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE. */ #define for_each_numa_hop_mask(mask, node) \ for (unsigned int __hops = 0; \ mask = (node != NUMA_NO_NODE || __hops) ? \ sched_numa_hop_mask(node, __hops) : \ cpu_online_mask, \ !IS_ERR_OR_NULL(mask); \ __hops++) DECLARE_PER_CPU(unsigned long, cpu_scale); static inline unsigned long topology_get_cpu_scale(int cpu) { return per_cpu(cpu_scale, cpu); } void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); #endif /* _LINUX_TOPOLOGY_H */ |
| 1405 1412 1406 1407 1411 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/domain.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/rculist.h> /* Variables definitions.*/ /* The initial domain. */ struct tomoyo_domain_info tomoyo_kernel_domain; /** * tomoyo_update_policy - Update an entry for exception policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)) { int error = param->is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_head *entry; struct list_head *list = param->list; if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; error = 0; break; } if (error && !param->is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); return error; } /** * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { return a->type == b->type && a->cond == b->cond; } /** * tomoyo_update_domain - Update an entry for domain policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * @merge_duplicate: Callback function to merge duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate)(struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)) { const bool is_delete = param->is_delete; int error = is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_info *entry; struct list_head * const list = param->list; if (param->data[0]) { new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; /* * Domain transition preference is allowed for only * "file execute" entries. */ if (new_entry->cond->transit && !(new_entry->type == TOMOYO_TYPE_PATH_ACL && container_of(new_entry, struct tomoyo_path_acl, head) ->perm == 1 << TOMOYO_TYPE_EXECUTE)) goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; if (merge_duplicate) entry->is_deleted = merge_duplicate(entry, new_entry, is_delete); else entry->is_deleted = is_delete; error = 0; break; } if (error && !is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_condition(new_entry->cond); return error; } /** * tomoyo_check_acl - Do permission check. * * @r: Pointer to "struct tomoyo_request_info". * @check_entry: Callback function to check type specific parameters. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)) { const struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; const struct list_head *list = &domain->acl_info_list; u16 i = 0; retry: list_for_each_entry_rcu(ptr, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) continue; if (!tomoyo_condition(r, ptr->cond)) continue; r->matched_acl = ptr; r->granted = true; return; } for (; i < TOMOYO_MAX_ACL_GROUPS; i++) { if (!test_bit(i, domain->group)) continue; list = &domain->ns->acl_group[i++]; goto retry; } r->granted = false; } /* The list for "struct tomoyo_domain_info". */ LIST_HEAD(tomoyo_domain_list); /** * tomoyo_last_word - Get last component of a domainname. * * @name: Domainname to check. * * Returns the last word of @domainname. */ static const char *tomoyo_last_word(const char *name) { const char *cp = strrchr(name, ' '); if (cp) return cp + 1; return name; } /** * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_transition_control *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_transition_control *p2 = container_of(b, typeof(*p2), head); return p1->type == p2->type && p1->is_last_name == p2->is_last_name && p1->domainname == p2->domainname && p1->program == p2->program; } /** * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this entry. * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type) { struct tomoyo_transition_control e = { .type = type }; int error = param->is_delete ? -ENOENT : -ENOMEM; char *program = param->data; char *domainname = strstr(program, " from "); if (domainname) { *domainname = '\0'; domainname += 6; } else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP || type == TOMOYO_TRANSITION_CONTROL_KEEP) { domainname = program; program = NULL; } if (program && strcmp(program, "any")) { if (!tomoyo_correct_path(program)) return -EINVAL; e.program = tomoyo_get_name(program); if (!e.program) goto out; } if (domainname && strcmp(domainname, "any")) { if (!tomoyo_correct_domain(domainname)) { if (!tomoyo_correct_path(domainname)) goto out; e.is_last_name = true; } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) goto out; } param->list = ¶m->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_transition_control); out: tomoyo_put_name(e.domainname); tomoyo_put_name(e.program); return error; } /** * tomoyo_scan_transition - Try to find specific domain transition type. * * @list: Pointer to "struct list_head". * @domainname: The name of current domain. * @program: The name of requested program. * @last_name: The last component of @domainname. * @type: One of values in "enum tomoyo_transition_type". * * Returns true if found one, false otherwise. * * Caller holds tomoyo_read_lock(). */ static inline bool tomoyo_scan_transition (const struct list_head *list, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program, const char *last_name, const enum tomoyo_transition_type type) { const struct tomoyo_transition_control *ptr; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { if (!ptr->is_last_name) { if (ptr->domainname != domainname) continue; } else { /* * Use direct strcmp() since this is * unlikely used. */ if (strcmp(ptr->domainname->name, last_name)) continue; } } if (ptr->program && tomoyo_pathcmp(ptr->program, program)) continue; return true; } return false; } /** * tomoyo_transition_type - Get domain transition type. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @domainname: The name of current domain. * @program: The name of requested program. * * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if * executing @program reinitializes domain transition within that namespace, * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname , * others otherwise. * * Caller holds tomoyo_read_lock(). */ static enum tomoyo_transition_type tomoyo_transition_type (const struct tomoyo_policy_namespace *ns, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program) { const char *last_name = tomoyo_last_word(domainname->name); enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET; while (type < TOMOYO_MAX_TRANSITION_TYPE) { const struct list_head * const list = &ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; if (!tomoyo_scan_transition(list, domainname, program, last_name, type)) { type++; continue; } if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET && type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE) break; /* * Do not check for reset_domain if no_reset_domain matched. * Do not check for initialize_domain if no_initialize_domain * matched. */ type++; type++; } return type; } /** * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2), head); return p1->original_name == p2->original_name && p1->aggregated_name == p2->aggregated_name; } /** * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_aggregator(struct tomoyo_acl_param *param) { struct tomoyo_aggregator e = { }; int error = param->is_delete ? -ENOENT : -ENOMEM; const char *original_name = tomoyo_read_token(param); const char *aggregated_name = tomoyo_read_token(param); if (!tomoyo_correct_word(original_name) || !tomoyo_correct_path(aggregated_name)) return -EINVAL; e.original_name = tomoyo_get_name(original_name); e.aggregated_name = tomoyo_get_name(aggregated_name); if (!e.original_name || !e.aggregated_name || e.aggregated_name->is_patterned) /* No patterns allowed. */ goto out; param->list = ¶m->ns->policy_list[TOMOYO_ID_AGGREGATOR]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_aggregator); out: tomoyo_put_name(e.original_name); tomoyo_put_name(e.aggregated_name); return error; } /** * tomoyo_find_namespace - Find specified namespace. * * @name: Name of namespace to find. * @len: Length of @name. * * Returns pointer to "struct tomoyo_policy_namespace" if found, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ static struct tomoyo_policy_namespace *tomoyo_find_namespace (const char *name, const unsigned int len) { struct tomoyo_policy_namespace *ns; list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { if (strncmp(name, ns->name, len) || (name[len] && name[len] != ' ')) continue; return ns; } return NULL; } /** * tomoyo_assign_namespace - Create a new namespace. * * @domainname: Name of namespace to create. * * Returns pointer to "struct tomoyo_policy_namespace" on success, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname) { struct tomoyo_policy_namespace *ptr; struct tomoyo_policy_namespace *entry; const char *cp = domainname; unsigned int len = 0; while (*cp && *cp++ != ' ') len++; ptr = tomoyo_find_namespace(domainname, len); if (ptr) return ptr; if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname)) return NULL; entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = tomoyo_find_namespace(domainname, len); if (!ptr && tomoyo_memory_ok(entry)) { char *name = (char *) (entry + 1); ptr = entry; memmove(name, domainname, len); name[len] = '\0'; entry->name = name; tomoyo_init_policy_namespace(entry); entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_namespace_jump - Check for namespace jump. * * @domainname: Name of domain. * * Returns true if namespace differs, false otherwise. */ static bool tomoyo_namespace_jump(const char *domainname) { const char *namespace = tomoyo_current_namespace()->name; const int len = strlen(namespace); return strncmp(domainname, namespace, len) || (domainname[len] && domainname[len] != ' '); } /** * tomoyo_assign_domain - Create a domain or a namespace. * * @domainname: The name of domain. * @transit: True if transit to domain found or created. * * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit) { struct tomoyo_domain_info e = { }; struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname); bool created = false; if (entry) { if (transit) { /* * Since namespace is created at runtime, profiles may * not be created by the moment the process transits to * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ if (tomoyo_policy_loaded && !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; } /* Requested domain does not exist. */ /* Don't create requested domain if domainname is invalid. */ if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_correct_domain(domainname)) return NULL; /* * Since definition of profiles and acl_groups may differ across * namespaces, do not inherit "use_profile" and "use_group" settings * by automatically creating requested domain upon domain transition. */ if (transit && tomoyo_namespace_jump(domainname)) return NULL; e.ns = tomoyo_assign_namespace(domainname); if (!e.ns) return NULL; /* * "use_profile" and "use_group" settings for automatically created * domains are inherited from current domain. These are 0 for manually * created domains. */ if (transit) { const struct tomoyo_domain_info *domain = tomoyo_domain(); e.profile = domain->profile; memcpy(e.group, domain->group, sizeof(e.group)); } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) return NULL; if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; entry = tomoyo_find_domain(domainname); if (!entry) { entry = tomoyo_commit_ok(&e, sizeof(e)); if (entry) { INIT_LIST_HEAD(&entry->acl_info_list); list_add_tail_rcu(&entry->list, &tomoyo_domain_list); created = true; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_name(e.domainname); if (entry && transit) { if (created) { struct tomoyo_request_info r; int i; tomoyo_init_request_info(&r, entry, TOMOYO_MAC_FILE_EXECUTE); r.granted = false; tomoyo_write_log(&r, "use_profile %u\n", entry->profile); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) if (test_bit(i, entry->group)) tomoyo_write_log(&r, "use_group %u\n", i); tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** * tomoyo_environ - Check permission for environment variable names. * * @ee: Pointer to "struct tomoyo_execve". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_environ(struct tomoyo_execve *ee) __must_hold_shared(&tomoyo_ss) { struct tomoyo_request_info *r = &ee->r; struct linux_binprm *bprm = ee->bprm; /* env_page.data is allocated by tomoyo_dump_page(). */ struct tomoyo_page_dump env_page = { }; char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; int error = -ENOMEM; ee->r.type = TOMOYO_MAC_ENVIRON; ee->r.profile = r->domain->profile; ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, TOMOYO_MAC_ENVIRON); if (!r->mode || !envp_count) return 0; arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!arg_ptr) goto out; while (error == -ENOMEM) { if (!tomoyo_dump_page(bprm, pos, &env_page)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (argv_count && offset < PAGE_SIZE) { if (!env_page.data[offset++]) argv_count--; } if (argv_count) { offset = 0; continue; } while (offset < PAGE_SIZE) { const unsigned char c = env_page.data[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '=') { arg_ptr[arg_len++] = '\0'; } else if (c == '\\') { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = '\\'; } else if (c > ' ' && c < 127) { arg_ptr[arg_len++] = c; } else { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = (c >> 6) + '0'; arg_ptr[arg_len++] = ((c >> 3) & 7) + '0'; arg_ptr[arg_len++] = (c & 7) + '0'; } } else { arg_ptr[arg_len] = '\0'; } if (c) continue; if (tomoyo_env_perm(r, arg_ptr)) { error = -EPERM; break; } if (!--envp_count) { error = 0; break; } arg_len = 0; } offset = 0; } out: if (r->mode != TOMOYO_CONFIG_ENFORCING) error = 0; kfree(env_page.data); kfree(arg_ptr); return error; } /** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_find_next_domain(struct linux_binprm *bprm) { struct tomoyo_domain_info *old_domain = tomoyo_domain(); struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; bool reject_on_transition_failure = false; const struct tomoyo_path_info *candidate; struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc_obj(*ee, GFP_NOFS); if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!ee->tmp) { kfree(ee); return -ENOMEM; } /* ee->dump->data is allocated by tomoyo_dump_page(). */ tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE); ee->r.ee = ee; ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* * Get symlink's pathname of program, but fallback to realpath if * symlink's pathname does not exist or symlink's pathname refers * to proc filesystem (e.g. /dev/fd/<num> or /proc/self/fd/<num> ). */ exename.name = tomoyo_realpath_nofollow(original_name); if (exename.name && !strncmp(exename.name, "proc:/", 6)) { kfree(exename.name); exename.name = NULL; } if (!exename.name) { exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) goto out; /* * To be able to specify domainnames with wildcards, use the * pathname specified in the policy (which may contain * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ if (ee->r.param.path.matched_path) candidate = ee->r.param.path.matched_path; /* * Check for domain transition preference if "file execute" matched. * If preference is given, make execve() fail if domain transition * has failed, for domain transition preference should be used with * destination domain defined. */ if (ee->transition) { const char *domainname = ee->transition->name; reject_on_transition_failure = true; if (!strcmp(domainname, "keep")) goto force_keep_domain; if (!strcmp(domainname, "child")) goto force_child_domain; if (!strcmp(domainname, "reset")) goto force_reset_domain; if (!strcmp(domainname, "initialize")) goto force_initialize_domain; if (!strcmp(domainname, "parent")) { char *cp; strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE); cp = strrchr(ee->tmp, ' '); if (cp) *cp = '\0'; } else if (*domainname == '<') strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE); else snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, domainname); goto force_jump_domain; } /* * No domain transition preference specified. * Calculate domain to transit to. */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: force_reset_domain: /* Transit to the root of specified namespace. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", candidate->name); /* * Make execve() fail if domain transition across namespaces * has failed. */ reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: force_keep_domain: /* Keep current domain. */ domain = old_domain; break; default: if (old_domain == &tomoyo_kernel_domain && !tomoyo_policy_loaded) { /* * Needn't to transit from kernel domain before * starting /sbin/init. But transit from kernel domain * if executing initializers because they might start * before /sbin/init. */ domain = old_domain; break; } force_child_domain: /* Normal domain transition. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, candidate->name); break; } force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) retval = 0; else if (reject_on_transition_failure) { pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp); retval = -ENOMEM; } else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING) retval = -ENOMEM; else { retval = 0; if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) { old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true; ee->r.granted = false; tomoyo_write_log(&ee->r, "%s", tomoyo_dif [TOMOYO_DIF_TRANSITION_FAILED]); pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp); } } out: if (!domain) domain = old_domain; /* Update reference count on "struct tomoyo_domain_info". */ { struct tomoyo_task *s = tomoyo_task(current); s->old_domain_info = s->domain_info; s->domain_info = domain; atomic_inc(&domain->users); } kfree(exename.name); if (!retval) { ee->r.domain = domain; retval = tomoyo_environ(ee); } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); return retval; } /** * tomoyo_dump_page - Dump a page to buffer. * * @bprm: Pointer to "struct linux_binprm". * @pos: Location to dump. * @dump: Pointer to "struct tomoyo_page_dump". * * Returns true on success, false otherwise. */ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; #ifdef CONFIG_MMU int ret; #endif /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) return false; } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around * in the argv/environment of the new process * (represented by bprm). */ mmap_read_lock(bprm->mm); ret = get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL); mmap_read_unlock(bprm->mm); if (ret <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; char *kaddr = kmap_local_page(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); kunmap_local(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU put_page(page); #endif return true; } |
| 261 261 261 260 261 259 261 260 261 261 258 1 261 260 262 264 264 224 225 225 262 264 264 225 225 58 58 58 57 58 58 58 58 57 58 261 261 260 261 260 261 261 261 259 261 261 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/switch.h> #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/percpu.h> #include <uapi/linux/psci.h> #include <kvm/arm_psci.h> #include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> #include <asm/thread_info.h> #include <asm/vectors.h> /* VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); /* * HCR_EL2 bits that the NV guest can freely change (no RES0/RES1 * semantics, irrespective of the configuration), but that cannot be * applied to the actual HW as things would otherwise break badly. * * - TGE: we want the guest to use EL1, which is incompatible with * this bit being set * * - API/APK: they are already accounted for by vcpu_load(), and can * only take effect across a load/put cycle (such as ERET) * * - FIEN: no way we let a guest have access to the RAS "Common Fault * Injection" thing, whatever that does */ #define NV_HCR_GUEST_EXCLUDE (HCR_TGE | HCR_API | HCR_APK | HCR_FIEN) static u64 __compute_hcr(struct kvm_vcpu *vcpu) { u64 guest_hcr, hcr = vcpu->arch.hcr_el2; if (!vcpu_has_nv(vcpu)) return hcr; /* * We rely on the invariant that a vcpu entered from HYP * context must also exit in the same context, as only an ERET * instruction can kick us out of it, and we obviously trap * that sucker. PSTATE.M will get fixed-up on exit. */ if (is_hyp_ctxt(vcpu)) { host_data_set_flag(VCPU_IN_HYP_CONTEXT); hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB; if (!vcpu_el2_e2h_is_set(vcpu)) hcr |= HCR_NV1; /* * Nothing in HCR_EL2 should impact running in hypervisor * context, apart from bits we have defined as RESx (E2H, * HCD and co), or that cannot be set directly (the EXCLUDE * bits). Given that we OR the guest's view with the host's, * we can use the 0 value as the starting point, and only * use the config-driven RES1 bits. */ guest_hcr = kvm_vcpu_apply_reg_masks(vcpu, HCR_EL2, 0); write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2); } else { host_data_clear_flag(VCPU_IN_HYP_CONTEXT); guest_hcr = __vcpu_sys_reg(vcpu, HCR_EL2); if (guest_hcr & HCR_NV) { u64 va = __fix_to_virt(vncr_fixmap(smp_processor_id())); /* Inherit the low bits from the actual register */ va |= __vcpu_sys_reg(vcpu, VNCR_EL2) & GENMASK(PAGE_SHIFT - 1, 0); write_sysreg_s(va, SYS_VNCR_EL2); /* Force NV2 in case the guest is forgetful... */ guest_hcr |= HCR_NV2; } /* * Exclude the guest's TWED configuration if it hasn't set TWE * to avoid potentially delaying traps for the host. */ if (!(guest_hcr & HCR_TWE)) guest_hcr &= ~(HCR_EL2_TWEDEn | HCR_EL2_TWEDEL); } BUG_ON(host_data_test_flag(VCPU_IN_HYP_CONTEXT) && host_data_test_flag(L1_VNCR_MAPPED)); return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE); } static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; ___activate_traps(vcpu, __compute_hcr(vcpu)); if (has_cntpoff()) { struct timer_map map; get_timer_map(vcpu, &map); /* * We're entrering the guest. Reload the correct * values from memory now that TGE is clear. */ if (map.direct_ptimer == vcpu_ptimer(vcpu)) val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); if (map.direct_ptimer == vcpu_hptimer(vcpu)) val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); if (map.direct_ptimer) { write_sysreg_el0(val, SYS_CNTP_CVAL); isb(); } } __activate_cptr_traps(vcpu); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); } NOKPROBE_SYMBOL(__activate_traps); static void __deactivate_traps(struct kvm_vcpu *vcpu) { const char *host_vectors = vectors; ___deactivate_traps(vcpu); write_sysreg_hcr(HCR_HOST_VHE_FLAGS); if (has_cntpoff()) { struct timer_map map; u64 val, offset; get_timer_map(vcpu, &map); /* * We're exiting the guest. Save the latest CVAL value * to memory and apply the offset now that TGE is set. */ val = read_sysreg_el0(SYS_CNTP_CVAL); if (map.direct_ptimer == vcpu_ptimer(vcpu)) __vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, val); if (map.direct_ptimer == vcpu_hptimer(vcpu)) __vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, val); offset = read_sysreg_s(SYS_CNTPOFF_EL2); if (map.direct_ptimer && offset) { write_sysreg_el0(val + offset, SYS_CNTP_CVAL); isb(); } } /* * ARM errata 1165522 and 1530923 require the actual execution of the * above before we can switch to the EL2/EL0 translation regime used by * the host. */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); __deactivate_cptr_traps(vcpu); if (!arm64_kernel_unmapped_at_el0()) host_vectors = __this_cpu_read(this_cpu_vector); write_sysreg(host_vectors, vbar_el1); } NOKPROBE_SYMBOL(__deactivate_traps); /* * Disable IRQs in __vcpu_{load,put}_{activate,deactivate}_traps() to * prevent a race condition between context switching of PMUSERENR_EL0 * in __{activate,deactivate}_traps_common() and IPIs that attempts to * update PMUSERENR_EL0. See also kvm_set_pmuserenr(). */ static void __vcpu_load_activate_traps(struct kvm_vcpu *vcpu) { unsigned long flags; local_irq_save(flags); __activate_traps_common(vcpu); local_irq_restore(flags); } static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu) { unsigned long flags; local_irq_save(flags); __deactivate_traps_common(vcpu); local_irq_restore(flags); } void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu) { host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu; __vcpu_load_switch_sysregs(vcpu); __vcpu_load_activate_traps(vcpu); __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch); } void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu) { __vcpu_put_deactivate_traps(vcpu); __vcpu_put_switch_sysregs(vcpu); host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL; } static u64 compute_emulated_cntx_ctl_el0(struct kvm_vcpu *vcpu, enum vcpu_sysreg reg) { unsigned long ctl; u64 cval, cnt; bool stat; switch (reg) { case CNTP_CTL_EL0: cval = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); ctl = __vcpu_sys_reg(vcpu, CNTP_CTL_EL0); cnt = compute_counter_value(vcpu_ptimer(vcpu)); break; case CNTV_CTL_EL0: cval = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); ctl = __vcpu_sys_reg(vcpu, CNTV_CTL_EL0); cnt = compute_counter_value(vcpu_vtimer(vcpu)); break; default: BUG(); } stat = cval <= cnt; __assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &ctl, stat); return ctl; } static bool kvm_hyp_handle_timer(struct kvm_vcpu *vcpu, u64 *exit_code) { u64 esr, val; /* * Having FEAT_ECV allows for a better quality of timer emulation. * However, this comes at a huge cost in terms of traps. Try and * satisfy the reads from guest's hypervisor context without * returning to the kernel if we can. */ if (!is_hyp_ctxt(vcpu)) return false; esr = kvm_vcpu_get_esr(vcpu); if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) != ESR_ELx_SYS64_ISS_DIR_READ) return false; switch (esr_sys64_to_sysreg(esr)) { case SYS_CNTP_CTL_EL02: val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0); break; case SYS_CNTP_CTL_EL0: if (vcpu_el2_e2h_is_set(vcpu)) val = read_sysreg_el0(SYS_CNTP_CTL); else val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0); break; case SYS_CNTP_CVAL_EL02: val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); break; case SYS_CNTP_CVAL_EL0: if (vcpu_el2_e2h_is_set(vcpu)) { val = read_sysreg_el0(SYS_CNTP_CVAL); if (!has_cntpoff()) val -= timer_get_offset(vcpu_hptimer(vcpu)); } else { val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); } break; case SYS_CNTPCT_EL0: case SYS_CNTPCTSS_EL0: val = compute_counter_value(vcpu_hptimer(vcpu)); break; case SYS_CNTV_CTL_EL02: val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0); break; case SYS_CNTV_CTL_EL0: if (vcpu_el2_e2h_is_set(vcpu)) val = read_sysreg_el0(SYS_CNTV_CTL); else val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0); break; case SYS_CNTV_CVAL_EL02: val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); break; case SYS_CNTV_CVAL_EL0: if (vcpu_el2_e2h_is_set(vcpu)) val = read_sysreg_el0(SYS_CNTV_CVAL); else val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); break; case SYS_CNTVCT_EL0: case SYS_CNTVCTSS_EL0: val = compute_counter_value(vcpu_hvtimer(vcpu)); break; default: return false; } vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); __kvm_skip_instr(vcpu); return true; } static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) { u64 esr = kvm_vcpu_get_esr(vcpu); u64 spsr, elr, mode; /* * Going through the whole put/load motions is a waste of time * if this is a VHE guest hypervisor returning to its own * userspace, or the hypervisor performing a local exception * return. No need to save/restore registers, no need to * switch S2 MMU. Just do the canonical ERET. * * Unless the trap has to be forwarded further down the line, * of course... */ if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) || (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_ERET)) return false; spsr = read_sysreg_el1(SYS_SPSR); mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT); switch (mode) { case PSR_MODE_EL0t: if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu))) return false; break; case PSR_MODE_EL2t: mode = PSR_MODE_EL1t; break; case PSR_MODE_EL2h: mode = PSR_MODE_EL1h; break; default: return false; } /* If ERETAx fails, take the slow path */ if (esr_iss_is_eretax(esr)) { if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr))) return false; } else { elr = read_sysreg_el1(SYS_ELR); } spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; write_sysreg_el2(spsr, SYS_SPSR); write_sysreg_el2(elr, SYS_ELR); return true; } static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) { int ret = -EINVAL; u32 instr; u64 val; /* * Ideally, we would never trap on EL2 S1 TLB invalidations using * the EL1 instructions when the guest's HCR_EL2.{E2H,TGE}=={1,1}. * But "thanks" to FEAT_NV2, we don't trap writes to HCR_EL2, * meaning that we can't track changes to the virtual TGE bit. So we * have to leave HCR_EL2.TTLB set on the host. Oopsie... * * Try and handle these invalidation as quickly as possible, without * fully exiting. Note that we don't need to consider any forwarding * here, as having E2H+TGE set is the very definition of being * InHost. * * For the lesser hypervisors out there that have failed to get on * with the VHE program, we can also handle the nVHE style of EL2 * invalidation. */ if (!(is_hyp_ctxt(vcpu))) return false; instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); if ((kvm_supported_tlbi_s1e1_op(vcpu, instr) && vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) || kvm_supported_tlbi_s1e2_op (vcpu, instr)) ret = __kvm_tlbi_s1e2(NULL, val, instr); if (ret) return false; /* * If we have to check for any VNCR mapping being invalidated, * go back to the slow path for further processing. */ if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu) && atomic_read(&vcpu->kvm->arch.vncr_map_count)) return false; __kvm_skip_instr(vcpu); return true; } static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code) { u64 esr = kvm_vcpu_get_esr(vcpu); int rt; if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1) return false; rt = kvm_vcpu_sys_get_rt(vcpu); if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) { vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2)); } else { vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2); __activate_cptr_traps(vcpu); } __kvm_skip_instr(vcpu); return true; } static bool kvm_hyp_handle_zcr_el2(struct kvm_vcpu *vcpu, u64 *exit_code) { u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); if (!vcpu_has_nv(vcpu)) return false; if (sysreg != SYS_ZCR_EL2) return false; if (guest_owns_fp_regs()) return false; /* * ZCR_EL2 traps are handled in the slow path, with the expectation * that the guest's FP context has already been loaded onto the CPU. * * Load the guest's FP context and unconditionally forward to the * slow path for handling (i.e. return false). */ kvm_hyp_handle_fpsimd(vcpu, exit_code); return false; } static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code) { if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code)) return true; if (kvm_hyp_handle_timer(vcpu, exit_code)) return true; if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code)) return true; if (kvm_hyp_handle_zcr_el2(vcpu, exit_code)) return true; return kvm_hyp_handle_sysreg(vcpu, exit_code); } static bool kvm_hyp_handle_impdef(struct kvm_vcpu *vcpu, u64 *exit_code) { u64 iss; if (!cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) return false; /* * Compute a synthetic ESR for a sysreg trap. Conveniently, AFSR1_EL2 * is populated with a correct ISS for a sysreg trap. These fruity * parts are 64bit only, so unconditionally set IL. */ iss = ESR_ELx_ISS(read_sysreg_s(SYS_AFSR1_EL2)); vcpu->arch.fault.esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SYS64) | FIELD_PREP(ESR_ELx_ISS_MASK, iss) | ESR_ELx_IL; return false; } static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, [ESR_ELx_EC_SYS64] = kvm_hyp_handle_sysreg_vhe, [ESR_ELx_EC_SVE] = kvm_hyp_handle_fpsimd, [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, [ESR_ELx_EC_ERET] = kvm_hyp_handle_eret, [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, /* Apple shenanigans */ [0x3F] = kvm_hyp_handle_impdef, }; static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { synchronize_vcpu_pstate(vcpu); /* * If we were in HYP context on entry, adjust the PSTATE view * so that the usual helpers work correctly. This enforces our * invariant that the guest's HYP context status is preserved * across a run. */ if (vcpu_has_nv(vcpu) && unlikely(host_data_test_flag(VCPU_IN_HYP_CONTEXT))) { u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); switch (mode) { case PSR_MODE_EL1t: mode = PSR_MODE_EL2t; break; case PSR_MODE_EL1h: mode = PSR_MODE_EL2h; break; } *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); *vcpu_cpsr(vcpu) |= mode; } /* Apply extreme paranoia! */ BUG_ON(vcpu_has_nv(vcpu) && !!host_data_test_flag(VCPU_IN_HYP_CONTEXT) != is_hyp_ctxt(vcpu)); return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); } /* Switch to the guest for VHE systems running in EL2 */ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; u64 exit_code; host_ctxt = host_data_ptr(host_ctxt); guest_ctxt = &vcpu->arch.ctxt; fpsimd_lazy_switch_to_guest(vcpu); sysreg_save_host_state_vhe(host_ctxt); /* * Note that ARM erratum 1165522 requires us to configure both stage 1 * and stage 2 translation for the guest context before we clear * HCR_EL2.TGE. The stage 1 and stage 2 guest context has already been * loaded on the CPU in kvm_vcpu_load_vhe(). */ __activate_traps(vcpu); __kvm_adjust_pc(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); do { /* Jump in the fire! */ exit_code = __guest_enter(vcpu); /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); sysreg_save_guest_state_vhe(guest_ctxt); __deactivate_traps(vcpu); sysreg_restore_host_state_vhe(host_ctxt); __debug_switch_to_host(vcpu); /* * Ensure that all system register writes above have taken effect * before returning to the host. In VHE mode, CPTR traps for * FPSIMD/SVE/SME also apply to EL2, so FPSIMD/SVE/SME state must be * manipulated after the ISB. */ isb(); fpsimd_lazy_switch_to_host(vcpu); if (guest_owns_fp_regs()) __fpsimd_save_fpexc32(vcpu); return exit_code; } NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); int __kvm_vcpu_run(struct kvm_vcpu *vcpu) { int ret; local_daif_mask(); /* * Having IRQs masked via PMR when entering the guest means the GIC * will not signal the CPU of interrupts of lower priority, and the * only way to get out will be via guest exceptions. * Naturally, we want to avoid this. * * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ pmr_sync(); ret = __kvm_vcpu_run_vhe(vcpu); /* * local_daif_restore() takes care to properly restore PSTATE.DAIF * and the GIC PMR if the host is using IRQ priorities. */ local_daif_restore(DAIF_PROCCTX_NOIRQ); return ret; } static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par) { struct kvm_cpu_context *host_ctxt; struct kvm_vcpu *vcpu; host_ctxt = host_data_ptr(host_ctxt); vcpu = host_ctxt->__hyp_running_vcpu; __deactivate_traps(vcpu); sysreg_restore_host_state_vhe(host_ctxt); panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n", spsr, elr, read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR), read_sysreg(hpfar_el2), par, vcpu); } NOKPROBE_SYMBOL(__hyp_call_panic); void __noreturn hyp_panic(void) { u64 spsr = read_sysreg_el2(SYS_SPSR); u64 elr = read_sysreg_el2(SYS_ELR); u64 par = read_sysreg_par(); __hyp_call_panic(spsr, elr, par); } asmlinkage void kvm_unexpected_el2_exception(void) { __kvm_unexpected_el2_exception(); } |
| 145 144 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * SafeSetID Linux Security Module * * Author: Micah Morton <mortonm@chromium.org> * * Copyright (C) 2018 The Chromium OS Authors. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, as * published by the Free Software Foundation. * */ #define pr_fmt(fmt) "SafeSetID: " fmt #include <linux/lsm_hooks.h> #include <linux/module.h> #include <linux/ptrace.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <uapi/linux/lsm.h> #include "lsm.h" /* Flag indicating whether initialization completed */ int safesetid_initialized __initdata; struct setid_ruleset __rcu *safesetid_setuid_rules; struct setid_ruleset __rcu *safesetid_setgid_rules; /* Compute a decision for a transition from @src to @dst under @policy. */ enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy, kid_t src, kid_t dst) { struct setid_rule *rule; enum sid_policy_type result = SIDPOL_DEFAULT; if (policy->type == UID) { hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) { if (!uid_eq(rule->src_id.uid, src.uid)) continue; if (uid_eq(rule->dst_id.uid, dst.uid)) return SIDPOL_ALLOWED; result = SIDPOL_CONSTRAINED; } } else if (policy->type == GID) { hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) { if (!gid_eq(rule->src_id.gid, src.gid)) continue; if (gid_eq(rule->dst_id.gid, dst.gid)){ return SIDPOL_ALLOWED; } result = SIDPOL_CONSTRAINED; } } else { /* Should not reach here, report the ID as contrainsted */ result = SIDPOL_CONSTRAINED; } return result; } /* * Compute a decision for a transition from @src to @dst under the active * policy. */ static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type) { enum sid_policy_type result = SIDPOL_DEFAULT; struct setid_ruleset *pol; rcu_read_lock(); if (new_type == UID) pol = rcu_dereference(safesetid_setuid_rules); else if (new_type == GID) pol = rcu_dereference(safesetid_setgid_rules); else { /* Should not reach here */ result = SIDPOL_CONSTRAINED; rcu_read_unlock(); return result; } if (pol) { pol->type = new_type; result = _setid_policy_lookup(pol, src, dst); } rcu_read_unlock(); return result; } static int safesetid_security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { /* We're only interested in CAP_SETUID and CAP_SETGID. */ if (cap != CAP_SETUID && cap != CAP_SETGID) return 0; /* * If CAP_SET{U/G}ID is currently used for a setid or setgroups syscall, we * want to let it go through here; the real security check happens later, in * the task_fix_set{u/g}id or task_fix_setgroups hooks. */ if ((opts & CAP_OPT_INSETID) != 0) return 0; switch (cap) { case CAP_SETUID: /* * If no policy applies to this task, allow the use of CAP_SETUID for * other purposes. */ if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*uid() (e.g. setting up userns uid mappings). */ pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n", __kuid_val(cred->uid)); return -EPERM; case CAP_SETGID: /* * If no policy applies to this task, allow the use of CAP_SETGID for * other purposes. */ if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*gid() (e.g. setting up userns gid mappings). */ pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n", __kgid_val(cred->gid)); return -EPERM; default: /* Error, the only capabilities were checking for is CAP_SETUID/GID */ return 0; } return 0; } /* * Check whether a caller with old credentials @old is allowed to switch to * credentials that contain @new_id. */ static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type) { bool permitted; /* If our old creds already had this ID in it, it's fine. */ if (new_type == UID) { if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) || uid_eq(new_id.uid, old->suid)) return true; } else if (new_type == GID){ if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) || gid_eq(new_id.gid, old->sgid)) return true; } else /* Error, new_type is an invalid type */ return false; /* * Transitions to new UIDs require a check against the policy of the old * RUID. */ permitted = setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED; if (!permitted) { if (new_type == UID) { pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n", __kuid_val(old->uid), __kuid_val(old->euid), __kuid_val(old->suid), __kuid_val(new_id.uid)); } else if (new_type == GID) { pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n", __kgid_val(old->gid), __kgid_val(old->egid), __kgid_val(old->sgid), __kgid_val(new_id.gid)); } else /* Error, new_type is an invalid type */ return false; } return permitted; } /* * Check whether there is either an exception for user under old cred struct to * set*uid to user under new cred struct, or the UID transition is allowed (by * Linux set*uid rules) even without CAP_SETUID. */ static int safesetid_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setuid restrictions for our old RUID. */ if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old) { int i; /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; get_group_info(new->group_info); for (i = 0; i < new->group_info->ngroups; i++) { if (!id_permitted_for_cred(old, (kid_t){.gid = new->group_info->gid[i]}, GID)) { put_group_info(new->group_info); /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } } put_group_info(new->group_info); return 0; } static const struct lsm_id safesetid_lsmid = { .name = "safesetid", .id = LSM_ID_SAFESETID, }; static struct security_hook_list safesetid_security_hooks[] = { LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid), LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid), LSM_HOOK_INIT(task_fix_setgroups, safesetid_task_fix_setgroups), LSM_HOOK_INIT(capable, safesetid_security_capable) }; static int __init safesetid_security_init(void) { security_add_hooks(safesetid_security_hooks, ARRAY_SIZE(safesetid_security_hooks), &safesetid_lsmid); /* Report that SafeSetID successfully initialized */ safesetid_initialized = 1; return 0; } DEFINE_LSM(safesetid_security_init) = { .id = &safesetid_lsmid, .init = safesetid_security_init, .initcall_fs = safesetid_init_securityfs, }; |
| 10 15 14 15 7 7 6 2 6 2 7 7 7 7 7 7 7 7 7 7 7 7 1 7 7 7 15 15 15 14 7 9 15 15 15 15 15 15 15 7 15 15 15 15 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only #undef DEBUG /* * ARM performance counter support. * * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com> * * This code is based on the sparc64 perf event code, which is in turn based * on the x86 code. */ #define pr_fmt(fmt) "hw perfevents: " fmt #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/cpu_pm.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/perf/arm_pmu.h> #include <linux/slab.h> #include <linux/sched/clock.h> #include <linux/spinlock.h> #include <linux/irq.h> #include <linux/irqdesc.h> #include <asm/irq_regs.h> static int armpmu_count_irq_users(const struct cpumask *affinity, const int irq); struct pmu_irq_ops { void (*enable_pmuirq)(unsigned int irq); void (*disable_pmuirq)(unsigned int irq); void (*free_pmuirq)(unsigned int irq, int cpu, void __percpu *devid); }; static void armpmu_free_pmuirq(unsigned int irq, int cpu, void __percpu *devid) { free_irq(irq, per_cpu_ptr(devid, cpu)); } static const struct pmu_irq_ops pmuirq_ops = { .enable_pmuirq = enable_irq, .disable_pmuirq = disable_irq_nosync, .free_pmuirq = armpmu_free_pmuirq }; static void armpmu_free_pmunmi(unsigned int irq, int cpu, void __percpu *devid) { free_nmi(irq, per_cpu_ptr(devid, cpu)); } static const struct pmu_irq_ops pmunmi_ops = { .enable_pmuirq = enable_nmi, .disable_pmuirq = disable_nmi_nosync, .free_pmuirq = armpmu_free_pmunmi }; static void armpmu_enable_percpu_pmuirq(unsigned int irq) { enable_percpu_irq(irq, IRQ_TYPE_NONE); } static void armpmu_free_percpu_pmuirq(unsigned int irq, int cpu, void __percpu *devid) { struct arm_pmu *armpmu = *per_cpu_ptr((void * __percpu *)devid, cpu); if (armpmu_count_irq_users(&armpmu->supported_cpus, irq) == 1) free_percpu_irq(irq, devid); } static const struct pmu_irq_ops percpu_pmuirq_ops = { .enable_pmuirq = armpmu_enable_percpu_pmuirq, .disable_pmuirq = disable_percpu_irq, .free_pmuirq = armpmu_free_percpu_pmuirq }; static void armpmu_enable_percpu_pmunmi(unsigned int irq) { if (!prepare_percpu_nmi(irq)) enable_percpu_nmi(irq, IRQ_TYPE_NONE); } static void armpmu_disable_percpu_pmunmi(unsigned int irq) { disable_percpu_nmi(irq); teardown_percpu_nmi(irq); } static void armpmu_free_percpu_pmunmi(unsigned int irq, int cpu, void __percpu *devid) { struct arm_pmu *armpmu = *per_cpu_ptr((void * __percpu *)devid, cpu); if (armpmu_count_irq_users(&armpmu->supported_cpus, irq) == 1) free_percpu_nmi(irq, devid); } static const struct pmu_irq_ops percpu_pmunmi_ops = { .enable_pmuirq = armpmu_enable_percpu_pmunmi, .disable_pmuirq = armpmu_disable_percpu_pmunmi, .free_pmuirq = armpmu_free_percpu_pmunmi }; static DEFINE_PER_CPU(int, cpu_irq); static DEFINE_PER_CPU(const struct pmu_irq_ops *, cpu_irq_ops); static bool has_nmi; static inline u64 arm_pmu_event_max_period(struct perf_event *event) { if (event->hw.flags & ARMPMU_EVT_64BIT) return GENMASK_ULL(63, 0); else if (event->hw.flags & ARMPMU_EVT_63BIT) return GENMASK_ULL(62, 0); else if (event->hw.flags & ARMPMU_EVT_47BIT) return GENMASK_ULL(46, 0); else return GENMASK_ULL(31, 0); } static int armpmu_map_cache_event(const unsigned (*cache_map) [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX], u64 config) { unsigned int cache_type, cache_op, cache_result, ret; cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; if (!cache_map) return -ENOENT; ret = (int)(*cache_map)[cache_type][cache_op][cache_result]; if (ret == CACHE_OP_UNSUPPORTED) return -ENOENT; return ret; } static int armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { int mapping; if (config >= PERF_COUNT_HW_MAX) return -EINVAL; if (!event_map) return -ENOENT; mapping = (*event_map)[config]; return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } static int armpmu_map_raw_event(u32 raw_event_mask, u64 config) { return (int)(config & raw_event_mask); } int armpmu_map_event(struct perf_event *event, const unsigned (*event_map)[PERF_COUNT_HW_MAX], const unsigned (*cache_map) [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX], u32 raw_event_mask) { u64 config = event->attr.config; int type = event->attr.type; if (type == event->pmu->type) return armpmu_map_raw_event(raw_event_mask, config); switch (type) { case PERF_TYPE_HARDWARE: return armpmu_map_hw_event(event_map, config); case PERF_TYPE_HW_CACHE: return armpmu_map_cache_event(cache_map, config); case PERF_TYPE_RAW: return armpmu_map_raw_event(raw_event_mask, config); } return -ENOENT; } int armpmu_event_set_period(struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; u64 max_period; int ret = 0; max_period = arm_pmu_event_max_period(event); if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } /* * Limit the maximum period to prevent the counter value * from overtaking the one we are about to program. In * effect we are reducing max_period to account for * interrupt latency (and we are being very conservative). */ if (left > (max_period >> 1)) left = (max_period >> 1); local64_set(&hwc->prev_count, (u64)-left); armpmu->write_counter(event, (u64)(-left) & max_period); perf_event_update_userpage(event); return ret; } u64 armpmu_event_update(struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; u64 delta, prev_raw_count, new_raw_count; u64 max_period = arm_pmu_event_max_period(event); again: prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = armpmu->read_counter(event); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; delta = (new_raw_count - prev_raw_count) & max_period; local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); return new_raw_count; } static void armpmu_read(struct perf_event *event) { armpmu_event_update(event); } static void armpmu_stop(struct perf_event *event, int flags) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; /* * ARM pmu always has to update the counter, so ignore * PERF_EF_UPDATE, see comments in armpmu_start(). */ if (!(hwc->state & PERF_HES_STOPPED)) { armpmu->disable(event); armpmu_event_update(event); hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; } } static void armpmu_start(struct perf_event *event, int flags) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; /* * ARM pmu always has to reprogram the period, so ignore * PERF_EF_RELOAD, see the comment below. */ if (flags & PERF_EF_RELOAD) WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); hwc->state = 0; /* * Set the period again. Some counters can't be stopped, so when we * were stopped we simply disabled the IRQ source and the counter * may have been left counting. If we don't do this step then we may * get an interrupt too soon or *way* too late if the overflow has * happened since disabling. */ armpmu_event_set_period(event); armpmu->enable(event); } static void armpmu_del(struct perf_event *event, int flags) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; armpmu_stop(event, PERF_EF_UPDATE); if (has_branch_stack(event)) { hw_events->branch_users--; perf_sched_cb_dec(event->pmu); } hw_events->events[idx] = NULL; armpmu->clear_event_idx(hw_events, event); perf_event_update_userpage(event); /* Clear the allocated counter */ hwc->idx = -1; } static int armpmu_add(struct perf_event *event, int flags) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); struct hw_perf_event *hwc = &event->hw; int idx; /* An event following a process won't be stopped earlier */ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus)) return -ENOENT; /* If we don't have a space for the counter then finish early. */ idx = armpmu->get_event_idx(hw_events, event); if (idx < 0) return idx; /* The newly-allocated counter should be empty */ WARN_ON_ONCE(hw_events->events[idx]); if (has_branch_stack(event)) { hw_events->branch_users++; perf_sched_cb_inc(event->pmu); } event->hw.idx = idx; hw_events->events[idx] = event; hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; if (flags & PERF_EF_START) armpmu_start(event, PERF_EF_RELOAD); /* Propagate our changes to the userspace mapping. */ perf_event_update_userpage(event); return 0; } static int validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events, struct perf_event *event) { struct arm_pmu *armpmu; if (is_software_event(event)) return 1; /* * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The * core perf code won't check that the pmu->ctx == leader->ctx * until after pmu->event_init(event). */ if (event->pmu != pmu) return 0; if (event->state < PERF_EVENT_STATE_OFF) return 1; if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) return 1; armpmu = to_arm_pmu(event->pmu); return armpmu->get_event_idx(hw_events, event) >= 0; } static int validate_group(struct perf_event *event) { struct perf_event *sibling, *leader = event->group_leader; struct pmu_hw_events fake_pmu; /* * Initialise the fake PMU. We only need to populate the * used_mask for the purposes of validation. */ memset(&fake_pmu.used_mask, 0, sizeof(fake_pmu.used_mask)); if (!validate_event(event->pmu, &fake_pmu, leader)) return -EINVAL; if (event == leader) return 0; for_each_sibling_event(sibling, leader) { if (!validate_event(event->pmu, &fake_pmu, sibling)) return -EINVAL; } if (!validate_event(event->pmu, &fake_pmu, event)) return -EINVAL; return 0; } static irqreturn_t armpmu_dispatch_irq(int irq, void *dev) { struct arm_pmu *armpmu; int ret; u64 start_clock, finish_clock; /* * we request the IRQ with a (possibly percpu) struct arm_pmu**, but * the handlers expect a struct arm_pmu*. The percpu_irq framework will * do any necessary shifting, we just need to perform the first * dereference. */ armpmu = *(void **)dev; if (WARN_ON_ONCE(!armpmu)) return IRQ_NONE; start_clock = sched_clock(); ret = armpmu->handle_irq(armpmu); finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); return ret; } static int __hw_perf_event_init(struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; int mapping, ret; hwc->flags = 0; mapping = armpmu->map_event(event); if (mapping < 0) { pr_debug("event %x:%llx not supported\n", event->attr.type, event->attr.config); return mapping; } /* * We don't assign an index until we actually place the event onto * hardware. Use -1 to signify that we haven't decided where to put it * yet. For SMP systems, each core has it's own PMU so we can't do any * clever allocation or constraints checking at this point. */ hwc->idx = -1; hwc->config_base = 0; hwc->config = 0; hwc->event_base = 0; /* * Check whether we need to exclude the counter from certain modes. */ if (armpmu->set_event_filter) { ret = armpmu->set_event_filter(hwc, &event->attr); if (ret) return ret; } /* * Store the event encoding into the config_base field. */ hwc->config_base |= (unsigned long)mapping; if (!is_sampling_event(event)) { /* * For non-sampling runs, limit the sample_period to half * of the counter width. That way, the new counter value * is far less likely to overtake the previous one unless * you have some serious IRQ latency issues. */ hwc->sample_period = arm_pmu_event_max_period(event) >> 1; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } return validate_group(event); } static int armpmu_event_init(struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); /* * Reject CPU-affine events for CPUs that are of a different class to * that which this PMU handles. Process-following events (where * event->cpu == -1) can be migrated between CPUs, and thus we have to * reject them later (in armpmu_add) if they're scheduled on a * different class of CPU. */ if (event->cpu != -1 && !cpumask_test_cpu(event->cpu, &armpmu->supported_cpus)) return -ENOENT; if (has_branch_stack(event) && !armpmu->reg_brbidr) return -EOPNOTSUPP; return __hw_perf_event_init(event); } static void armpmu_enable(struct pmu *pmu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS); /* For task-bound events we may be called on other CPUs */ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus)) return; if (enabled) armpmu->start(armpmu); } static void armpmu_disable(struct pmu *pmu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); /* For task-bound events we may be called on other CPUs */ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus)) return; armpmu->stop(armpmu); } /* * In heterogeneous systems, events are specific to a particular * microarchitecture, and aren't suitable for another. Thus, only match CPUs of * the same microarchitecture. */ static bool armpmu_filter(struct pmu *pmu, int cpu) { struct arm_pmu *armpmu = to_arm_pmu(pmu); return !cpumask_test_cpu(cpu, &armpmu->supported_cpus); } static ssize_t cpus_show(struct device *dev, struct device_attribute *attr, char *buf) { struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev)); return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus); } static DEVICE_ATTR_RO(cpus); static struct attribute *armpmu_common_attrs[] = { &dev_attr_cpus.attr, NULL, }; static const struct attribute_group armpmu_common_attr_group = { .attrs = armpmu_common_attrs, }; static int armpmu_count_irq_users(const struct cpumask *affinity, const int irq) { int cpu, count = 0; for_each_cpu(cpu, affinity) { if (per_cpu(cpu_irq, cpu) == irq) count++; } return count; } static const struct pmu_irq_ops * armpmu_find_irq_ops(const struct cpumask *affinity, int irq) { const struct pmu_irq_ops *ops = NULL; int cpu; for_each_cpu(cpu, affinity) { if (per_cpu(cpu_irq, cpu) != irq) continue; ops = per_cpu(cpu_irq_ops, cpu); if (ops) break; } return ops; } void armpmu_free_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu) { if (per_cpu(cpu_irq, cpu) == 0) return; if (WARN_ON(irq != per_cpu(cpu_irq, cpu))) return; per_cpu(cpu_irq_ops, cpu)->free_pmuirq(irq, cpu, armpmu); per_cpu(cpu_irq, cpu) = 0; per_cpu(cpu_irq_ops, cpu) = NULL; } int armpmu_request_irq(struct arm_pmu * __percpu *pcpu_armpmu, int irq, int cpu) { int err = 0; struct arm_pmu **armpmu = per_cpu_ptr(pcpu_armpmu, cpu); const struct cpumask *affinity = *armpmu ? &(*armpmu)->supported_cpus : cpu_possible_mask; /* ACPI */ const irq_handler_t handler = armpmu_dispatch_irq; const struct pmu_irq_ops *irq_ops; if (!irq) return 0; if (!irq_is_percpu_devid(irq)) { unsigned long irq_flags; err = irq_force_affinity(irq, cpumask_of(cpu)); if (err && num_possible_cpus() > 1) { pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n", irq, cpu); goto err_out; } irq_flags = IRQF_PERCPU | IRQF_NOBALANCING | IRQF_NO_AUTOEN | IRQF_NO_THREAD; err = request_nmi(irq, handler, irq_flags, "arm-pmu", armpmu); /* If cannot get an NMI, get a normal interrupt */ if (err) { err = request_irq(irq, handler, irq_flags, "arm-pmu", armpmu); irq_ops = &pmuirq_ops; } else { has_nmi = true; irq_ops = &pmunmi_ops; } } else if (armpmu_count_irq_users(affinity, irq) == 0) { err = request_percpu_nmi(irq, handler, "arm-pmu", affinity, pcpu_armpmu); /* If cannot get an NMI, get a normal interrupt */ if (err) { err = request_percpu_irq_affinity(irq, handler, "arm-pmu", affinity, pcpu_armpmu); irq_ops = &percpu_pmuirq_ops; } else { has_nmi = true; irq_ops = &percpu_pmunmi_ops; } } else { /* Per cpudevid irq was already requested by another CPU */ irq_ops = armpmu_find_irq_ops(affinity, irq); if (WARN_ON(!irq_ops)) err = -EINVAL; } if (err) goto err_out; per_cpu(cpu_irq, cpu) = irq; per_cpu(cpu_irq_ops, cpu) = irq_ops; return 0; err_out: pr_err("unable to request IRQ%d for ARM PMU counters\n", irq); return err; } static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu) { struct pmu_hw_events __percpu *hw_events = pmu->hw_events; return per_cpu(hw_events->irq, cpu); } bool arm_pmu_irq_is_nmi(void) { return has_nmi; } /* * PMU hardware loses all context when a CPU goes offline. * When a CPU is hotplugged back in, since some hardware registers are * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading * junk values out of them. */ static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node) { struct arm_pmu *pmu = hlist_entry_safe(node, struct arm_pmu, node); int irq; if (!cpumask_test_cpu(cpu, &pmu->supported_cpus)) return 0; if (pmu->reset) pmu->reset(pmu); irq = armpmu_get_cpu_irq(pmu, cpu); if (irq) per_cpu(cpu_irq_ops, cpu)->enable_pmuirq(irq); return 0; } static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node) { struct arm_pmu *pmu = hlist_entry_safe(node, struct arm_pmu, node); int irq; if (!cpumask_test_cpu(cpu, &pmu->supported_cpus)) return 0; irq = armpmu_get_cpu_irq(pmu, cpu); if (irq) per_cpu(cpu_irq_ops, cpu)->disable_pmuirq(irq); return 0; } #ifdef CONFIG_CPU_PM static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd) { struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); struct perf_event *event; int idx; for_each_set_bit(idx, armpmu->cntr_mask, ARMPMU_MAX_HWEVENTS) { event = hw_events->events[idx]; if (!event) continue; switch (cmd) { case CPU_PM_ENTER: /* * Stop and update the counter */ armpmu_stop(event, PERF_EF_UPDATE); break; case CPU_PM_EXIT: case CPU_PM_ENTER_FAILED: /* * Restore and enable the counter. */ armpmu_start(event, PERF_EF_RELOAD); break; default: break; } } } static int cpu_pm_pmu_notify(struct notifier_block *b, unsigned long cmd, void *v) { struct arm_pmu *armpmu = container_of(b, struct arm_pmu, cpu_pm_nb); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); bool enabled = !bitmap_empty(hw_events->used_mask, ARMPMU_MAX_HWEVENTS); if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus)) return NOTIFY_DONE; /* * Always reset the PMU registers on power-up even if * there are no events running. */ if (cmd == CPU_PM_EXIT && armpmu->reset) armpmu->reset(armpmu); if (!enabled) return NOTIFY_OK; switch (cmd) { case CPU_PM_ENTER: armpmu->stop(armpmu); cpu_pm_pmu_setup(armpmu, cmd); break; case CPU_PM_EXIT: case CPU_PM_ENTER_FAILED: cpu_pm_pmu_setup(armpmu, cmd); armpmu->start(armpmu); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int cpu_pm_pmu_register(struct arm_pmu *cpu_pmu) { cpu_pmu->cpu_pm_nb.notifier_call = cpu_pm_pmu_notify; return cpu_pm_register_notifier(&cpu_pmu->cpu_pm_nb); } static void cpu_pm_pmu_unregister(struct arm_pmu *cpu_pmu) { cpu_pm_unregister_notifier(&cpu_pmu->cpu_pm_nb); } #else static inline int cpu_pm_pmu_register(struct arm_pmu *cpu_pmu) { return 0; } static inline void cpu_pm_pmu_unregister(struct arm_pmu *cpu_pmu) { } #endif static int cpu_pmu_init(struct arm_pmu *cpu_pmu) { int err; err = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_STARTING, &cpu_pmu->node); if (err) goto out; err = cpu_pm_pmu_register(cpu_pmu); if (err) goto out_unregister; return 0; out_unregister: cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING, &cpu_pmu->node); out: return err; } static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu) { cpu_pm_pmu_unregister(cpu_pmu); cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING, &cpu_pmu->node); } struct arm_pmu *armpmu_alloc(void) { struct arm_pmu *pmu; int cpu; pmu = kzalloc_obj(*pmu); if (!pmu) goto out; pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, GFP_KERNEL); if (!pmu->hw_events) { pr_info("failed to allocate per-cpu PMU data.\n"); goto out_free_pmu; } pmu->pmu = (struct pmu) { .pmu_enable = armpmu_enable, .pmu_disable = armpmu_disable, .event_init = armpmu_event_init, .add = armpmu_add, .del = armpmu_del, .start = armpmu_start, .stop = armpmu_stop, .read = armpmu_read, .filter = armpmu_filter, .attr_groups = pmu->attr_groups, /* * This is a CPU PMU potentially in a heterogeneous * configuration (e.g. big.LITTLE) so * PERF_PMU_CAP_EXTENDED_HW_TYPE is required to open * PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE events on a * specific PMU. */ .capabilities = PERF_PMU_CAP_EXTENDED_REGS | PERF_PMU_CAP_EXTENDED_HW_TYPE, }; pmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] = &armpmu_common_attr_group; for_each_possible_cpu(cpu) { struct pmu_hw_events *events; events = per_cpu_ptr(pmu->hw_events, cpu); events->percpu_pmu = pmu; } return pmu; out_free_pmu: kfree(pmu); out: return NULL; } void armpmu_free(struct arm_pmu *pmu) { free_percpu(pmu->hw_events); kfree(pmu); } int armpmu_register(struct arm_pmu *pmu) { int ret; ret = cpu_pmu_init(pmu); if (ret) return ret; /* * By this stage we know our supported CPUs on either DT/ACPI platforms, * detect the SMT implementation. */ pmu->has_smt = topology_core_has_smt(cpumask_first(&pmu->supported_cpus)); if (!pmu->set_event_filter) pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); if (ret) goto out_destroy; pr_info("enabled with %s PMU driver, %d (%*pb) counters available%s\n", pmu->name, bitmap_weight(pmu->cntr_mask, ARMPMU_MAX_HWEVENTS), ARMPMU_MAX_HWEVENTS, &pmu->cntr_mask, has_nmi ? ", using NMIs" : ""); kvm_host_pmu_init(pmu); return 0; out_destroy: cpu_pmu_destroy(pmu); return ret; } static int arm_pmu_hp_init(void) { int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING, "perf/arm/pmu:starting", arm_perf_starting_cpu, arm_perf_teardown_cpu); if (ret) pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n", ret); return ret; } subsys_initcall(arm_pmu_hp_init); |
| 37 7 30 30 30 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2023 ARM Ltd. */ #include <linux/mm.h> #include <linux/efi.h> #include <linux/export.h> #include <asm/tlbflush.h> static inline bool mm_is_user(struct mm_struct *mm) { /* * Don't attempt to apply the contig bit to kernel mappings, because * dynamically adding/removing the contig bit can cause page faults. * These racing faults are ok for user space, since they get serialized * on the PTL. But kernel mappings can't tolerate faults. */ if (unlikely(mm_is_efi(mm))) return false; return mm != &init_mm; } static inline pte_t *contpte_align_down(pte_t *ptep) { return PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES); } static inline pte_t *contpte_align_addr_ptep(unsigned long *start, unsigned long *end, pte_t *ptep, unsigned int nr) { /* * Note: caller must ensure these nr PTEs are consecutive (present) * PTEs that map consecutive pages of the same large folio within a * single VMA and a single page table. */ if (pte_cont(__ptep_get(ptep + nr - 1))) *end = ALIGN(*end, CONT_PTE_SIZE); if (pte_cont(__ptep_get(ptep))) { *start = ALIGN_DOWN(*start, CONT_PTE_SIZE); ptep = contpte_align_down(ptep); } return ptep; } static void contpte_try_unfold_partial(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * Unfold any partially covered contpte block at the beginning and end * of the range. */ if (ptep != contpte_align_down(ptep) || nr < CONT_PTES) contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); if (ptep + nr != contpte_align_down(ptep + nr)) { unsigned long last_addr = addr + PAGE_SIZE * (nr - 1); pte_t *last_ptep = ptep + nr - 1; contpte_try_unfold(mm, last_addr, last_ptep, __ptep_get(last_ptep)); } } static void contpte_convert(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long start_addr; pte_t *start_ptep; int i; start_ptep = ptep = contpte_align_down(ptep); start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); pte = pfn_pte(ALIGN_DOWN(pte_pfn(pte), CONT_PTES), pte_pgprot(pte)); for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) { pte_t ptent = __ptep_get_and_clear(mm, addr, ptep); if (pte_dirty(ptent)) pte = pte_mkdirty(pte); if (pte_young(ptent)) pte = pte_mkyoung(pte); } /* * On eliding the __tlb_flush_range() under BBML2+noabort: * * NOTE: Instead of using N=16 as the contiguous block length, we use * N=4 for clarity. * * NOTE: 'n' and 'c' are used to denote the "contiguous bit" being * unset and set, respectively. * * We worry about two cases where contiguous bit is used: * - When folding N smaller non-contiguous ptes as 1 contiguous block. * - When unfolding a contiguous block into N smaller non-contiguous ptes. * * Currently, the BBML0 folding case looks as follows: * * 0) Initial page-table layout: * * +----+----+----+----+ * |RO,n|RO,n|RO,n|RW,n| <--- last page being set as RO * +----+----+----+----+ * * 1) Aggregate AF + dirty flags using __ptep_get_and_clear(): * * +----+----+----+----+ * | 0 | 0 | 0 | 0 | * +----+----+----+----+ * * 2) __flush_tlb_range(): * * |____ tlbi + dsb ____| * * 3) __set_ptes() to repaint contiguous block: * * +----+----+----+----+ * |RO,c|RO,c|RO,c|RO,c| * +----+----+----+----+ * * 4) The kernel will eventually __flush_tlb() for changed page: * * |____| <--- tlbi + dsb * * As expected, the intermediate tlbi+dsb ensures that other PEs * only ever see an invalid (0) entry, or the new contiguous TLB entry. * The final tlbi+dsb will always throw away the newly installed * contiguous TLB entry, which is a micro-optimisation opportunity, * but does not affect correctness. * * In the BBML2 case, the change is avoiding the intermediate tlbi+dsb. * This means a few things, but notably other PEs will still "see" any * stale cached TLB entries. This could lead to a "contiguous bit * misprogramming" issue until the final tlbi+dsb of the changed page, * which would clear out both the stale (RW,n) entry and the new (RO,c) * contiguous entry installed in its place. * * What this is saying, is the following: * * +----+----+----+----+ * |RO,n|RO,n|RO,n|RW,n| <--- old page tables, all non-contiguous * +----+----+----+----+ * * +----+----+----+----+ * |RO,c|RO,c|RO,c|RO,c| <--- new page tables, all contiguous * +----+----+----+----+ * /\ * || * * If both the old single (RW,n) and new contiguous (RO,c) TLB entries * are present, and a write is made to this address, do we fault or * is the write permitted (via amalgamation)? * * The relevant Arm ARM DDI 0487L.a requirements are RNGLXZ and RJQQTC, * and together state that when BBML1 or BBML2 are implemented, either * a TLB conflict abort is raised (which we expressly forbid), or will * "produce an OA, access permissions, and memory attributes that are * consistent with any of the programmed translation table values". * * That is to say, will either raise a TLB conflict, or produce one of * the cached TLB entries, but never amalgamate. * * Thus, as the page tables are only considered "consistent" after * the final tlbi+dsb (which evicts both the single stale (RW,n) TLB * entry as well as the new contiguous (RO,c) TLB entry), omitting the * initial tlbi+dsb is correct. * * It is also important to note that at the end of the BBML2 folding * case, we are still left with potentially all N TLB entries still * cached (the N-1 non-contiguous ptes, and the single contiguous * block). However, over time, natural TLB pressure will cause the * non-contiguous pte TLB entries to be flushed, leaving only the * contiguous block TLB entry. This means that omitting the tlbi+dsb is * not only correct, but also keeps our eventual performance benefits. * * For the unfolding case, BBML0 looks as follows: * * 0) Initial page-table layout: * * +----+----+----+----+ * |RW,c|RW,c|RW,c|RW,c| <--- last page being set as RO * +----+----+----+----+ * * 1) Aggregate AF + dirty flags using __ptep_get_and_clear(): * * +----+----+----+----+ * | 0 | 0 | 0 | 0 | * +----+----+----+----+ * * 2) __flush_tlb_range(): * * |____ tlbi + dsb ____| * * 3) __set_ptes() to repaint as non-contiguous: * * +----+----+----+----+ * |RW,n|RW,n|RW,n|RW,n| * +----+----+----+----+ * * 4) Update changed page permissions: * * +----+----+----+----+ * |RW,n|RW,n|RW,n|RO,n| <--- last page permissions set * +----+----+----+----+ * * 5) The kernel will eventually __flush_tlb() for changed page: * * |____| <--- tlbi + dsb * * For BBML2, we again remove the intermediate tlbi+dsb. Here, there * are no issues, as the final tlbi+dsb covering the changed page is * guaranteed to remove the original large contiguous (RW,c) TLB entry, * as well as the intermediate (RW,n) TLB entry; the next access will * install the new (RO,n) TLB entry and the page tables are only * considered "consistent" after the final tlbi+dsb, so software must * be prepared for this inconsistency prior to finishing the mm dance * regardless. */ if (!system_supports_bbml2_noabort()) __flush_tlb_range(&vma, start_addr, addr, PAGE_SIZE, true, 3); __set_ptes(mm, start_addr, start_ptep, pte, CONT_PTES); } void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * We have already checked that the virtual and pysical addresses are * correctly aligned for a contpte mapping in contpte_try_fold() so the * remaining checks are to ensure that the contpte range is fully * covered by a single folio, and ensure that all the ptes are valid * with contiguous PFNs and matching prots. We ignore the state of the * access and dirty bits for the purpose of deciding if its a contiguous * range; the folding process will generate a single contpte entry which * has a single access and dirty bit. Those 2 bits are the logical OR of * their respective bits in the constituent pte entries. In order to * ensure the contpte range is covered by a single folio, we must * recover the folio from the pfn, but special mappings don't have a * folio backing them. Fortunately contpte_try_fold() already checked * that the pte is not special - we never try to fold special mappings. * Note we can't use vm_normal_page() for this since we don't have the * vma. */ unsigned long folio_start, folio_end; unsigned long cont_start, cont_end; pte_t expected_pte, subpte; struct folio *folio; struct page *page; unsigned long pfn; pte_t *orig_ptep; pgprot_t prot; int i; if (!mm_is_user(mm)) return; page = pte_page(pte); folio = page_folio(page); folio_start = addr - (page - &folio->page) * PAGE_SIZE; folio_end = folio_start + folio_nr_pages(folio) * PAGE_SIZE; cont_start = ALIGN_DOWN(addr, CONT_PTE_SIZE); cont_end = cont_start + CONT_PTE_SIZE; if (folio_start > cont_start || folio_end < cont_end) return; pfn = ALIGN_DOWN(pte_pfn(pte), CONT_PTES); prot = pte_pgprot(pte_mkold(pte_mkclean(pte))); expected_pte = pfn_pte(pfn, prot); orig_ptep = ptep; ptep = contpte_align_down(ptep); for (i = 0; i < CONT_PTES; i++) { subpte = pte_mkold(pte_mkclean(__ptep_get(ptep))); if (!pte_same(subpte, expected_pte)) return; expected_pte = pte_advance_pfn(expected_pte, 1); ptep++; } pte = pte_mkcont(pte); contpte_convert(mm, addr, orig_ptep, pte); } EXPORT_SYMBOL_GPL(__contpte_try_fold); void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * We have already checked that the ptes are contiguous in * contpte_try_unfold(), so just check that the mm is user space. */ if (!mm_is_user(mm)) return; pte = pte_mknoncont(pte); contpte_convert(mm, addr, ptep, pte); } EXPORT_SYMBOL_GPL(__contpte_try_unfold); pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte) { /* * Gather access/dirty bits, which may be populated in any of the ptes * of the contig range. We are guaranteed to be holding the PTL, so any * contiguous range cannot be unfolded or otherwise modified under our * feet. */ pte_t pte; int i; ptep = contpte_align_down(ptep); for (i = 0; i < CONT_PTES; i++, ptep++) { pte = __ptep_get(ptep); if (pte_dirty(pte)) { orig_pte = pte_mkdirty(orig_pte); for (; i < CONT_PTES; i++, ptep++) { pte = __ptep_get(ptep); if (pte_young(pte)) { orig_pte = pte_mkyoung(orig_pte); break; } } break; } if (pte_young(pte)) { orig_pte = pte_mkyoung(orig_pte); i++; ptep++; for (; i < CONT_PTES; i++, ptep++) { pte = __ptep_get(ptep); if (pte_dirty(pte)) { orig_pte = pte_mkdirty(orig_pte); break; } } break; } } return orig_pte; } EXPORT_SYMBOL_GPL(contpte_ptep_get); static inline bool contpte_is_consistent(pte_t pte, unsigned long pfn, pgprot_t orig_prot) { pgprot_t prot = pte_pgprot(pte_mkold(pte_mkclean(pte))); return pte_valid_cont(pte) && pte_pfn(pte) == pfn && pgprot_val(prot) == pgprot_val(orig_prot); } pte_t contpte_ptep_get_lockless(pte_t *orig_ptep) { /* * The ptep_get_lockless() API requires us to read and return *orig_ptep * so that it is self-consistent, without the PTL held, so we may be * racing with other threads modifying the pte. Usually a READ_ONCE() * would suffice, but for the contpte case, we also need to gather the * access and dirty bits from across all ptes in the contiguous block, * and we can't read all of those neighbouring ptes atomically, so any * contiguous range may be unfolded/modified/refolded under our feet. * Therefore we ensure we read a _consistent_ contpte range by checking * that all ptes in the range are valid and have CONT_PTE set, that all * pfns are contiguous and that all pgprots are the same (ignoring * access/dirty). If we find a pte that is not consistent, then we must * be racing with an update so start again. If the target pte does not * have CONT_PTE set then that is considered consistent on its own * because it is not part of a contpte range. */ pgprot_t orig_prot; unsigned long pfn; pte_t orig_pte; pte_t *ptep; pte_t pte; int i; retry: orig_pte = __ptep_get(orig_ptep); if (!pte_valid_cont(orig_pte)) return orig_pte; orig_prot = pte_pgprot(pte_mkold(pte_mkclean(orig_pte))); ptep = contpte_align_down(orig_ptep); pfn = pte_pfn(orig_pte) - (orig_ptep - ptep); for (i = 0; i < CONT_PTES; i++, ptep++, pfn++) { pte = __ptep_get(ptep); if (!contpte_is_consistent(pte, pfn, orig_prot)) goto retry; if (pte_dirty(pte)) { orig_pte = pte_mkdirty(orig_pte); for (; i < CONT_PTES; i++, ptep++, pfn++) { pte = __ptep_get(ptep); if (!contpte_is_consistent(pte, pfn, orig_prot)) goto retry; if (pte_young(pte)) { orig_pte = pte_mkyoung(orig_pte); break; } } break; } if (pte_young(pte)) { orig_pte = pte_mkyoung(orig_pte); i++; ptep++; pfn++; for (; i < CONT_PTES; i++, ptep++, pfn++) { pte = __ptep_get(ptep); if (!contpte_is_consistent(pte, pfn, orig_prot)) goto retry; if (pte_dirty(pte)) { orig_pte = pte_mkdirty(orig_pte); break; } } break; } } return orig_pte; } EXPORT_SYMBOL_GPL(contpte_ptep_get_lockless); void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { unsigned long next; unsigned long end; unsigned long pfn; pgprot_t prot; /* * The set_ptes() spec guarantees that when nr > 1, the initial state of * all ptes is not-present. Therefore we never need to unfold or * otherwise invalidate a range before we set the new ptes. * contpte_set_ptes() should never be called for nr < 2. */ VM_WARN_ON(nr == 1); if (!mm_is_user(mm)) return __set_ptes(mm, addr, ptep, pte, nr); end = addr + (nr << PAGE_SHIFT); pfn = pte_pfn(pte); prot = pte_pgprot(pte); do { next = pte_cont_addr_end(addr, end); nr = (next - addr) >> PAGE_SHIFT; pte = pfn_pte(pfn, prot); if (((addr | next | (pfn << PAGE_SHIFT)) & ~CONT_PTE_MASK) == 0) pte = pte_mkcont(pte); else pte = pte_mknoncont(pte); __set_ptes(mm, addr, ptep, pte, nr); addr = next; ptep += nr; pfn += nr; } while (addr != end); } EXPORT_SYMBOL_GPL(contpte_set_ptes); void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { contpte_try_unfold_partial(mm, addr, ptep, nr); __clear_full_ptes(mm, addr, ptep, nr, full); } EXPORT_SYMBOL_GPL(contpte_clear_full_ptes); pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { contpte_try_unfold_partial(mm, addr, ptep, nr); return __get_and_clear_full_ptes(mm, addr, ptep, nr, full); } EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes); int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * ptep_clear_flush_young() technically requires us to clear the access * flag for a _single_ pte. However, the core-mm code actually tracks * access/dirty per folio, not per page. And since we only create a * contig range when the range is covered by a single folio, we can get * away with clearing young for the whole contig range here, so we avoid * having to unfold. * * The 'nr' means consecutive (present) PTEs that map consecutive pages * of the same large folio in a single VMA and a single page table. */ unsigned long end = addr + nr * PAGE_SIZE; int young = 0; ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr); for (; addr != end; ptep++, addr += PAGE_SIZE) young |= __ptep_test_and_clear_young(vma, addr, ptep); return young; } EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes); int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { int young; young = contpte_test_and_clear_young_ptes(vma, addr, ptep, nr); if (young) { unsigned long end = addr + nr * PAGE_SIZE; contpte_align_addr_ptep(&addr, &end, ptep, nr); /* * See comment in __ptep_clear_flush_young(); same rationale for * eliding the trailing DSB applies here. */ __flush_tlb_range_nosync(vma->vm_mm, addr, end, PAGE_SIZE, true, 3); } return young; } EXPORT_SYMBOL_GPL(contpte_clear_flush_young_ptes); void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * If wrprotecting an entire contig range, we can avoid unfolding. Just * set wrprotect and wait for the later mmu_gather flush to invalidate * the tlb. Until the flush, the page may or may not be wrprotected. * After the flush, it is guaranteed wrprotected. If it's a partial * range though, we must unfold, because we can't have a case where * CONT_PTE is set but wrprotect applies to a subset of the PTEs; this * would cause it to continue to be unpredictable after the flush. */ contpte_try_unfold_partial(mm, addr, ptep, nr); __wrprotect_ptes(mm, addr, ptep, nr); } EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes); void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { /* * We can safely clear access/dirty without needing to unfold from * the architectures perspective, even when contpte is set. If the * range starts or ends midway through a contpte block, we can just * expand to include the full contpte block. While this is not * exactly what the core-mm asked for, it tracks access/dirty per * folio, not per page. And since we only create a contpte block * when it is covered by a single folio, we can get away with * clearing access/dirty for the whole block. */ unsigned long start = addr; unsigned long end = start + nr * PAGE_SIZE; ptep = contpte_align_addr_ptep(&start, &end, ptep, nr); __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags); } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); static bool contpte_all_subptes_match_access_flags(pte_t *ptep, pte_t entry) { pte_t *cont_ptep = contpte_align_down(ptep); /* * PFNs differ per sub-PTE. Match only bits consumed by * __ptep_set_access_flags(): AF, DIRTY and write permission. */ const pteval_t cmp_mask = PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; pteval_t entry_cmp = pte_val(entry) & cmp_mask; int i; for (i = 0; i < CONT_PTES; i++) { pteval_t pte_cmp = pte_val(__ptep_get(cont_ptep + i)) & cmp_mask; if (pte_cmp != entry_cmp) return false; } return true; } int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) { unsigned long start_addr; pte_t orig_pte; int i; /* * Check whether all sub-PTEs in the CONT block already match the * requested access flags/write permission, using raw per-PTE values * rather than the gathered ptep_get() view. * * __ptep_set_access_flags() can update AF, dirty and write * permission, but only to make the mapping more permissive. * * ptep_get() gathers AF/dirty state across the whole CONT block, * which is correct for a CPU with FEAT_HAFDBS. But page-table * walkers that evaluate each descriptor individually (e.g. a CPU * without DBM support, or an SMMU without HTTU, or with HA/HD * disabled in CD.TCR) can keep faulting on the target sub-PTE if * only a sibling has been updated. Gathering can therefore cause * false no-ops when only a sibling has been updated: * - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared) * - read faults: target still lacks PTE_AF * * Per Arm ARM (DDI 0487) D8.7.1, any sub-PTE in a CONT range may * become the effective cached translation, so all entries must have * consistent attributes. Check the full CONT block before returning * no-op, and when any sub-PTE mismatches, proceed to update the whole * range. */ if (contpte_all_subptes_match_access_flags(ptep, entry)) return 0; /* * Use raw target pte (not gathered) for write-bit unfold decision. */ orig_pte = pte_mknoncont(__ptep_get(ptep)); /* * We can fix up access/dirty bits without having to unfold the contig * range. But if the write bit is changing, we must unfold. */ if (pte_write(orig_pte) == pte_write(entry)) { /* * For HW access management, we technically only need to update * the flag on a single pte in the range. But for SW access * management, we need to update all the ptes to prevent extra * faults. Avoid per-page tlb flush in __ptep_set_access_flags() * and instead flush the whole range at the end. */ ptep = contpte_align_down(ptep); start_addr = addr = ALIGN_DOWN(addr, CONT_PTE_SIZE); /* * We are not advancing entry because __ptep_set_access_flags() * only consumes access flags from entry. And since we have checked * for the whole contpte block and returned early, pte_same() * within __ptep_set_access_flags() is likely false. */ for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE) __ptep_set_access_flags(vma, addr, ptep, entry, 0); if (dirty) local_flush_tlb_contpte(vma, start_addr); } else { __contpte_try_unfold(vma->vm_mm, addr, ptep, orig_pte); __ptep_set_access_flags(vma, addr, ptep, entry, dirty); } return 1; } EXPORT_SYMBOL_GPL(contpte_ptep_set_access_flags); |
| 1 5 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_device.c - IPsec device offloading code. * * Copyright (c) 2015 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/xfrm.h> #include <linux/notifier.h> #ifdef CONFIG_XFRM_OFFLOAD static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); pskb_pull(skb, skb->mac_len + x->props.header_len - x->props.enc_hdr_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); int phlen = 0; if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); if (x->sel.family != AF_INET6) { phlen = IPV4_BEET_PHMAXLEN; if (x->outer_mode.family == AF_INET6) phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr); } pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen)); } /* Adjust pointers into the packet when IPsec is done at layer2 */ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { case XFRM_MODE_IPTFS: case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_TRANSPORT: if (x->outer_mode.family == AF_INET) return __xfrm_transport_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_transport_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_BEET: if (x->outer_mode.family == AF_INET) return __xfrm_mode_beet_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_beet_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: break; } } static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); __u32 seq = xo->seq.low; seq += skb_shinfo(skb)->gso_segs; if (unlikely(seq < xo->seq.low)) return true; return false; } struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; unsigned long flags; struct xfrm_state *x; struct softnet_data *sd; struct sk_buff *skb2, *nskb, *pskb = NULL; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct net_device *dev = skb->dev; struct sec_path *sp; if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN) return skb; /* The packet was sent to HW IPsec packet offload engine, * but to wrong device. Drop the packet, so it won't skip * XFRM stack. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); err = !skb_queue_empty(&sd->xfrm_backlog); local_irq_restore(flags); if (err) { *again = true; return skb; } if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP); segs = skb_gso_segment(skb, esp_features); if (IS_ERR(segs)) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } else { consume_skb(skb); skb = segs; } } if (!skb->next) { esp_features |= skb->dev->gso_partial_features; xfrm_outer_mode_prep(x, skb); xo->flags |= XFRM_DEV_RESUME; err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) return NULL; XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return NULL; } skb_push(skb, skb->data - skb_mac_header(skb)); return skb; } skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; xfrm_outer_mode_prep(x, skb2); err = x->type_offload->xmit(x, skb2, esp_features); if (!err) { skb2->next = nskb; } else if (err != -EINPROGRESS) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); skb2->next = nskb; kfree_skb_list(skb2); return NULL; } else { if (skb == skb2) skb = nskb; else pskb->next = nskb; continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); pskb = skb2; } return skb; } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { int err; struct dst_entry *dst; struct net_device *dev; struct xfrm_dev_offload *xso = &x->xso; xfrm_address_t *saddr; xfrm_address_t *daddr; bool is_packet_offload; if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) { NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); return -EINVAL; } if (xuo->flags & XFRM_OFFLOAD_INBOUND && x->if_id) { NL_SET_ERR_MSG(extack, "XFRM if_id is not supported in RX path"); return -EINVAL; } is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support TFC padding. */ if (x->tfcpad) { NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { struct xfrm_dst_lookup_params params; if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; } else { saddr = &x->id.daddr; daddr = &x->props.saddr; } memset(¶ms, 0, sizeof(params)); params.net = net; params.saddr = saddr; params.daddr = daddr; params.mark = xfrm_smark_get(0, x); dst = __xfrm_dst_lookup(x->props.family, ¶ms); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; dev = dst->dev; dev_hold(dev); dst_release(dst); } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { xso->dev = NULL; dev_put(dev); return (is_packet_offload) ? -EINVAL : 0; } if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN && !dev->xfrmdev_ops->xdo_dev_state_advance_esn) { NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN"); xso->dev = NULL; dev_put(dev); return -EINVAL; } if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); dev_put(dev); return -EINVAL; } xso->dev = dev; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); if (xuo->flags & XFRM_OFFLOAD_INBOUND) xso->dir = XFRM_DEV_OFFLOAD_IN; else xso->dir = XFRM_DEV_OFFLOAD_OUT; if (is_packet_offload) xso->type = XFRM_DEV_OFFLOAD_PACKET; else xso->type = XFRM_DEV_OFFLOAD_CRYPTO; err = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, extack); if (err) { xso->dev = NULL; xso->dir = 0; netdev_put(dev, &xso->dev_tracker); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xfrm_unset_type_offload(x); /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. */ if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { struct xfrm_dev_offload *xdo = &xp->xdo; struct net_device *dev; int err; if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { /* We support only packet offload mode and it means * that user must set XFRM_OFFLOAD_PACKET bit. */ NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) return -EINVAL; if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { xdo->dev = NULL; dev_put(dev); NL_SET_ERR_MSG(extack, "Policy offload is not supported"); return -EINVAL; } xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: xdo->dir = XFRM_DEV_OFFLOAD_IN; break; case XFRM_POLICY_OUT: xdo->dir = XFRM_DEV_OFFLOAD_OUT; break; case XFRM_POLICY_FWD: xdo->dir = XFRM_DEV_OFFLOAD_FWD; break; default: xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; bool check_tunnel_size; if (!x->type_offload || (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if ((!dev || dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } return false; ok: if (!dev) return true; check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (skb_dst(skb)->ops->family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) return false; if (check_tunnel_size && xfrm4_tunnel_check_size(skb)) return false; break; case AF_INET6: /* Check for IPv6 extensions */ if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) return false; if (check_tunnel_size && xfrm6_tunnel_check_size(skb)) return false; break; default: break; } if (dev->xfrmdev_ops->xdo_dev_offload_ok) return dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); void xfrm_dev_resume(struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret = NETDEV_TX_BUSY; struct netdev_queue *txq; struct softnet_data *sd; unsigned long flags; rcu_read_lock(); txq = netdev_core_pick_tx(dev, skb, NULL); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); if (!dev_xmit_complete(ret)) { local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); skb_queue_tail(&sd->xfrm_backlog, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xfrm_dev_resume); void xfrm_dev_backlog(struct softnet_data *sd) { struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog; struct sk_buff_head list; struct sk_buff *skb; if (skb_queue_empty(xfrm_backlog)) return; __skb_queue_head_init(&list); spin_lock(&xfrm_backlog->lock); skb_queue_splice_init(xfrm_backlog, &list); spin_unlock(&xfrm_backlog->lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); xfrm_dev_resume(skb); } } #endif static int xfrm_api_check(struct net_device *dev) { #ifdef CONFIG_XFRM_OFFLOAD if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && !(dev->features & NETIF_F_HW_ESP)) return NOTIFY_BAD; if ((dev->features & NETIF_F_HW_ESP) && (!(dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_add && dev->xfrmdev_ops->xdo_dev_state_delete))) return NOTIFY_BAD; #else if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM)) return NOTIFY_BAD; #endif return NOTIFY_DONE; } static int xfrm_dev_down(struct net_device *dev) { if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); } return NOTIFY_DONE; } static int xfrm_dev_unregister(struct net_device *dev) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); return NOTIFY_DONE; } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: return xfrm_api_check(dev); case NETDEV_FEAT_CHANGE: return xfrm_api_check(dev); case NETDEV_DOWN: return xfrm_dev_down(dev); case NETDEV_UNREGISTER: return xfrm_dev_unregister(dev); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { .notifier_call = xfrm_dev_event, }; void __init xfrm_dev_init(void) { register_netdevice_notifier(&xfrm_dev_notifier); } |
| 671 15 427 145 146 104 105 105 427 427 428 99 99 97 36 36 36 36 36 36 3 3 34 34 34 34 4 4 244 244 13 13 13 13 11 11 16 16 23 24 132 134 669 671 672 119 120 153 153 152 1341 1351 215 95 276 279 274 276 1 1 239 239 229 229 13 13 372 373 516 515 387 239 239 4 4 15 15 15 3 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies * Copyright (C) 2023 Microsoft Corporation <paul@paul-moore.com> */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/xattr.h> #include <linux/msg.h> #include <linux/overflow.h> #include <linux/perf_event.h> #include <linux/fs.h> #include <net/flow.h> #include <net/sock.h> #include "lsm.h" /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_DEVICE_TREE] = "modifying device tree contents", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_XFRM_SECRET] = "xfrm SA secret", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; bool lsm_debug __ro_after_init; unsigned int lsm_active_cnt __ro_after_init; const struct lsm_id *lsm_idlist[MAX_LSM_COUNT]; struct lsm_blob_sizes blob_sizes; struct kmem_cache *lsm_file_cache; struct kmem_cache *lsm_inode_cache; #define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX /* * Identifier for the LSM static calls. * HOOK is an LSM hook as defined in linux/lsm_hookdefs.h * IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT */ #define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX /* * Call the macro M for each LSM hook MAX_LSM_COUNT times. */ #define LSM_LOOP_UNROLL(M, ...) \ do { \ UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) \ } while (0) #define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) #ifdef CONFIG_HAVE_STATIC_CALL #define LSM_HOOK_TRAMP(NAME, NUM) \ &STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM)) #else #define LSM_HOOK_TRAMP(NAME, NUM) NULL #endif /* * Define static calls and static keys for each LSM hook. */ #define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...) \ DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM), \ *((RET(*)(__VA_ARGS__))NULL)); \ static DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM)); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef DEFINE_LSM_STATIC_CALL /* * Initialise a table of static calls for each LSM hook. * DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY) * and a trampoline (STATIC_CALL_TRAMP) which are used to call * __static_call_update when updating the static call. * * The static calls table is used by early LSMs, some architectures can fault on * unaligned accesses and the fault handling code may not be ready by then. * Thus, the static calls table should be aligned to avoid any unhandled faults * in early init. */ struct lsm_static_calls_table static_calls_table __ro_after_init __aligned(sizeof(u64)) = { #define INIT_LSM_STATIC_CALL(NUM, NAME) \ (struct lsm_static_call) { \ .key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)), \ .trampoline = LSM_HOOK_TRAMP(NAME, NUM), \ .active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM), \ }, #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ .NAME = { \ LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME) \ }, #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef INIT_LSM_STATIC_CALL }; /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_blob_alloc - allocate a composite blob * @dest: the destination for the blob * @size: the size of the blob * @gfp: allocation type * * Allocate a blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_blob_alloc(void **dest, size_t size, gfp_t gfp) { if (size == 0) { *dest = NULL; return 0; } *dest = kzalloc(size, gfp); if (*dest == NULL) return -ENOMEM; return 0; } /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { return lsm_blob_alloc(&cred->security, blob_sizes.lbs_cred, gfp); } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * @gfp: allocation flags * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_inode_alloc(struct inode *inode, gfp_t gfp) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, gfp); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_task_alloc(struct task_struct *task) { return lsm_blob_alloc(&task->security, blob_sizes.lbs_task, GFP_KERNEL); } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { return lsm_blob_alloc(&kip->security, blob_sizes.lbs_ipc, GFP_KERNEL); } #ifdef CONFIG_KEYS /** * lsm_key_alloc - allocate a composite key blob * @key: the key that needs a blob * * Allocate the key blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_key_alloc(struct key *key) { return lsm_blob_alloc(&key->security, blob_sizes.lbs_key, GFP_KERNEL); } #endif /* CONFIG_KEYS */ /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { return lsm_blob_alloc(&mp->security, blob_sizes.lbs_msg_msg, GFP_KERNEL); } /** * lsm_bdev_alloc - allocate a composite block_device blob * @bdev: the block_device that needs a blob * * Allocate the block_device blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bdev_alloc(struct block_device *bdev) { return lsm_blob_alloc(&bdev->bd_security, blob_sizes.lbs_bdev, GFP_KERNEL); } #ifdef CONFIG_BPF_SYSCALL /** * lsm_bpf_map_alloc - allocate a composite bpf_map blob * @map: the bpf_map that needs a blob * * Allocate the bpf_map blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_map_alloc(struct bpf_map *map) { return lsm_blob_alloc(&map->security, blob_sizes.lbs_bpf_map, GFP_KERNEL); } /** * lsm_bpf_prog_alloc - allocate a composite bpf_prog blob * @prog: the bpf_prog that needs a blob * * Allocate the bpf_prog blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_prog_alloc(struct bpf_prog *prog) { return lsm_blob_alloc(&prog->aux->security, blob_sizes.lbs_bpf_prog, GFP_KERNEL); } /** * lsm_bpf_token_alloc - allocate a composite bpf_token blob * @token: the bpf_token that needs a blob * * Allocate the bpf_token blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_token_alloc(struct bpf_token *token) { return lsm_blob_alloc(&token->security, blob_sizes.lbs_bpf_token, GFP_KERNEL); } #endif /* CONFIG_BPF_SYSCALL */ /** * lsm_superblock_alloc - allocate a composite superblock blob * @sb: the superblock that needs a blob * * Allocate the superblock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_superblock_alloc(struct super_block *sb) { return lsm_blob_alloc(&sb->s_security, blob_sizes.lbs_superblock, GFP_KERNEL); } /** * lsm_fill_user_ctx - Fill a user space lsm_ctx structure * @uctx: a userspace LSM context to be filled * @uctx_len: available uctx size (input), used uctx size (output) * @val: the new LSM context value * @val_len: the size of the new LSM context value * @id: LSM id * @flags: LSM defined flags * * Fill all of the fields in a userspace lsm_ctx structure. If @uctx is NULL * simply calculate the required size to output via @utc_len and return * success. * * Returns 0 on success, -E2BIG if userspace buffer is not large enough, * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated. */ int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { struct lsm_ctx *nctx = NULL; size_t nctx_len; int rc = 0; nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *)); if (nctx_len > *uctx_len) { rc = -E2BIG; goto out; } /* no buffer - return success/0 and set @uctx_len to the req size */ if (!uctx) goto out; nctx = kzalloc(nctx_len, GFP_KERNEL); if (nctx == NULL) { rc = -ENOMEM; goto out; } nctx->id = id; nctx->flags = flags; nctx->len = nctx_len; nctx->ctx_len = val_len; memcpy(nctx->ctx, val, val_len); if (copy_to_user(uctx, nctx, nctx_len)) rc = -EFAULT; out: kfree(nctx); *uctx_len = nctx_len; return rc; } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define __CALL_STATIC_VOID(NUM, HOOK, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ } \ } while (0); #define call_void_hook(HOOK, ...) \ do { \ LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \ } while (0) #define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ if (R != LSM_RET_DEFAULT(HOOK)) \ goto LABEL; \ } \ } while (0); #define call_int_hook(HOOK, ...) \ ({ \ __label__ OUT; \ int RC = LSM_RET_DEFAULT(HOOK); \ \ LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__); \ OUT: \ RC; \ }) #define lsm_for_each_hook(scall, NAME) \ for (scall = static_calls_table.NAME; \ scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++) \ if (static_key_enabled(&scall->active->key)) /* Security operations */ /** * security_binder_set_context_mgr() - Check if becoming binder ctx mgr is ok * @mgr: task credentials of current binder process * * Check whether @mgr is allowed to be the binder context manager. * * Return: Return 0 if permission is granted. */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, mgr); } /** * security_binder_transaction() - Check if a binder transaction is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to invoke a binder transaction call to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, from, to); } /** * security_binder_transfer_binder() - Check if a binder transfer is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to transfer a binder reference to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, from, to); } /** * security_binder_transfer_file() - Check if a binder file xfer is allowed * @from: sending process * @to: receiving process * @file: file being transferred * * Check whether @from is allowed to transfer @file to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { return call_int_hook(binder_transfer_file, from, to, file); } /** * security_ptrace_access_check() - Check if tracing is allowed * @child: target process * @mode: PTRACE_MODE flags * * Check permission before allowing the current process to trace the @child * process. Security modules may also want to perform a process tracing check * during an execve in the set_security or apply_creds hooks of tracing check * during an execve in the bprm_set_creds hook of binprm_security_ops if the * process is being traced and its security attributes would be changed by the * execve. * * Return: Returns 0 if permission is granted. */ int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, child, mode); } /** * security_ptrace_traceme() - Check if tracing is allowed * @parent: tracing process * * Check that the @parent process has sufficient permission to trace the * current process before allowing the current process to present itself to the * @parent process for tracing. * * Return: Returns 0 if permission is granted. */ int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, parent); } /** * security_capget() - Get the capability sets for a process * @target: target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Get the @effective, @inheritable, and @permitted capability sets for the * @target process. The hook may also perform permission checking to determine * if the current process is allowed to see the capability sets of the @target * process. * * Return: Returns 0 if the capability sets were successfully obtained. */ int security_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, target, effective, inheritable, permitted); } /** * security_capset() - Set the capability sets for a process * @new: new credentials for the target process * @old: current credentials of the target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Set the @effective, @inheritable, and @permitted capability sets for the * current process. * * Return: Returns 0 and update @new if permission is granted. */ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, new, old, effective, inheritable, permitted); } /** * security_capable() - Check if a process has the necessary capability * @cred: credentials to examine * @ns: user namespace * @cap: capability requested * @opts: capability check options * * Check whether the @tsk process has the @cap capability in the indicated * credentials. @cap contains the capability <include/linux/capability.h>. * @opts contains options for the capable check <include/linux/security.h>. * * Return: Returns 0 if the capability is granted. */ int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, cred, ns, cap, opts); } /** * security_quotactl() - Check if a quotactl() syscall is allowed for this fs * @cmds: commands * @type: type * @id: id * @sb: filesystem * * Check whether the quotactl syscall is allowed for this @sb. * * Return: Returns 0 if permission is granted. */ int security_quotactl(int cmds, int type, int id, const struct super_block *sb) { return call_int_hook(quotactl, cmds, type, id, sb); } /** * security_quota_on() - Check if QUOTAON is allowed for a dentry * @dentry: dentry * * Check whether QUOTAON is allowed for @dentry. * * Return: Returns 0 if permission is granted. */ int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, dentry); } /** * security_syslog() - Check if accessing the kernel message ring is allowed * @type: SYSLOG_ACTION_* type * * Check permission before accessing the kernel message ring or changing * logging to the console. See the syslog(2) manual page for an explanation of * the @type values. * * Return: Return 0 if permission is granted. */ int security_syslog(int type) { return call_int_hook(syslog, type); } /** * security_settime64() - Check if changing the system time is allowed * @ts: new time * @tz: timezone * * Check permission to change the system time, struct timespec64 is defined in * <include/linux/time64.h> and timezone is defined in <include/linux/time.h>. * * Return: Returns 0 if permission is granted. */ int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, ts, tz); } /** * security_vm_enough_memory_mm() - Check if allocating a new mem map is allowed * @mm: mm struct * @pages: number of pages * * Check permissions for allocating a new virtual mapping. If all LSMs return * a positive value, __vm_enough_memory() will be called with cap_sys_admin * set. If at least one LSM returns 0 or negative, __vm_enough_memory() will be * called with cap_sys_admin cleared. * * Return: Returns 0 if permission is granted by the LSM infrastructure to the * caller. */ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct lsm_static_call *scall; int cap_sys_admin = 1; int rc; /* * The module will respond with 0 if it thinks the __vm_enough_memory() * call should be made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module thinks it should * not be set it won't. */ lsm_for_each_hook(scall, vm_enough_memory) { rc = scall->hl->hook.vm_enough_memory(mm, pages); if (rc < 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } /** * security_bprm_creds_for_exec() - Prepare the credentials for exec() * @bprm: binary program information * * If the setup in prepare_exec_creds did not setup @bprm->cred->security * properly for executing @bprm->file, update the LSM's portion of * @bprm->cred->security to be what commit_creds needs to install for the new * program. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. @bprm * contains the linux_binprm structure. * * If execveat(2) is called with the AT_EXECVE_CHECK flag, bprm->is_check is * set. The result must be the same as without this flag even if the execution * will never really happen and @bprm will always be dropped. * * This hook must not change current->cred, only @bprm->cred. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, bprm); } /** * security_bprm_creds_from_file() - Update linux_binprm creds based on file * @bprm: binary program information * @file: associated file * * If @file is setpcap, suid, sgid or otherwise marked to change privilege upon * exec, update @bprm->cred to reflect that change. This is called after * finding the binary that will be executed without an interpreter. This * ensures that the credentials will not be derived from a script that the * binary will need to reopen, which when reopend may end up being a completely * different file. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. The * hook must add to @bprm->per_clear any personality flags that should be * cleared from current->personality. @bprm contains the linux_binprm * structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { return call_int_hook(bprm_creds_from_file, bprm, file); } /** * security_bprm_check() - Mediate binary handler search * @bprm: binary program information * * This hook mediates the point when a search for a binary handler will begin. * It allows a check against the @bprm->cred->security value which was set in * the preceding creds_for_exec call. The argv list and envp list are reliably * available in @bprm. This hook may be called multiple times during a single * execve. @bprm contains the linux_binprm structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_check(struct linux_binprm *bprm) { return call_int_hook(bprm_check_security, bprm); } /** * security_bprm_committing_creds() - Install creds for a process during exec() * @bprm: binary program information * * Prepare to install the new security attributes of a process being * transformed by an execve operation, based on the old credentials pointed to * by @current->cred and the information set in @bprm->cred by the * bprm_creds_for_exec hook. @bprm points to the linux_binprm structure. This * hook is a good place to perform state changes on the process such as closing * open file descriptors to which access will no longer be granted when the * attributes are changed. This is called immediately before commit_creds(). */ void security_bprm_committing_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } /** * security_bprm_committed_creds() - Tidy up after cred install during exec() * @bprm: binary program information * * Tidy up after the installation of the new security attributes of a process * being transformed by an execve operation. The new credentials have, by this * point, been set to @current->cred. @bprm points to the linux_binprm * structure. This hook is a good place to perform state changes on the * process such as clearing out non-inheritable signal state. This is called * immediately after commit_creds(). */ void security_bprm_committed_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } /** * security_fs_context_submount() - Initialise fc->security * @fc: new filesystem context * @reference: dentry reference for submount/remount * * Fill out the ->security field for a new fs_context. * * Return: Returns 0 on success or negative error code on failure. */ int security_fs_context_submount(struct fs_context *fc, struct super_block *reference) { return call_int_hook(fs_context_submount, fc, reference); } /** * security_fs_context_dup() - Duplicate a fs_context LSM blob * @fc: destination filesystem context * @src_fc: source filesystem context * * Allocate and attach a security structure to sc->security. This pointer is * initialised to NULL by the caller. @fc indicates the new filesystem context. * @src_fc indicates the original filesystem context. * * Return: Returns 0 on success or a negative error code on failure. */ int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, fc, src_fc); } /** * security_fs_context_parse_param() - Configure a filesystem context * @fc: filesystem context * @param: filesystem parameter * * Userspace provided a parameter to configure a superblock. The LSM can * consume the parameter or return it to the caller for use elsewhere. * * Return: If the parameter is used by the LSM it should return 0, if it is * returned to the caller -ENOPARAM is returned, otherwise a negative * error code is returned. */ int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct lsm_static_call *scall; int trc; int rc = -ENOPARAM; lsm_for_each_hook(scall, fs_context_parse_param) { trc = scall->hl->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } /** * security_sb_alloc() - Allocate a super_block LSM blob * @sb: filesystem superblock * * Allocate and attach a security structure to the sb->s_security field. The * s_security field is initialized to NULL when the structure is allocated. * @sb contains the super_block structure to be modified. * * Return: Returns 0 if operation was successful. */ int security_sb_alloc(struct super_block *sb) { int rc = lsm_superblock_alloc(sb); if (unlikely(rc)) return rc; rc = call_int_hook(sb_alloc_security, sb); if (unlikely(rc)) security_sb_free(sb); return rc; } /** * security_sb_delete() - Release super_block LSM associated objects * @sb: filesystem superblock * * Release objects tied to a superblock (e.g. inodes). @sb contains the * super_block structure being released. */ void security_sb_delete(struct super_block *sb) { call_void_hook(sb_delete, sb); } /** * security_sb_free() - Free a super_block LSM blob * @sb: filesystem superblock * * Deallocate and clear the sb->s_security field. @sb contains the super_block * structure to be modified. */ void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); kfree(sb->s_security); sb->s_security = NULL; } /** * security_free_mnt_opts() - Free memory associated with mount options * @mnt_opts: LSM processed mount options * * Free memory associated with @mnt_ops. */ void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); /** * security_sb_eat_lsm_opts() - Consume LSM mount options * @options: mount options * @mnt_opts: LSM processed mount options * * Eat (scan @options) and save them in @mnt_opts. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); /** * security_sb_mnt_opts_compat() - Check if new mount options are allowed * @sb: filesystem superblock * @mnt_opts: new mount options * * Determine if the new mount options in @mnt_opts are allowed given the * existing mounted filesystem at @sb. @sb superblock being compared. * * Return: Returns 0 if options are compatible. */ int security_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_mnt_opts_compat, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_mnt_opts_compat); /** * security_sb_remount() - Verify no incompatible mount changes during remount * @sb: filesystem superblock * @mnt_opts: (re)mount options * * Extracts security system specific mount options and verifies no changes are * being made to those options. * * Return: Returns 0 if permission is granted. */ int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); /** * security_sb_kern_mount() - Check if a kernel mount is allowed * @sb: filesystem superblock * * Mount this @sb if allowed by permissions. * * Return: Returns 0 if permission is granted. */ int security_sb_kern_mount(const struct super_block *sb) { return call_int_hook(sb_kern_mount, sb); } /** * security_sb_show_options() - Output the mount options for a superblock * @m: output file * @sb: filesystem superblock * * Show (print on @m) mount options for this @sb. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, m, sb); } /** * security_sb_statfs() - Check if accessing fs stats is allowed * @dentry: superblock handle * * Check permission before obtaining filesystem statistics for the @mnt * mountpoint. @dentry is a handle on the superblock for the filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, dentry); } /** * security_sb_mount() - Check permission for mounting a filesystem * @dev_name: filesystem backing device * @path: mount point * @type: filesystem type * @flags: mount flags * @data: filesystem specific data * * Check permission before an object specified by @dev_name is mounted on the * mount point named by @nd. For an ordinary mount, @dev_name identifies a * device if the file system type requires a device. For a remount * (@flags & MS_REMOUNT), @dev_name is irrelevant. For a loopback/bind mount * (@flags & MS_BIND), @dev_name identifies the pathname of the object being * mounted. * * Return: Returns 0 if permission is granted. */ int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, dev_name, path, type, flags, data); } /** * security_sb_umount() - Check permission for unmounting a filesystem * @mnt: mounted filesystem * @flags: unmount flags * * Check permission before the @mnt file system is unmounted. * * Return: Returns 0 if permission is granted. */ int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, mnt, flags); } /** * security_sb_pivotroot() - Check permissions for pivoting the rootfs * @old_path: new location for current rootfs * @new_path: location of the new rootfs * * Check permission before pivoting the root filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, old_path, new_path); } /** * security_sb_set_mnt_opts() - Set the mount options for a filesystem * @sb: filesystem superblock * @mnt_opts: binary mount options * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Set the security relevant mount options used for a superblock. * * Return: Returns 0 on success, error on failure. */ int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { struct lsm_static_call *scall; int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts); lsm_for_each_hook(scall, sb_set_mnt_opts) { rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags, set_kern_flags); if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts)) break; } return rc; } EXPORT_SYMBOL(security_sb_set_mnt_opts); /** * security_sb_clone_mnt_opts() - Duplicate superblock mount options * @oldsb: source superblock * @newsb: destination superblock * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Copy all security options from a given superblock to another. * * Return: Returns 0 on success, error on failure. */ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); /** * security_move_mount() - Check permissions for moving a mount * @from_path: source mount point * @to_path: destination mount point * * Check permission before a mount is moved. * * Return: Returns 0 if permission is granted. */ int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, from_path, to_path); } /** * security_path_notify() - Check if setting a watch is allowed * @path: file path * @mask: event mask * @obj_type: file path type * * Check permissions before setting a watch on events as defined by @mask, on * an object at @path, whose type is defined by @obj_type. * * Return: Returns 0 if permission is granted. */ int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, path, mask, obj_type); } /** * security_inode_alloc() - Allocate an inode LSM blob * @inode: the inode * @gfp: allocation flags * * Allocate and attach a security structure to @inode->i_security. The * i_security field is initialized to NULL when the inode structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_inode_alloc(struct inode *inode, gfp_t gfp) { int rc = lsm_inode_alloc(inode, gfp); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* The rcu head is at the start of the inode blob */ call_void_hook(inode_free_security_rcu, head); kmem_cache_free(lsm_inode_cache, head); } /** * security_inode_free() - Free an inode's LSM blob * @inode: the inode * * Release any LSM resources associated with @inode, although due to the * inode's RCU protections it is possible that the resources will not be * fully released until after the current RCU grace period has elapsed. * * It is important for LSMs to note that despite being present in a call to * security_inode_free(), @inode may still be referenced in a VFS path walk * and calls to security_inode_permission() may be made during, or after, * a call to security_inode_free(). For this reason the inode->i_security * field is released via a call_rcu() callback and any LSMs which need to * retain inode state for use in security_inode_permission() should only * release that state in the inode_free_security_rcu() LSM hook callback. */ void security_inode_free(struct inode *inode) { call_void_hook(inode_free_security, inode); if (!inode->i_security) return; call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } /** * security_dentry_init_security() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @xattr_name: name of the security/LSM xattr * @lsmctx: pointer to the resulting LSM context * * Compute a context for a dentry as the inode is not yet available since NFSv4 * has no label backed by an EA anyway. It is important to note that * @xattr_name does not need to be free'd by the caller, it is a static string. * * Return: Returns 0 on success, negative values on failure. */ int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, struct lsm_context *lsmctx) { return call_int_hook(dentry_init_security, dentry, mode, name, xattr_name, lsmctx); } EXPORT_SYMBOL(security_dentry_init_security); /** * security_dentry_create_files_as() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @old: creds to use for LSM context calculations * @new: creds to modify * * Compute a context for a dentry as the inode is not yet available and set * that context in passed in creds so that new files are created using that * context. Context is calculated using the passed in creds and not the creds * of the caller. * * Return: Returns 0 on success, error on failure. */ int security_dentry_create_files_as(struct dentry *dentry, int mode, const struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); /** * security_inode_init_security() - Initialize an inode's LSM context * @inode: the inode * @dir: parent directory * @qstr: last component of the pathname * @initxattrs: callback function to write xattrs * @fs_data: filesystem specific data * * Obtain the security attribute name suffix and value to set on a newly * created inode and set up the incore security field for the new inode. This * hook is called by the fs code as part of the inode creation transaction and * provides for atomic labeling of the inode, unlike the post_create/mkdir/... * hooks called by the VFS. * * The hook function is expected to populate the xattrs array, by calling * lsm_get_xattr_slot() to retrieve the slots reserved by the security module * with the lbs_xattr_count field of the lsm_blob_sizes structure. For each * slot, the hook function should set ->name to the attribute name suffix * (e.g. selinux), to allocate ->value (will be freed by the caller) and set it * to the attribute value, to set ->value_len to the length of the value. If * the security module does not use security attributes or does not wish to put * a security attribute on this particular inode, then it should return * -EOPNOTSUPP to skip this processing. * * Return: Returns 0 if the LSM successfully initialized all of the inode * security attributes that are required, negative values otherwise. */ int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct lsm_static_call *scall; struct xattr *new_xattrs = NULL; int ret = -EOPNOTSUPP, xattr_count = 0; if (unlikely(IS_PRIVATE(inode))) return 0; if (!blob_sizes.lbs_xattr_count) return 0; if (initxattrs) { /* Allocate +1 as terminator. */ new_xattrs = kcalloc(blob_sizes.lbs_xattr_count + 1, sizeof(*new_xattrs), GFP_NOFS); if (!new_xattrs) return -ENOMEM; } lsm_for_each_hook(scall, inode_init_security) { ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs, &xattr_count); if (ret && ret != -EOPNOTSUPP) goto out; /* * As documented in lsm_hooks.h, -EOPNOTSUPP in this context * means that the LSM is not willing to provide an xattr, not * that it wants to signal an error. Thus, continue to invoke * the remaining LSMs. */ } /* If initxattrs() is NULL, xattr_count is zero, skip the call. */ if (!xattr_count) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (; xattr_count > 0; xattr_count--) kfree(new_xattrs[xattr_count - 1].value); kfree(new_xattrs); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); /** * security_inode_init_security_anon() - Initialize an anonymous inode * @inode: the inode * @name: the anonymous inode class * @context_inode: an optional related inode * * Set up the incore security field for the new anonymous inode and return * whether the inode creation is permitted by the security module or not. * * Return: Returns 0 on success, -EACCES if the security module denies the * creation of this inode, or another -errno upon other errors. */ int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { return call_int_hook(inode_init_security_anon, inode, name, context_inode); } #ifdef CONFIG_SECURITY_PATH /** * security_path_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a file. Note that this hook is called even * if mknod operation is being done for a regular file. * * Return: Returns 0 if permission is granted. */ int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); /** * security_path_post_mknod() - Update inode security after reg file creation * @idmap: idmap of the mount * @dentry: new file * * Update inode security field after a regular file has been created. */ void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(path_post_mknod, idmap, dentry); } /** * security_path_mkdir() - Check if creating a new directory is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory. * * Return: Returns 0 if permission is granted. */ int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, dir, dentry, mode); } EXPORT_SYMBOL(security_path_mkdir); /** * security_path_rmdir() - Check if removing a directory is allowed * @dir: parent directory * @dentry: directory to remove * * Check the permission to remove a directory. * * Return: Returns 0 if permission is granted. */ int security_path_rmdir(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_rmdir, dir, dentry); } /** * security_path_unlink() - Check if removing a hard link is allowed * @dir: parent directory * @dentry: file * * Check the permission to remove a hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_unlink(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_unlink, dir, dentry); } EXPORT_SYMBOL(security_path_unlink); /** * security_path_symlink() - Check if creating a symbolic link is allowed * @dir: parent directory * @dentry: symbolic link * @old_name: file pathname * * Check the permission to create a symbolic link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_symlink, dir, dentry, old_name); } /** * security_path_link - Check if creating a hard link is allowed * @old_dentry: existing file * @new_dir: new parent directory * @new_dentry: new link * * Check permission before creating a new hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(path_link, old_dentry, new_dir, new_dentry); } /** * security_path_rename() - Check if renaming a file is allowed * @old_dir: parent directory of the old file * @old_dentry: the old file * @new_dir: parent directory of the new file * @new_dentry: the new file * @flags: flags * * Check for permission to rename a file or directory. * * Return: Returns 0 if permission is granted. */ int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; return call_int_hook(path_rename, old_dir, old_dentry, new_dir, new_dentry, flags); } EXPORT_SYMBOL(security_path_rename); /** * security_path_truncate() - Check if truncating a file is allowed * @path: file * * Check permission before truncating the file indicated by path. Note that * truncation permissions may also be checked based on already opened files, * using the security_file_truncate() hook. * * Return: Returns 0 if permission is granted. */ int security_path_truncate(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_truncate, path); } /** * security_path_chmod() - Check if changing the file's mode is allowed * @path: file * @mode: new mode * * Check for permission to change a mode of the file @path. The new mode is * specified in @mode which is a bitmask of constants from * <include/uapi/linux/stat.h>. * * Return: Returns 0 if permission is granted. */ int security_path_chmod(const struct path *path, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chmod, path, mode); } /** * security_path_chown() - Check if changing the file's owner/group is allowed * @path: file * @uid: file owner * @gid: file group * * Check for permission to change owner/group of a file or directory. * * Return: Returns 0 if permission is granted. */ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chown, path, uid, gid); } /** * security_path_chroot() - Check if changing the root directory is allowed * @path: directory * * Check for permission to change root directory. * * Return: Returns 0 if permission is granted. */ int security_path_chroot(const struct path *path) { return call_int_hook(path_chroot, path); } #endif /* CONFIG_SECURITY_PATH */ /** * security_inode_create() - Check if creating a file is allowed * @dir: the parent directory * @dentry: the file being created * @mode: requested file mode * * Check permission to create a regular file. * * Return: Returns 0 if permission is granted. */ int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_create, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_create); /** * security_inode_post_create_tmpfile() - Update inode security of new tmpfile * @idmap: idmap of the mount * @inode: inode of the new tmpfile * * Update inode security data after a tmpfile has been created. */ void security_inode_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { if (unlikely(IS_PRIVATE(inode))) return; call_void_hook(inode_post_create_tmpfile, idmap, inode); } /** * security_inode_link() - Check if creating a hard link is allowed * @old_dentry: existing file * @dir: new parent directory * @new_dentry: new link * * Check permission before creating a new hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(inode_link, old_dentry, dir, new_dentry); } /** * security_inode_unlink() - Check if removing a hard link is allowed * @dir: parent directory * @dentry: file * * Check the permission to remove a hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_unlink(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_unlink, dir, dentry); } /** * security_inode_symlink() - Check if creating a symbolic link is allowed * @dir: parent directory * @dentry: symbolic link * @old_name: existing filename * * Check the permission to create a symbolic link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_symlink(struct inode *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_symlink, dir, dentry, old_name); } /** * security_inode_mkdir() - Check if creating a new directory is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory * associated with inode structure @dir. * * Return: Returns 0 if permission is granted. */ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mkdir, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_mkdir); /** * security_inode_rmdir() - Check if removing a directory is allowed * @dir: parent directory * @dentry: directory to be removed * * Check the permission to remove a directory. * * Return: Returns 0 if permission is granted. */ int security_inode_rmdir(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_rmdir, dir, dentry); } /** * security_inode_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a special file (or a socket or a fifo file * created via the mknod system call). Note that if mknod operation is being * done for a regular file, then the create hook will be called and not this * hook. * * Return: Returns 0 if permission is granted. */ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mknod, dir, dentry, mode, dev); } /** * security_inode_rename() - Check if renaming a file is allowed * @old_dir: parent directory of the old file * @old_dentry: the old file * @new_dir: parent directory of the new file * @new_dentry: the new file * @flags: flags * * Check for permission to rename a file or directory. * * Return: Returns 0 if permission is granted. */ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(inode_rename, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(inode_rename, old_dir, old_dentry, new_dir, new_dentry); } /** * security_inode_readlink() - Check if reading a symbolic link is allowed * @dentry: link * * Check the permission to read the symbolic link. * * Return: Returns 0 if permission is granted. */ int security_inode_readlink(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_readlink, dentry); } /** * security_inode_follow_link() - Check if following a symbolic link is allowed * @dentry: link dentry * @inode: link inode * @rcu: true if in RCU-walk mode * * Check permission to follow a symbolic link when looking up a pathname. If * @rcu is true, @inode is not stable. * * Return: Returns 0 if permission is granted. */ int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_follow_link, dentry, inode, rcu); } /** * security_inode_permission() - Check if accessing an inode is allowed * @inode: inode * @mask: access mask * * Check permission before accessing an inode. This hook is called by the * existing Linux permission function, so a security module can use it to * provide additional checking for existing Linux permission checks. Notice * that this hook is called when a file is opened (as well as many other * operations), whereas the file_security_ops permission hook is called when * the actual read/write operations are performed. * * Return: Returns 0 if permission is granted. */ int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_permission, inode, mask); } /** * security_inode_setattr() - Check if setting file attributes is allowed * @idmap: idmap of the mount * @dentry: file * @attr: new attributes * * Check permission before setting file attributes. Note that the kernel call * to notify_change is performed from several locations, whenever file * attributes change (such as when a file is truncated, chown/chmod operations, * transferring disk quotas, etc). * * Return: Returns 0 if permission is granted. */ int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_setattr, idmap, dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); /** * security_inode_post_setattr() - Update the inode after a setattr operation * @idmap: idmap of the mount * @dentry: file * @ia_valid: file attributes set * * Update inode security field after successful setting file attributes. */ void security_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setattr, idmap, dentry, ia_valid); } /** * security_inode_getattr() - Check if getting file attributes is allowed * @path: file * * Check permission before obtaining file attributes. * * Return: Returns 0 if permission is granted. */ int security_inode_getattr(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(inode_getattr, path); } /** * security_inode_setxattr() - Check if setting file xattrs is allowed * @idmap: idmap of the mount * @dentry: file * @name: xattr name * @value: xattr value * @size: size of xattr value * @flags: flags * * This hook performs the desired permission checks before setting the extended * attributes (xattrs) on @dentry. It is important to note that we have some * additional logic before the main LSM implementation calls to detect if we * need to perform an additional capability check at the LSM layer. * * Normally we enforce a capability check prior to executing the various LSM * hook implementations, but if a LSM wants to avoid this capability check, * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for * xattrs that it wants to avoid the capability check, leaving the LSM fully * responsible for enforcing the access control for the specific xattr. If all * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook, * or return a 0 (the default return value), the capability check is still * performed. If no 'inode_xattr_skipcap' hooks are registered the capability * check is performed. * * Return: Returns 0 if permission is granted. */ int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int rc; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* enforce the capability checks at the lsm layer, if needed */ if (!call_int_hook(inode_xattr_skipcap, name)) { rc = cap_inode_setxattr(dentry, name, value, size, flags); if (rc) return rc; } return call_int_hook(inode_setxattr, idmap, dentry, name, value, size, flags); } /** * security_inode_set_acl() - Check if setting posix acls is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * @kacl: acl struct * * Check permission before setting posix acls, the posix acls in @kacl are * identified by @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_set_acl, idmap, dentry, acl_name, kacl); } /** * security_inode_post_set_acl() - Update inode security from posix acls set * @dentry: file * @acl_name: acl name * @kacl: acl struct * * Update inode security data after successfully setting posix acls on @dentry. * The posix acls in @kacl are identified by @acl_name. */ void security_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_set_acl, dentry, acl_name, kacl); } /** * security_inode_get_acl() - Check if reading posix acls is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Check permission before getting osix acls, the posix acls are identified by * @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_get_acl, idmap, dentry, acl_name); } /** * security_inode_remove_acl() - Check if removing a posix acl is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Check permission before removing posix acls, the posix acls are identified * by @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_remove_acl, idmap, dentry, acl_name); } /** * security_inode_post_remove_acl() - Update inode security after rm posix acls * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Update inode security data after successfully removing posix acls on * @dentry in @idmap. The posix acls are identified by @acl_name. */ void security_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_remove_acl, idmap, dentry, acl_name); } /** * security_inode_post_setxattr() - Update the inode after a setxattr operation * @dentry: file * @name: xattr name * @value: xattr value * @size: xattr value size * @flags: flags * * Update inode security field after successful setxattr operation. */ void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); } /** * security_inode_getxattr() - Check if xattr access is allowed * @dentry: file * @name: xattr name * * Check permission before obtaining the extended attributes identified by * @name for @dentry. * * Return: Returns 0 if permission is granted. */ int security_inode_getxattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_getxattr, dentry, name); } /** * security_inode_listxattr() - Check if listing xattrs is allowed * @dentry: file * * Check permission before obtaining the list of extended attribute names for * @dentry. * * Return: Returns 0 if permission is granted. */ int security_inode_listxattr(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_listxattr, dentry); } /** * security_inode_removexattr() - Check if removing an xattr is allowed * @idmap: idmap of the mount * @dentry: file * @name: xattr name * * This hook performs the desired permission checks before setting the extended * attributes (xattrs) on @dentry. It is important to note that we have some * additional logic before the main LSM implementation calls to detect if we * need to perform an additional capability check at the LSM layer. * * Normally we enforce a capability check prior to executing the various LSM * hook implementations, but if a LSM wants to avoid this capability check, * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for * xattrs that it wants to avoid the capability check, leaving the LSM fully * responsible for enforcing the access control for the specific xattr. If all * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook, * or return a 0 (the default return value), the capability check is still * performed. If no 'inode_xattr_skipcap' hooks are registered the capability * check is performed. * * Return: Returns 0 if permission is granted. */ int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { int rc; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* enforce the capability checks at the lsm layer, if needed */ if (!call_int_hook(inode_xattr_skipcap, name)) { rc = cap_inode_removexattr(idmap, dentry, name); if (rc) return rc; } return call_int_hook(inode_removexattr, idmap, dentry, name); } /** * security_inode_post_removexattr() - Update the inode after a removexattr op * @dentry: file * @name: xattr name * * Update the inode after a successful removexattr operation. */ void security_inode_post_removexattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_removexattr, dentry, name); } /** * security_inode_file_setattr() - check if setting fsxattr is allowed * @dentry: file to set filesystem extended attributes on * @fa: extended attributes to set on the inode * * Called when file_setattr() syscall or FS_IOC_FSSETXATTR ioctl() is called on * inode * * Return: Returns 0 if permission is granted. */ int security_inode_file_setattr(struct dentry *dentry, struct file_kattr *fa) { return call_int_hook(inode_file_setattr, dentry, fa); } /** * security_inode_file_getattr() - check if retrieving fsxattr is allowed * @dentry: file to retrieve filesystem extended attributes from * @fa: extended attributes to get * * Called when file_getattr() syscall or FS_IOC_FSGETXATTR ioctl() is called on * inode * * Return: Returns 0 if permission is granted. */ int security_inode_file_getattr(struct dentry *dentry, struct file_kattr *fa) { return call_int_hook(inode_file_getattr, dentry, fa); } /** * security_inode_need_killpriv() - Check if security_inode_killpriv() required * @dentry: associated dentry * * Called when an inode has been changed to determine if * security_inode_killpriv() should be called. * * Return: Return <0 on error to abort the inode change operation, return 0 if * security_inode_killpriv() does not need to be called, return >0 if * security_inode_killpriv() does need to be called. */ int security_inode_need_killpriv(struct dentry *dentry) { return call_int_hook(inode_need_killpriv, dentry); } /** * security_inode_killpriv() - The setuid bit is removed, update LSM state * @idmap: idmap of the mount * @dentry: associated dentry * * The @dentry's setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. * * Return: Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. */ int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { return call_int_hook(inode_killpriv, idmap, dentry); } /** * security_inode_getsecurity() - Get the xattr security label of an inode * @idmap: idmap of the mount * @inode: inode * @name: xattr name * @buffer: security label buffer * @alloc: allocation flag * * Retrieve a copy of the extended attribute representation of the security * label associated with @name for @inode via @buffer. Note that @name is the * remainder of the attribute name after the security prefix has been removed. * @alloc is used to specify if the call should return a value via the buffer * or just the value length. * * Return: Returns size of buffer on success. */ int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_getsecurity); return call_int_hook(inode_getsecurity, idmap, inode, name, buffer, alloc); } /** * security_inode_setsecurity() - Set the xattr security label of an inode * @inode: inode * @name: xattr name * @value: security label * @size: length of security label * @flags: flags * * Set the security label associated with @name for @inode from the extended * attribute value @value. @size indicates the size of the @value in bytes. * @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. Note that @name is the * remainder of the attribute name after the security. prefix has been removed. * * Return: Returns 0 on success. */ int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_setsecurity); return call_int_hook(inode_setsecurity, inode, name, value, size, flags); } /** * security_inode_listsecurity() - List the xattr security label names * @inode: inode * @buffer: buffer * @buffer_size: size of buffer * * Copy the extended attribute names for the security labels associated with * @inode into @buffer. The maximum size of @buffer is specified by * @buffer_size. @buffer may be NULL to request the size of the buffer * required. * * Return: Returns number of bytes used/required on success. */ int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_listsecurity, inode, buffer, buffer_size); } EXPORT_SYMBOL(security_inode_listsecurity); /** * security_inode_getlsmprop() - Get an inode's LSM data * @inode: inode * @prop: lsm specific information to return * * Get the lsm specific information associated with the node. */ void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop) { call_void_hook(inode_getlsmprop, inode, prop); } /** * security_inode_copy_up() - Create new creds for an overlayfs copy-up op * @src: union dentry of copy-up file * @new: newly created creds * * A file is about to be copied up from lower layer to upper layer of overlay * filesystem. Security module can prepare a set of new creds and modify as * need be and return new creds. Caller will switch to new creds temporarily to * create new file and release newly allocated creds. * * Return: Returns 0 on success or a negative error code on error. */ int security_inode_copy_up(struct dentry *src, struct cred **new) { return call_int_hook(inode_copy_up, src, new); } EXPORT_SYMBOL(security_inode_copy_up); /** * security_inode_copy_up_xattr() - Filter xattrs in an overlayfs copy-up op * @src: union dentry of copy-up file * @name: xattr name * * Filter the xattrs being copied up when a unioned file is copied up from a * lower layer to the union/overlay layer. The caller is responsible for * reading and writing the xattrs, this hook is merely a filter. * * Return: Returns 0 to accept the xattr, -ECANCELED to discard the xattr, * -EOPNOTSUPP if the security module does not know about attribute, * or a negative error code to abort the copy up. */ int security_inode_copy_up_xattr(struct dentry *src, const char *name) { int rc; rc = call_int_hook(inode_copy_up_xattr, src, name); if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) return rc; return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); /** * security_inode_setintegrity() - Set the inode's integrity data * @inode: inode * @type: type of integrity, e.g. hash digest, signature, etc * @value: the integrity value * @size: size of the integrity value * * Register a verified integrity measurement of a inode with LSMs. * LSMs should free the previously saved data if @value is NULL. * * Return: Returns 0 on success, negative values on failure. */ int security_inode_setintegrity(const struct inode *inode, enum lsm_integrity_type type, const void *value, size_t size) { return call_int_hook(inode_setintegrity, inode, type, value, size); } EXPORT_SYMBOL(security_inode_setintegrity); /** * security_kernfs_init_security() - Init LSM context for a kernfs node * @kn_dir: parent kernfs node * @kn: the kernfs node to initialize * * Initialize the security context of a newly created kernfs node based on its * own and its parent's attributes. * * Return: Returns 0 if permission is granted. */ int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return call_int_hook(kernfs_init_security, kn_dir, kn); } /** * security_file_permission() - Check file permissions * @file: file * @mask: requested permissions * * Check file permissions before accessing an open file. This hook is called * by various operations that read or write files. A security module can use * this hook to perform additional checking on these operations, e.g. to * revalidate permissions on use to support privilege bracketing or policy * changes. Notice that this hook is used when the actual read/write * operations are performed, whereas the inode_security_ops hook is called when * a file is opened (as well as many other operations). Although this hook can * be used to revalidate permissions for various system call operations that * read or write files, it does not address the revalidation of permissions for * memory-mapped files. Security modules must handle this separately if they * need such revalidation. * * Return: Returns 0 if permission is granted. */ int security_file_permission(struct file *file, int mask) { return call_int_hook(file_permission, file, mask); } /** * security_file_alloc() - Allocate and init a file's LSM blob * @file: the file * * Allocate and attach a security structure to the file->f_security field. The * security field is initialized to NULL when the structure is first created. * * Return: Return 0 if the hook is successful and permission is granted. */ int security_file_alloc(struct file *file) { int rc = lsm_file_alloc(file); if (rc) return rc; rc = call_int_hook(file_alloc_security, file); if (unlikely(rc)) security_file_free(file); return rc; } /** * security_file_release() - Perform actions before releasing the file ref * @file: the file * * Perform actions before releasing the last reference to a file. */ void security_file_release(struct file *file) { call_void_hook(file_release, file); } /** * security_file_free() - Free a file's LSM blob * @file: the file * * Deallocate and free any security structures stored in file->f_security. */ void security_file_free(struct file *file) { void *blob; call_void_hook(file_free_security, file); blob = file->f_security; if (blob) { file->f_security = NULL; kmem_cache_free(lsm_file_cache, blob); } } /** * security_file_ioctl() - Check if an ioctl is allowed * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Check permission for an ioctl operation on @file. Note that @arg sometimes * represents a user space pointer; in other cases, it may be a simple integer * value. When @arg represents a user space pointer, it should never be used * by the security module. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl); /** * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Compat version of security_file_ioctl() that correctly handles 32-bit * processes running on 64-bit kernels. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl_compat, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl_compat); static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* * Does we have PROT_READ and does the application expect * it to imply PROT_EXEC? If not, nothing to talk about... */ if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) return prot; if (!(current->personality & READ_IMPLIES_EXEC)) return prot; /* * if that's an anonymous mapping, let it. */ if (!file) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!path_noexec(&file->f_path)) { #ifndef CONFIG_MMU if (file->f_op->mmap_capabilities) { unsigned caps = file->f_op->mmap_capabilities(file); if (!(caps & NOMMU_MAP_EXEC)) return prot; } #endif return prot | PROT_EXEC; } /* anything on noexec mount won't get PROT_EXEC */ return prot; } /** * security_mmap_file() - Check if mmap'ing a file is allowed * @file: file * @prot: protection applied by the kernel * @flags: flags * * Check permissions for a mmap operation. The @file may be NULL, e.g. if * mapping anonymous memory. * * Return: Returns 0 if permission is granted. */ int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { return call_int_hook(mmap_file, file, prot, mmap_prot(file, prot), flags); } /** * security_mmap_addr() - Check if mmap'ing an address is allowed * @addr: address * * Check permissions for a mmap operation at @addr. * * Return: Returns 0 if permission is granted. */ int security_mmap_addr(unsigned long addr) { return call_int_hook(mmap_addr, addr); } /** * security_file_mprotect() - Check if changing memory protections is allowed * @vma: memory region * @reqprot: application requested protection * @prot: protection applied by the kernel * * Check permissions before changing memory access permissions. * * Return: Returns 0 if permission is granted. */ int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { return call_int_hook(file_mprotect, vma, reqprot, prot); } /** * security_file_lock() - Check if a file lock is allowed * @file: file * @cmd: lock operation (e.g. F_RDLCK, F_WRLCK) * * Check permission before performing file locking operations. Note the hook * mediates both flock and fcntl style locks. * * Return: Returns 0 if permission is granted. */ int security_file_lock(struct file *file, unsigned int cmd) { return call_int_hook(file_lock, file, cmd); } /** * security_file_fcntl() - Check if fcntl() op is allowed * @file: file * @cmd: fcntl command * @arg: command argument * * Check permission before allowing the file operation specified by @cmd from * being performed on the file @file. Note that @arg sometimes represents a * user space pointer; in other cases, it may be a simple integer value. When * @arg represents a user space pointer, it should never be used by the * security module. * * Return: Returns 0 if permission is granted. */ int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_fcntl, file, cmd, arg); } /** * security_file_set_fowner() - Set the file owner info in the LSM blob * @file: the file * * Save owner security information (typically from current->security) in * file->f_security for later use by the send_sigiotask hook. * * This hook is called with file->f_owner.lock held. * * Return: Returns 0 on success. */ void security_file_set_fowner(struct file *file) { call_void_hook(file_set_fowner, file); } /** * security_file_send_sigiotask() - Check if sending SIGIO/SIGURG is allowed * @tsk: target task * @fown: signal sender * @sig: signal to be sent, SIGIO is sent if 0 * * Check permission for the file owner @fown to send SIGIO or SIGURG to the * process @tsk. Note that this hook is sometimes called from interrupt. Note * that the fown_struct, @fown, is never outside the context of a struct file, * so the file structure (and associated security information) can always be * obtained: container_of(fown, struct file, f_owner). * * Return: Returns 0 if permission is granted. */ int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig) { return call_int_hook(file_send_sigiotask, tsk, fown, sig); } /** * security_file_receive() - Check if receiving a file via IPC is allowed * @file: file being received * * This hook allows security modules to control the ability of a process to * receive an open file descriptor via socket IPC. * * Return: Returns 0 if permission is granted. */ int security_file_receive(struct file *file) { return call_int_hook(file_receive, file); } /** * security_file_open() - Save open() time state for late use by the LSM * @file: * * Save open-time permission checking state for later use upon file_permission, * and recheck access if anything has changed since inode_permission. * * We can check if a file is opened for execution (e.g. execve(2) call), either * directly or indirectly (e.g. ELF's ld.so) by checking file->f_flags & * __FMODE_EXEC . * * Return: Returns 0 if permission is granted. */ int security_file_open(struct file *file) { return call_int_hook(file_open, file); } /** * security_file_post_open() - Evaluate a file after it has been opened * @file: the file * @mask: access mask * * Evaluate an opened file and the access mask requested with open(). The hook * is useful for LSMs that require the file content to be available in order to * make decisions. * * Return: Returns 0 if permission is granted. */ int security_file_post_open(struct file *file, int mask) { return call_int_hook(file_post_open, file, mask); } EXPORT_SYMBOL_GPL(security_file_post_open); /** * security_file_truncate() - Check if truncating a file is allowed * @file: file * * Check permission before truncating a file, i.e. using ftruncate. Note that * truncation permission may also be checked based on the path, using the * @path_truncate hook. * * Return: Returns 0 if permission is granted. */ int security_file_truncate(struct file *file) { return call_int_hook(file_truncate, file); } /** * security_task_alloc() - Allocate a task's LSM blob * @task: the task * @clone_flags: flags indicating what is being shared * * Handle allocation of task-related resources. * * Return: Returns a zero on success, negative values on failure. */ int security_task_alloc(struct task_struct *task, u64 clone_flags) { int rc = lsm_task_alloc(task); if (rc) return rc; rc = call_int_hook(task_alloc, task, clone_flags); if (unlikely(rc)) security_task_free(task); return rc; } /** * security_task_free() - Free a task's LSM blob and related resources * @task: task * * Handle release of task-related resources. Note that this can be called from * interrupt context. */ void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); kfree(task->security); task->security = NULL; } /** * security_cred_alloc_blank() - Allocate the min memory to allow cred_transfer * @cred: credentials * @gfp: gfp flags * * Only allocate sufficient memory and attach to @cred such that * cred_transfer() will not get ENOMEM. * * Return: Returns 0 on success, negative values on failure. */ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { int rc = lsm_cred_alloc(cred, gfp); if (rc) return rc; rc = call_int_hook(cred_alloc_blank, cred, gfp); if (unlikely(rc)) security_cred_free(cred); return rc; } /** * security_cred_free() - Free the cred's LSM blob and associated resources * @cred: credentials * * Deallocate and clear the cred->security field in a set of credentials. */ void security_cred_free(struct cred *cred) { /* * There is a failure case in prepare_creds() that * may result in a call here with ->security being NULL. */ if (unlikely(cred->security == NULL)) return; call_void_hook(cred_free, cred); kfree(cred->security); cred->security = NULL; } /** * security_prepare_creds() - Prepare a new set of credentials * @new: new credentials * @old: original credentials * @gfp: gfp flags * * Prepare a new set of credentials by copying the data from the old set. * * Return: Returns 0 on success, negative values on failure. */ int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { int rc = lsm_cred_alloc(new, gfp); if (rc) return rc; rc = call_int_hook(cred_prepare, new, old, gfp); if (unlikely(rc)) security_cred_free(new); return rc; } /** * security_transfer_creds() - Transfer creds * @new: target credentials * @old: original credentials * * Transfer data from original creds to new creds. */ void security_transfer_creds(struct cred *new, const struct cred *old) { call_void_hook(cred_transfer, new, old); } /** * security_cred_getsecid() - Get the secid from a set of credentials * @c: credentials * @secid: secid value * * Retrieve the security identifier of the cred structure @c. In case of * failure, @secid will be set to zero. */ void security_cred_getsecid(const struct cred *c, u32 *secid) { *secid = 0; call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); /** * security_cred_getlsmprop() - Get the LSM data from a set of credentials * @c: credentials * @prop: destination for the LSM data * * Retrieve the security data of the cred structure @c. In case of * failure, @prop will be cleared. */ void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(cred_getlsmprop, c, prop); } EXPORT_SYMBOL(security_cred_getlsmprop); /** * security_kernel_act_as() - Set the kernel credentials to act as secid * @new: credentials * @secid: secid * * Set the credentials for a kernel service to act as (subjective context). * The current task must be the one that nominated @secid. * * Return: Returns 0 if successful. */ int security_kernel_act_as(struct cred *new, u32 secid) { return call_int_hook(kernel_act_as, new, secid); } /** * security_kernel_create_files_as() - Set file creation context using an inode * @new: target credentials * @inode: reference inode * * Set the file creation context in a set of credentials to be the same as the * objective context of the specified inode. The current task must be the one * that nominated @inode. * * Return: Returns 0 if successful. */ int security_kernel_create_files_as(struct cred *new, struct inode *inode) { return call_int_hook(kernel_create_files_as, new, inode); } /** * security_kernel_module_request() - Check if loading a module is allowed * @kmod_name: module name * * Ability to trigger the kernel to automatically upcall to userspace for * userspace to load a kernel module with the given name. * * Return: Returns 0 if successful. */ int security_kernel_module_request(char *kmod_name) { return call_int_hook(kernel_module_request, kmod_name); } /** * security_kernel_read_file() - Read a file specified by userspace * @file: file * @id: file identifier * @contents: trust if security_kernel_post_read_file() will be called * * Read a file specified by userspace. * * Return: Returns 0 if permission is granted. */ int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { return call_int_hook(kernel_read_file, file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); /** * security_kernel_post_read_file() - Read a file specified by userspace * @file: file * @buf: file contents * @size: size of file contents * @id: file identifier * * Read a file specified by userspace. This must be paired with a prior call * to security_kernel_read_file() call that indicated this hook would also be * called, see security_kernel_read_file() for more information. * * Return: Returns 0 if permission is granted. */ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { return call_int_hook(kernel_post_read_file, file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); /** * security_kernel_load_data() - Load data provided by userspace * @id: data identifier * @contents: true if security_kernel_post_load_data() will be called * * Load data provided by userspace. * * Return: Returns 0 if permission is granted. */ int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { return call_int_hook(kernel_load_data, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); /** * security_kernel_post_load_data() - Load userspace data from a non-file source * @buf: data * @size: size of data * @id: data identifier * @description: text description of data, specific to the id value * * Load data provided by a non-file source (usually userspace buffer). This * must be paired with a prior security_kernel_load_data() call that indicated * this hook would also be called, see security_kernel_load_data() for more * information. * * Return: Returns 0 if permission is granted. */ int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { return call_int_hook(kernel_post_load_data, buf, size, id, description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); /** * security_task_fix_setuid() - Update LSM with new user id attributes * @new: updated credentials * @old: credentials being replaced * @flags: LSM_SETID_* flag values * * Update the module's state after setting one or more of the user identity * attributes of the current process. The @flags parameter indicates which of * the set*uid system calls invoked this hook. If @new is the set of * credentials that will be installed. Modifications should be made to this * rather than to @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setuid, new, old, flags); } /** * security_task_fix_setgid() - Update LSM with new group id attributes * @new: updated credentials * @old: credentials being replaced * @flags: LSM_SETID_* flag value * * Update the module's state after setting one or more of the group identity * attributes of the current process. The @flags parameter indicates which of * the set*gid system calls invoked this hook. @new is the set of credentials * that will be installed. Modifications should be made to this rather than to * @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setgid, new, old, flags); } /** * security_task_fix_setgroups() - Update LSM with new supplementary groups * @new: updated credentials * @old: credentials being replaced * * Update the module's state after setting the supplementary group identity * attributes of the current process. @new is the set of credentials that will * be installed. Modifications should be made to this rather than to * @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setgroups(struct cred *new, const struct cred *old) { return call_int_hook(task_fix_setgroups, new, old); } /** * security_task_setpgid() - Check if setting the pgid is allowed * @p: task being modified * @pgid: new pgid * * Check permission before setting the process group identifier of the process * @p to @pgid. * * Return: Returns 0 if permission is granted. */ int security_task_setpgid(struct task_struct *p, pid_t pgid) { return call_int_hook(task_setpgid, p, pgid); } /** * security_task_getpgid() - Check if getting the pgid is allowed * @p: task * * Check permission before getting the process group identifier of the process * @p. * * Return: Returns 0 if permission is granted. */ int security_task_getpgid(struct task_struct *p) { return call_int_hook(task_getpgid, p); } /** * security_task_getsid() - Check if getting the session id is allowed * @p: task * * Check permission before getting the session identifier of the process @p. * * Return: Returns 0 if permission is granted. */ int security_task_getsid(struct task_struct *p) { return call_int_hook(task_getsid, p); } /** * security_current_getlsmprop_subj() - Current task's subjective LSM data * @prop: lsm specific information * * Retrieve the subjective security identifier of the current task and return * it in @prop. */ void security_current_getlsmprop_subj(struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(current_getlsmprop_subj, prop); } EXPORT_SYMBOL(security_current_getlsmprop_subj); /** * security_task_getlsmprop_obj() - Get a task's objective LSM data * @p: target task * @prop: lsm specific information * * Retrieve the objective security identifier of the task_struct in @p and * return it in @prop. */ void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(task_getlsmprop_obj, p, prop); } EXPORT_SYMBOL(security_task_getlsmprop_obj); /** * security_task_setnice() - Check if setting a task's nice value is allowed * @p: target task * @nice: nice value * * Check permission before setting the nice value of @p to @nice. * * Return: Returns 0 if permission is granted. */ int security_task_setnice(struct task_struct *p, int nice) { return call_int_hook(task_setnice, p, nice); } /** * security_task_setioprio() - Check if setting a task's ioprio is allowed * @p: target task * @ioprio: ioprio value * * Check permission before setting the ioprio value of @p to @ioprio. * * Return: Returns 0 if permission is granted. */ int security_task_setioprio(struct task_struct *p, int ioprio) { return call_int_hook(task_setioprio, p, ioprio); } /** * security_task_getioprio() - Check if getting a task's ioprio is allowed * @p: task * * Check permission before getting the ioprio value of @p. * * Return: Returns 0 if permission is granted. */ int security_task_getioprio(struct task_struct *p) { return call_int_hook(task_getioprio, p); } /** * security_task_prlimit() - Check if get/setting resources limits is allowed * @cred: current task credentials * @tcred: target task credentials * @flags: LSM_PRLIMIT_* flag bits indicating a get/set/both * * Check permission before getting and/or setting the resource limits of * another task. * * Return: Returns 0 if permission is granted. */ int security_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { return call_int_hook(task_prlimit, cred, tcred, flags); } /** * security_task_setrlimit() - Check if setting a new rlimit value is allowed * @p: target task's group leader * @resource: resource whose limit is being set * @new_rlim: new resource limit * * Check permission before setting the resource limits of process @p for * @resource to @new_rlim. The old resource limit values can be examined by * dereferencing (p->signal->rlim + resource). * * Return: Returns 0 if permission is granted. */ int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { return call_int_hook(task_setrlimit, p, resource, new_rlim); } /** * security_task_setscheduler() - Check if setting sched policy/param is allowed * @p: target task * * Check permission before setting scheduling policy and/or parameters of * process @p. * * Return: Returns 0 if permission is granted. */ int security_task_setscheduler(struct task_struct *p) { return call_int_hook(task_setscheduler, p); } /** * security_task_getscheduler() - Check if getting scheduling info is allowed * @p: target task * * Check permission before obtaining scheduling information for process @p. * * Return: Returns 0 if permission is granted. */ int security_task_getscheduler(struct task_struct *p) { return call_int_hook(task_getscheduler, p); } /** * security_task_movememory() - Check if moving memory is allowed * @p: task * * Check permission before moving memory owned by process @p. * * Return: Returns 0 if permission is granted. */ int security_task_movememory(struct task_struct *p) { return call_int_hook(task_movememory, p); } /** * security_task_kill() - Check if sending a signal is allowed * @p: target process * @info: signal information * @sig: signal value * @cred: credentials of the signal sender, NULL if @current * * Check permission before sending signal @sig to @p. @info can be NULL, the * constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming from * the kernel and should typically be permitted. SIGIO signals are handled * separately by the send_sigiotask hook in file_security_ops. * * Return: Returns 0 if permission is granted. */ int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, p, info, sig, cred); } /** * security_task_prctl() - Check if a prctl op is allowed * @option: operation * @arg2: argument * @arg3: argument * @arg4: argument * @arg5: argument * * Check permission before performing a process control operation on the * current process. * * Return: Return -ENOSYS if no-one wanted to handle this op, any other value * to cause prctl() to return immediately with that value. */ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); struct lsm_static_call *scall; lsm_for_each_hook(scall, task_prctl) { thisrc = scall->hl->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; } } return rc; } /** * security_task_to_inode() - Set the security attributes of a task's inode * @p: task * @inode: inode * * Set the security attributes for an inode based on an associated task's * security attributes, e.g. for /proc/pid inodes. */ void security_task_to_inode(struct task_struct *p, struct inode *inode) { call_void_hook(task_to_inode, p, inode); } /** * security_create_user_ns() - Check if creating a new userns is allowed * @cred: prepared creds * * Check permission prior to creating a new user namespace. * * Return: Returns 0 if successful, otherwise < 0 error code. */ int security_create_user_ns(const struct cred *cred) { return call_int_hook(userns_create, cred); } /** * security_ipc_permission() - Check if sysv ipc access is allowed * @ipcp: ipc permission structure * @flag: requested permissions * * Check permissions for access to IPC. * * Return: Returns 0 if permission is granted. */ int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { return call_int_hook(ipc_permission, ipcp, flag); } /** * security_ipc_getlsmprop() - Get the sysv ipc object LSM data * @ipcp: ipc permission structure * @prop: pointer to lsm information * * Get the lsm information associated with the ipc object. */ void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(ipc_getlsmprop, ipcp, prop); } /** * security_msg_msg_alloc() - Allocate a sysv ipc message LSM blob * @msg: message structure * * Allocate and attach a security structure to the msg->security field. The * security field is initialized to NULL when the structure is first created. * * Return: Return 0 if operation was successful and permission is granted. */ int security_msg_msg_alloc(struct msg_msg *msg) { int rc = lsm_msg_msg_alloc(msg); if (unlikely(rc)) return rc; rc = call_int_hook(msg_msg_alloc_security, msg); if (unlikely(rc)) security_msg_msg_free(msg); return rc; } /** * security_msg_msg_free() - Free a sysv ipc message LSM blob * @msg: message structure * * Deallocate the security structure for this message. */ void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; } /** * security_msg_queue_alloc() - Allocate a sysv ipc msg queue LSM blob * @msq: sysv ipc permission structure * * Allocate and attach a security structure to @msg. The security field is * initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_msg_queue_alloc(struct kern_ipc_perm *msq) { int rc = lsm_ipc_alloc(msq); if (unlikely(rc)) return rc; rc = call_int_hook(msg_queue_alloc_security, msq); if (unlikely(rc)) security_msg_queue_free(msq); return rc; } /** * security_msg_queue_free() - Free a sysv ipc msg queue LSM blob * @msq: sysv ipc permission structure * * Deallocate security field @perm->security for the message queue. */ void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); kfree(msq->security); msq->security = NULL; } /** * security_msg_queue_associate() - Check if a msg queue operation is allowed * @msq: sysv ipc permission structure * @msqflg: operation flags * * Check permission when a message queue is requested through the msgget system * call. This hook is only called when returning the message queue identifier * for an existing message queue, not when a new message queue is created. * * Return: Return 0 if permission is granted. */ int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { return call_int_hook(msg_queue_associate, msq, msqflg); } /** * security_msg_queue_msgctl() - Check if a msg queue operation is allowed * @msq: sysv ipc permission structure * @cmd: operation * * Check permission when a message control operation specified by @cmd is to be * performed on the message queue with permissions. * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { return call_int_hook(msg_queue_msgctl, msq, cmd); } /** * security_msg_queue_msgsnd() - Check if sending a sysv ipc message is allowed * @msq: sysv ipc permission structure * @msg: message * @msqflg: operation flags * * Check permission before a message, @msg, is enqueued on the message queue * with permissions specified in @msq. * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { return call_int_hook(msg_queue_msgsnd, msq, msg, msqflg); } /** * security_msg_queue_msgrcv() - Check if receiving a sysv ipc msg is allowed * @msq: sysv ipc permission structure * @msg: message * @target: target task * @type: type of message requested * @mode: operation flags * * Check permission before a message, @msg, is removed from the message queue. * The @target task structure contains a pointer to the process that will be * receiving the message (not equal to the current process when inline receives * are being performed). * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { return call_int_hook(msg_queue_msgrcv, msq, msg, target, type, mode); } /** * security_shm_alloc() - Allocate a sysv shm LSM blob * @shp: sysv ipc permission structure * * Allocate and attach a security structure to the @shp security field. The * security field is initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_shm_alloc(struct kern_ipc_perm *shp) { int rc = lsm_ipc_alloc(shp); if (unlikely(rc)) return rc; rc = call_int_hook(shm_alloc_security, shp); if (unlikely(rc)) security_shm_free(shp); return rc; } /** * security_shm_free() - Free a sysv shm LSM blob * @shp: sysv ipc permission structure * * Deallocate the security structure @perm->security for the memory segment. */ void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); kfree(shp->security); shp->security = NULL; } /** * security_shm_associate() - Check if a sysv shm operation is allowed * @shp: sysv ipc permission structure * @shmflg: operation flags * * Check permission when a shared memory region is requested through the shmget * system call. This hook is only called when returning the shared memory * region identifier for an existing region, not when a new shared memory * region is created. * * Return: Returns 0 if permission is granted. */ int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) { return call_int_hook(shm_associate, shp, shmflg); } /** * security_shm_shmctl() - Check if a sysv shm operation is allowed * @shp: sysv ipc permission structure * @cmd: operation * * Check permission when a shared memory control operation specified by @cmd is * to be performed on the shared memory region with permissions in @shp. * * Return: Return 0 if permission is granted. */ int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { return call_int_hook(shm_shmctl, shp, cmd); } /** * security_shm_shmat() - Check if a sysv shm attach operation is allowed * @shp: sysv ipc permission structure * @shmaddr: address of memory region to attach * @shmflg: operation flags * * Check permissions prior to allowing the shmat system call to attach the * shared memory segment with permissions @shp to the data segment of the * calling process. The attaching address is specified by @shmaddr. * * Return: Returns 0 if permission is granted. */ int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { return call_int_hook(shm_shmat, shp, shmaddr, shmflg); } /** * security_sem_alloc() - Allocate a sysv semaphore LSM blob * @sma: sysv ipc permission structure * * Allocate and attach a security structure to the @sma security field. The * security field is initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_sem_alloc(struct kern_ipc_perm *sma) { int rc = lsm_ipc_alloc(sma); if (unlikely(rc)) return rc; rc = call_int_hook(sem_alloc_security, sma); if (unlikely(rc)) security_sem_free(sma); return rc; } /** * security_sem_free() - Free a sysv semaphore LSM blob * @sma: sysv ipc permission structure * * Deallocate security structure @sma->security for the semaphore. */ void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); kfree(sma->security); sma->security = NULL; } /** * security_sem_associate() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @semflg: operation flags * * Check permission when a semaphore is requested through the semget system * call. This hook is only called when returning the semaphore identifier for * an existing semaphore, not when a new one must be created. * * Return: Returns 0 if permission is granted. */ int security_sem_associate(struct kern_ipc_perm *sma, int semflg) { return call_int_hook(sem_associate, sma, semflg); } /** * security_sem_semctl() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @cmd: operation * * Check permission when a semaphore operation specified by @cmd is to be * performed on the semaphore. * * Return: Returns 0 if permission is granted. */ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd) { return call_int_hook(sem_semctl, sma, cmd); } /** * security_sem_semop() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @sops: operations to perform * @nsops: number of operations * @alter: flag indicating changes will be made * * Check permissions before performing operations on members of the semaphore * set. If the @alter flag is nonzero, the semaphore set may be modified. * * Return: Returns 0 if permission is granted. */ int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { return call_int_hook(sem_semop, sma, sops, nsops, alter); } /** * security_d_instantiate() - Populate an inode's LSM state based on a dentry * @dentry: dentry * @inode: inode * * Fill in @inode security information for a @dentry if allowed. */ void security_d_instantiate(struct dentry *dentry, struct inode *inode) { if (unlikely(inode && IS_PRIVATE(inode))) return; call_void_hook(d_instantiate, dentry, inode); } EXPORT_SYMBOL(security_d_instantiate); /* * Please keep this in sync with it's counterpart in security/lsm_syscalls.c */ /** * security_getselfattr - Read an LSM attribute of the current process. * @attr: which attribute to return * @uctx: the user-space destination for the information, or NULL * @size: pointer to the size of space available to receive the data * @flags: special handling options. LSM_FLAG_SINGLE indicates that only * attributes associated with the LSM identified in the passed @ctx be * reported. * * A NULL value for @uctx can be used to get both the number of attributes * and the size of the data. * * Returns the number of attributes found on success, negative value * on error. @size is reset to the total size of the data. * If @size is insufficient to contain the data -E2BIG is returned. */ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 __user *size, u32 flags) { struct lsm_static_call *scall; struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, }; u8 __user *base = (u8 __user *)uctx; u32 entrysize; u32 total = 0; u32 left; bool toobig = false; bool single = false; int count = 0; int rc; if (attr == LSM_ATTR_UNDEF) return -EINVAL; if (size == NULL) return -EINVAL; if (get_user(left, size)) return -EFAULT; if (flags) { /* * Only flag supported is LSM_FLAG_SINGLE */ if (flags != LSM_FLAG_SINGLE || !uctx) return -EINVAL; if (copy_from_user(&lctx, uctx, sizeof(lctx))) return -EFAULT; /* * If the LSM ID isn't specified it is an error. */ if (lctx.id == LSM_ID_UNDEF) return -EINVAL; single = true; } /* * In the usual case gather all the data from the LSMs. * In the single case only get the data from the LSM specified. */ lsm_for_each_hook(scall, getselfattr) { if (single && lctx.id != scall->hl->lsmid->id) continue; entrysize = left; if (base) uctx = (struct lsm_ctx __user *)(base + total); rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags); if (rc == -EOPNOTSUPP) continue; if (rc == -E2BIG) { rc = 0; left = 0; toobig = true; } else if (rc < 0) return rc; else left -= entrysize; total += entrysize; count += rc; if (single) break; } if (put_user(total, size)) return -EFAULT; if (toobig) return -E2BIG; if (count == 0) return LSM_RET_DEFAULT(getselfattr); return count; } /* * Please keep this in sync with it's counterpart in security/lsm_syscalls.c */ /** * security_setselfattr - Set an LSM attribute on the current process. * @attr: which attribute to set * @uctx: the user-space source for the information * @size: the size of the data * @flags: reserved for future use, must be 0 * * Set an LSM attribute for the current process. The LSM, attribute * and new value are included in @uctx. * * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT * if the user buffer is inaccessible, E2BIG if size is too big, or an * LSM specific failure. */ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 size, u32 flags) { struct lsm_static_call *scall; struct lsm_ctx *lctx; int rc = LSM_RET_DEFAULT(setselfattr); u64 required_len; if (flags) return -EINVAL; if (size < sizeof(*lctx)) return -EINVAL; if (size > PAGE_SIZE) return -E2BIG; lctx = memdup_user(uctx, size); if (IS_ERR(lctx)) return PTR_ERR(lctx); if (size < lctx->len || check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) || lctx->len < required_len) { rc = -EINVAL; goto free_out; } lsm_for_each_hook(scall, setselfattr) if ((scall->hl->lsmid->id) == lctx->id) { rc = scall->hl->hook.setselfattr(attr, lctx, size, flags); break; } free_out: kfree(lctx); return rc; } /** * security_getprocattr() - Read an attribute for a task * @p: the task * @lsmid: LSM identification * @name: attribute name * @value: attribute value * * Read attribute @name for task @p and store it into @value if allowed. * * Return: Returns the length of @value on success, a negative value otherwise. */ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value) { struct lsm_static_call *scall; lsm_for_each_hook(scall, getprocattr) { if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } /** * security_setprocattr() - Set an attribute for a task * @lsmid: LSM identification * @name: attribute name * @value: attribute value * @size: attribute value size * * Write (set) the current task's attribute @name to @value, size @size if * allowed. * * Return: Returns bytes written on success, a negative value otherwise. */ int security_setprocattr(int lsmid, const char *name, void *value, size_t size) { struct lsm_static_call *scall; lsm_for_each_hook(scall, setprocattr) { if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } /** * security_ismaclabel() - Check if the named attribute is a MAC label * @name: full extended attribute name * * Check if the extended attribute specified by @name represents a MAC label. * * Return: Returns 1 if name is a MAC attribute otherwise returns 0. */ int security_ismaclabel(const char *name) { return call_int_hook(ismaclabel, name); } EXPORT_SYMBOL(security_ismaclabel); /** * security_secid_to_secctx() - Convert a secid to a secctx * @secid: secid * @cp: the LSM context * * Convert secid to security context. If @cp is NULL the length of the * result will be returned, but no data will be returned. This * does mean that the length could change between calls to check the length and * the next call which actually allocates and returns the data. * * Return: Return length of data on success, error on failure. */ int security_secid_to_secctx(u32 secid, struct lsm_context *cp) { return call_int_hook(secid_to_secctx, secid, cp); } EXPORT_SYMBOL(security_secid_to_secctx); /** * security_lsmprop_to_secctx() - Convert a lsm_prop to a secctx * @prop: lsm specific information * @cp: the LSM context * @lsmid: which security module to report * * Convert a @prop entry to security context. If @cp is NULL the * length of the result will be returned. This does mean that the * length could change between calls to check the length and the * next call which actually allocates and returns the @cp. * * @lsmid identifies which LSM should supply the context. * A value of LSM_ID_UNDEF indicates that the first LSM suppling * the hook should be used. This is used in cases where the * ID of the supplying LSM is unambiguous. * * Return: Return length of data on success, error on failure. */ int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp, int lsmid) { struct lsm_static_call *scall; lsm_for_each_hook(scall, lsmprop_to_secctx) { if (lsmid != LSM_ID_UNDEF && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.lsmprop_to_secctx(prop, cp); } return LSM_RET_DEFAULT(lsmprop_to_secctx); } EXPORT_SYMBOL(security_lsmprop_to_secctx); /** * security_secctx_to_secid() - Convert a secctx to a secid * @secdata: secctx * @seclen: length of secctx * @secid: secid * * Convert security context to secid. * * Return: Returns 0 on success, error on failure. */ int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { *secid = 0; return call_int_hook(secctx_to_secid, secdata, seclen, secid); } EXPORT_SYMBOL(security_secctx_to_secid); /** * security_release_secctx() - Free a secctx buffer * @cp: the security context * * Release the security context. */ void security_release_secctx(struct lsm_context *cp) { call_void_hook(release_secctx, cp); memset(cp, 0, sizeof(*cp)); } EXPORT_SYMBOL(security_release_secctx); /** * security_inode_invalidate_secctx() - Invalidate an inode's security label * @inode: inode * * Notify the security module that it must revalidate the security context of * an inode. */ void security_inode_invalidate_secctx(struct inode *inode) { call_void_hook(inode_invalidate_secctx, inode); } EXPORT_SYMBOL(security_inode_invalidate_secctx); /** * security_inode_notifysecctx() - Notify the LSM of an inode's security label * @inode: inode * @ctx: secctx * @ctxlen: length of secctx * * Notify the security module of what the security context of an inode should * be. Initializes the incore security context managed by the security module * for this inode. Example usage: NFS client invokes this hook to initialize * the security context in its incore inode to the value provided by the server * for the file when the server returned the file's attributes to the client. * Must be called with inode->i_mutex locked. * * Return: Returns 0 on success, error on failure. */ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { return call_int_hook(inode_notifysecctx, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_notifysecctx); /** * security_inode_setsecctx() - Change the security label of an inode * @dentry: inode * @ctx: secctx * @ctxlen: length of secctx * * Change the security context of an inode. Updates the incore security * context managed by the security module and invokes the fs code as needed * (via __vfs_setxattr_noperm) to update any backing xattrs that represent the * context. Example usage: NFS server invokes this hook to change the security * context in its incore inode and on the backing filesystem to a value * provided by the client on a SETATTR operation. Must be called with * inode->i_mutex locked. * * Return: Returns 0 on success, error on failure. */ int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return call_int_hook(inode_setsecctx, dentry, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_setsecctx); /** * security_inode_getsecctx() - Get the security label of an inode * @inode: inode * @cp: security context * * On success, returns 0 and fills out @cp with the security context * for the given @inode. * * Return: Returns 0 on success, error on failure. */ int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp) { memset(cp, 0, sizeof(*cp)); return call_int_hook(inode_getsecctx, inode, cp); } EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_WATCH_QUEUE /** * security_post_notification() - Check if a watch notification can be posted * @w_cred: credentials of the task that set the watch * @cred: credentials of the task which triggered the watch * @n: the notification * * Check to see if a watch notification can be posted to a particular queue. * * Return: Returns 0 if permission is granted. */ int security_post_notification(const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) { return call_int_hook(post_notification, w_cred, cred, n); } #endif /* CONFIG_WATCH_QUEUE */ #ifdef CONFIG_KEY_NOTIFICATIONS /** * security_watch_key() - Check if a task is allowed to watch for key events * @key: the key to watch * * Check to see if a process is allowed to watch for event notifications from * a key or keyring. * * Return: Returns 0 if permission is granted. */ int security_watch_key(struct key *key) { return call_int_hook(watch_key, key); } #endif /* CONFIG_KEY_NOTIFICATIONS */ #ifdef CONFIG_SECURITY_NETWORK /** * security_netlink_send() - Save info and check if netlink sending is allowed * @sk: sending socket * @skb: netlink message * * Save security information for a netlink message so that permission checking * can be performed when the message is processed. The security information * can be saved using the eff_cap field of the netlink_skb_parms structure. * Also may be used to provide fine grained control over message transmission. * * Return: Returns 0 if the information was successfully saved and message is * allowed to be transmitted. */ int security_netlink_send(struct sock *sk, struct sk_buff *skb) { return call_int_hook(netlink_send, sk, skb); } /** * security_unix_stream_connect() - Check if a AF_UNIX stream is allowed * @sock: originating sock * @other: peer sock * @newsk: new sock * * Check permissions before establishing a Unix domain stream connection * between @sock and @other. * * The @unix_stream_connect and @unix_may_send hooks were necessary because * Linux provides an alternative to the conventional file name space for Unix * domain sockets. Whereas binding and connecting to sockets in the file name * space is mediated by the typical file permissions (and caught by the mknod * and permission hooks in inode_security_ops), binding and connecting to * sockets in the abstract name space is completely unmediated. Sufficient * control of Unix domain sockets in the abstract name space isn't possible * using only the socket layer hooks, since we need to know the actual target * socket, which is not looked up until we are inside the af_unix code. * * Return: Returns 0 if permission is granted. */ int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return call_int_hook(unix_stream_connect, sock, other, newsk); } EXPORT_SYMBOL(security_unix_stream_connect); /** * security_unix_may_send() - Check if AF_UNIX socket can send datagrams * @sock: originating sock * @other: peer sock * * Check permissions before connecting or sending datagrams from @sock to * @other. * * The @unix_stream_connect and @unix_may_send hooks were necessary because * Linux provides an alternative to the conventional file name space for Unix * domain sockets. Whereas binding and connecting to sockets in the file name * space is mediated by the typical file permissions (and caught by the mknod * and permission hooks in inode_security_ops), binding and connecting to * sockets in the abstract name space is completely unmediated. Sufficient * control of Unix domain sockets in the abstract name space isn't possible * using only the socket layer hooks, since we need to know the actual target * socket, which is not looked up until we are inside the af_unix code. * * Return: Returns 0 if permission is granted. */ int security_unix_may_send(struct socket *sock, struct socket *other) { return call_int_hook(unix_may_send, sock, other); } EXPORT_SYMBOL(security_unix_may_send); /** * security_socket_create() - Check if creating a new socket is allowed * @family: protocol family * @type: communications type * @protocol: requested protocol * @kern: set to 1 if a kernel socket is requested * * Check permissions prior to creating a new socket. * * Return: Returns 0 if permission is granted. */ int security_socket_create(int family, int type, int protocol, int kern) { return call_int_hook(socket_create, family, type, protocol, kern); } /** * security_socket_post_create() - Initialize a newly created socket * @sock: socket * @family: protocol family * @type: communications type * @protocol: requested protocol * @kern: set to 1 if a kernel socket is requested * * This hook allows a module to update or allocate a per-socket security * structure. Note that the security field was not added directly to the socket * structure, but rather, the socket security information is stored in the * associated inode. Typically, the inode alloc_security hook will allocate * and attach security information to SOCK_INODE(sock)->i_security. This hook * may be used to update the SOCK_INODE(sock)->i_security field with additional * information that wasn't available when the inode was allocated. * * Return: Returns 0 if permission is granted. */ int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { return call_int_hook(socket_post_create, sock, family, type, protocol, kern); } /** * security_socket_socketpair() - Check if creating a socketpair is allowed * @socka: first socket * @sockb: second socket * * Check permissions before creating a fresh pair of sockets. * * Return: Returns 0 if permission is granted and the connection was * established. */ int security_socket_socketpair(struct socket *socka, struct socket *sockb) { return call_int_hook(socket_socketpair, socka, sockb); } EXPORT_SYMBOL(security_socket_socketpair); /** * security_socket_bind() - Check if a socket bind operation is allowed * @sock: socket * @address: requested bind address * @addrlen: length of address * * Check permission before socket protocol layer bind operation is performed * and the socket @sock is bound to the address specified in the @address * parameter. * * Return: Returns 0 if permission is granted. */ int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_bind, sock, address, addrlen); } /** * security_socket_connect() - Check if a socket connect operation is allowed * @sock: socket * @address: address of remote connection point * @addrlen: length of address * * Check permission before socket protocol layer connect operation attempts to * connect socket @sock to a remote address, @address. * * Return: Returns 0 if permission is granted. */ int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_connect, sock, address, addrlen); } /** * security_socket_listen() - Check if a socket is allowed to listen * @sock: socket * @backlog: connection queue size * * Check permission before socket protocol layer listen operation. * * Return: Returns 0 if permission is granted. */ int security_socket_listen(struct socket *sock, int backlog) { return call_int_hook(socket_listen, sock, backlog); } /** * security_socket_accept() - Check if a socket is allowed to accept connections * @sock: listening socket * @newsock: newly creation connection socket * * Check permission before accepting a new connection. Note that the new * socket, @newsock, has been created and some information copied to it, but * the accept operation has not actually been performed. * * Return: Returns 0 if permission is granted. */ int security_socket_accept(struct socket *sock, struct socket *newsock) { return call_int_hook(socket_accept, sock, newsock); } /** * security_socket_sendmsg() - Check if sending a message is allowed * @sock: sending socket * @msg: message to send * @size: size of message * * Check permission before transmitting a message to another socket. * * Return: Returns 0 if permission is granted. */ int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return call_int_hook(socket_sendmsg, sock, msg, size); } /** * security_socket_recvmsg() - Check if receiving a message is allowed * @sock: receiving socket * @msg: message to receive * @size: size of message * @flags: operational flags * * Check permission before receiving a message from a socket. * * Return: Returns 0 if permission is granted. */ int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return call_int_hook(socket_recvmsg, sock, msg, size, flags); } /** * security_socket_getsockname() - Check if reading the socket addr is allowed * @sock: socket * * Check permission before reading the local address (name) of the socket * object. * * Return: Returns 0 if permission is granted. */ int security_socket_getsockname(struct socket *sock) { return call_int_hook(socket_getsockname, sock); } /** * security_socket_getpeername() - Check if reading the peer's addr is allowed * @sock: socket * * Check permission before the remote address (name) of a socket object. * * Return: Returns 0 if permission is granted. */ int security_socket_getpeername(struct socket *sock) { return call_int_hook(socket_getpeername, sock); } /** * security_socket_getsockopt() - Check if reading a socket option is allowed * @sock: socket * @level: option's protocol level * @optname: option name * * Check permissions before retrieving the options associated with socket * @sock. * * Return: Returns 0 if permission is granted. */ int security_socket_getsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_getsockopt, sock, level, optname); } /** * security_socket_setsockopt() - Check if setting a socket option is allowed * @sock: socket * @level: option's protocol level * @optname: option name * * Check permissions before setting the options associated with socket @sock. * * Return: Returns 0 if permission is granted. */ int security_socket_setsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_setsockopt, sock, level, optname); } /** * security_socket_shutdown() - Checks if shutting down the socket is allowed * @sock: socket * @how: flag indicating how sends and receives are handled * * Checks permission before all or part of a connection on the socket @sock is * shut down. * * Return: Returns 0 if permission is granted. */ int security_socket_shutdown(struct socket *sock, int how) { return call_int_hook(socket_shutdown, sock, how); } /** * security_sock_rcv_skb() - Check if an incoming network packet is allowed * @sk: destination sock * @skb: incoming packet * * Check permissions on incoming network packets. This hook is distinct from * Netfilter's IP input hooks since it is the first time that the incoming * sk_buff @skb has been associated with a particular socket, @sk. Must not * sleep inside this hook because some callers hold spinlocks. * * Return: Returns 0 if permission is granted. */ int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { return call_int_hook(socket_sock_rcv_skb, sk, skb); } EXPORT_SYMBOL(security_sock_rcv_skb); /** * security_socket_getpeersec_stream() - Get the remote peer label * @sock: socket * @optval: destination buffer * @optlen: size of peer label copied into the buffer * @len: maximum size of the destination buffer * * This hook allows the security module to provide peer socket security state * for unix or connected tcp sockets to userspace via getsockopt SO_GETPEERSEC. * For tcp sockets this can be meaningful if the socket is associated with an * ipsec SA. * * Return: Returns 0 if all is well, otherwise, typical getsockopt return * values. */ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { return call_int_hook(socket_getpeersec_stream, sock, optval, optlen, len); } /** * security_socket_getpeersec_dgram() - Get the remote peer label * @sock: socket * @skb: datagram packet * @secid: remote peer label secid * * This hook allows the security module to provide peer socket security state * for udp sockets on a per-packet basis to userspace via getsockopt * SO_GETPEERSEC. The application must first have indicated the IP_PASSSEC * option via getsockopt. It can then retrieve the security state returned by * this hook for a packet via the SCM_SECURITY ancillary message type. * * Return: Returns 0 on success, error on failure. */ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { return call_int_hook(socket_getpeersec_dgram, sock, skb, secid); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); /** * lsm_sock_alloc - allocate a composite sock blob * @sock: the sock that needs a blob * @gfp: allocation mode * * Allocate the sock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_sock_alloc(struct sock *sock, gfp_t gfp) { return lsm_blob_alloc(&sock->sk_security, blob_sizes.lbs_sock, gfp); } /** * security_sk_alloc() - Allocate and initialize a sock's LSM blob * @sk: sock * @family: protocol family * @priority: gfp flags * * Allocate and attach a security structure to the sk->sk_security field, which * is used to copy security attributes between local stream sockets. * * Return: Returns 0 on success, error on failure. */ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { int rc = lsm_sock_alloc(sk, priority); if (unlikely(rc)) return rc; rc = call_int_hook(sk_alloc_security, sk, family, priority); if (unlikely(rc)) security_sk_free(sk); return rc; } /** * security_sk_free() - Free the sock's LSM blob * @sk: sock * * Deallocate security structure. */ void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); kfree(sk->sk_security); sk->sk_security = NULL; } /** * security_sk_clone() - Clone a sock's LSM state * @sk: original sock * @newsk: target sock * * Clone/copy security structure. */ void security_sk_clone(const struct sock *sk, struct sock *newsk) { call_void_hook(sk_clone_security, sk, newsk); } EXPORT_SYMBOL(security_sk_clone); /** * security_sk_classify_flow() - Set a flow's secid based on socket * @sk: original socket * @flic: target flow * * Set the target flow's secid to socket's secid. */ void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } EXPORT_SYMBOL(security_sk_classify_flow); /** * security_req_classify_flow() - Set a flow's secid based on request_sock * @req: request_sock * @flic: target flow * * Sets @flic's secid to @req's secid. */ void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { call_void_hook(req_classify_flow, req, flic); } EXPORT_SYMBOL(security_req_classify_flow); /** * security_sock_graft() - Reconcile LSM state when grafting a sock on a socket * @sk: sock being grafted * @parent: target parent socket * * Sets @parent's inode secid to @sk's secid and update @sk with any necessary * LSM state from @parent. */ void security_sock_graft(struct sock *sk, struct socket *parent) { call_void_hook(sock_graft, sk, parent); } EXPORT_SYMBOL(security_sock_graft); /** * security_inet_conn_request() - Set request_sock state using incoming connect * @sk: parent listening sock * @skb: incoming connection * @req: new request_sock * * Initialize the @req LSM state based on @sk and the incoming connect in @skb. * * Return: Returns 0 if permission is granted. */ int security_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { return call_int_hook(inet_conn_request, sk, skb, req); } EXPORT_SYMBOL(security_inet_conn_request); /** * security_inet_csk_clone() - Set new sock LSM state based on request_sock * @newsk: new sock * @req: connection request_sock * * Set that LSM state of @sock using the LSM state from @req. */ void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { call_void_hook(inet_csk_clone, newsk, req); } /** * security_inet_conn_established() - Update sock's LSM state with connection * @sk: sock * @skb: connection packet * * Update @sock's LSM state to represent a new connection from @skb. */ void security_inet_conn_established(struct sock *sk, struct sk_buff *skb) { call_void_hook(inet_conn_established, sk, skb); } EXPORT_SYMBOL(security_inet_conn_established); /** * security_secmark_relabel_packet() - Check if setting a secmark is allowed * @secid: new secmark value * * Check if the process should be allowed to relabel packets to @secid. * * Return: Returns 0 if permission is granted. */ int security_secmark_relabel_packet(u32 secid) { return call_int_hook(secmark_relabel_packet, secid); } EXPORT_SYMBOL(security_secmark_relabel_packet); /** * security_secmark_refcount_inc() - Increment the secmark labeling rule count * * Tells the LSM to increment the number of secmark labeling rules loaded. */ void security_secmark_refcount_inc(void) { call_void_hook(secmark_refcount_inc); } EXPORT_SYMBOL(security_secmark_refcount_inc); /** * security_secmark_refcount_dec() - Decrement the secmark labeling rule count * * Tells the LSM to decrement the number of secmark labeling rules loaded. */ void security_secmark_refcount_dec(void) { call_void_hook(secmark_refcount_dec); } EXPORT_SYMBOL(security_secmark_refcount_dec); /** * security_tun_dev_alloc_security() - Allocate a LSM blob for a TUN device * @security: pointer to the LSM blob * * This hook allows a module to allocate a security structure for a TUN device, * returning the pointer in @security. * * Return: Returns a zero on success, negative values on failure. */ int security_tun_dev_alloc_security(void **security) { int rc; rc = lsm_blob_alloc(security, blob_sizes.lbs_tun_dev, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(tun_dev_alloc_security, *security); if (rc) { kfree(*security); *security = NULL; } return rc; } EXPORT_SYMBOL(security_tun_dev_alloc_security); /** * security_tun_dev_free_security() - Free a TUN device LSM blob * @security: LSM blob * * This hook allows a module to free the security structure for a TUN device. */ void security_tun_dev_free_security(void *security) { kfree(security); } EXPORT_SYMBOL(security_tun_dev_free_security); /** * security_tun_dev_create() - Check if creating a TUN device is allowed * * Check permissions prior to creating a new TUN device. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_create(void) { return call_int_hook(tun_dev_create); } EXPORT_SYMBOL(security_tun_dev_create); /** * security_tun_dev_attach_queue() - Check if attaching a TUN queue is allowed * @security: TUN device LSM blob * * Check permissions prior to attaching to a TUN device queue. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_attach_queue(void *security) { return call_int_hook(tun_dev_attach_queue, security); } EXPORT_SYMBOL(security_tun_dev_attach_queue); /** * security_tun_dev_attach() - Update TUN device LSM state on attach * @sk: associated sock * @security: TUN device LSM blob * * This hook can be used by the module to update any security state associated * with the TUN device's sock structure. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_attach(struct sock *sk, void *security) { return call_int_hook(tun_dev_attach, sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); /** * security_tun_dev_open() - Update TUN device LSM state on open * @security: TUN device LSM blob * * This hook can be used by the module to update any security state associated * with the TUN device's security structure. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_open(void *security) { return call_int_hook(tun_dev_open, security); } EXPORT_SYMBOL(security_tun_dev_open); /** * security_sctp_assoc_request() - Update the LSM on a SCTP association req * @asoc: SCTP association * @skb: packet requesting the association * * Passes the @asoc and @chunk->skb of the association INIT packet to the LSM. * * Return: Returns 0 on success, error on failure. */ int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_request, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); /** * security_sctp_bind_connect() - Validate a list of addrs for a SCTP option * @sk: socket * @optname: SCTP option to validate * @address: list of IP addresses to validate * @addrlen: length of the address list * * Validiate permissions required for each address associated with sock @sk. * Depending on @optname, the addresses will be treated as either a connect or * bind service. The @addrlen is calculated on each IPv4 and IPv6 address using * sizeof(struct sockaddr_in) or sizeof(struct sockaddr_in6). * * Return: Returns 0 on success, error on failure. */ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { return call_int_hook(sctp_bind_connect, sk, optname, address, addrlen); } EXPORT_SYMBOL(security_sctp_bind_connect); /** * security_sctp_sk_clone() - Clone a SCTP sock's LSM state * @asoc: SCTP association * @sk: original sock * @newsk: target sock * * Called whenever a new socket is created by accept(2) (i.e. a TCP style * socket) or when a socket is 'peeled off' e.g userspace calls * sctp_peeloff(3). */ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { call_void_hook(sctp_sk_clone, asoc, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); /** * security_sctp_assoc_established() - Update LSM state when assoc established * @asoc: SCTP association * @skb: packet establishing the association * * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet to the * security module. * * Return: Returns 0 if permission is granted. */ int security_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_established, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_established); /** * security_mptcp_add_subflow() - Inherit the LSM label from the MPTCP socket * @sk: the owning MPTCP socket * @ssk: the new subflow * * Update the labeling for the given MPTCP subflow, to match the one of the * owning MPTCP socket. This hook has to be called after the socket creation and * initialization via the security_socket_create() and * security_socket_post_create() LSM hooks. * * Return: Returns 0 on success or a negative error code on failure. */ int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { return call_int_hook(mptcp_add_subflow, sk, ssk); } #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND /** * security_ib_pkey_access() - Check if access to an IB pkey is allowed * @sec: LSM blob * @subnet_prefix: subnet prefix of the port * @pkey: IB pkey * * Check permission to access a pkey when modifying a QP. * * Return: Returns 0 if permission is granted. */ int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) { return call_int_hook(ib_pkey_access, sec, subnet_prefix, pkey); } EXPORT_SYMBOL(security_ib_pkey_access); /** * security_ib_endport_manage_subnet() - Check if SMPs traffic is allowed * @sec: LSM blob * @dev_name: IB device name * @port_num: port number * * Check permissions to send and receive SMPs on a end port. * * Return: Returns 0 if permission is granted. */ int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) { return call_int_hook(ib_endport_manage_subnet, sec, dev_name, port_num); } EXPORT_SYMBOL(security_ib_endport_manage_subnet); /** * security_ib_alloc_security() - Allocate an Infiniband LSM blob * @sec: LSM blob * * Allocate a security structure for Infiniband objects. * * Return: Returns 0 on success, non-zero on failure. */ int security_ib_alloc_security(void **sec) { int rc; rc = lsm_blob_alloc(sec, blob_sizes.lbs_ib, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(ib_alloc_security, *sec); if (rc) { kfree(*sec); *sec = NULL; } return rc; } EXPORT_SYMBOL(security_ib_alloc_security); /** * security_ib_free_security() - Free an Infiniband LSM blob * @sec: LSM blob * * Deallocate an Infiniband security structure. */ void security_ib_free_security(void *sec) { kfree(sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM /** * security_xfrm_policy_alloc() - Allocate a xfrm policy LSM blob * @ctxp: xfrm security context being added to the SPD * @sec_ctx: security label provided by userspace * @gfp: gfp flags * * Allocate a security structure to the xp->security field; the security field * is initialized to NULL when the xfrm_policy is allocated. * * Return: Return 0 if operation was successful. */ int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) { return call_int_hook(xfrm_policy_alloc_security, ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); /** * security_xfrm_policy_clone() - Clone xfrm policy LSM state * @old_ctx: xfrm security context * @new_ctxp: target xfrm security context * * Allocate a security structure in new_ctxp that contains the information from * the old_ctx structure. * * Return: Return 0 if operation was successful. */ int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp) { return call_int_hook(xfrm_policy_clone_security, old_ctx, new_ctxp); } /** * security_xfrm_policy_free() - Free a xfrm security context * @ctx: xfrm security context * * Free LSM resources associated with @ctx. */ void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx) { call_void_hook(xfrm_policy_free_security, ctx); } EXPORT_SYMBOL(security_xfrm_policy_free); /** * security_xfrm_policy_delete() - Check if deleting a xfrm policy is allowed * @ctx: xfrm security context * * Authorize deletion of a SPD entry. * * Return: Returns 0 if permission is granted. */ int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { return call_int_hook(xfrm_policy_delete_security, ctx); } /** * security_xfrm_state_alloc() - Allocate a xfrm state LSM blob * @x: xfrm state being added to the SAD * @sec_ctx: security label provided by userspace * * Allocate a security structure to the @x->security field; the security field * is initialized to NULL when the xfrm_state is allocated. Set the context to * correspond to @sec_ctx. * * Return: Return 0 if operation was successful. */ int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { return call_int_hook(xfrm_state_alloc, x, sec_ctx); } EXPORT_SYMBOL(security_xfrm_state_alloc); /** * security_xfrm_state_alloc_acquire() - Allocate a xfrm state LSM blob * @x: xfrm state being added to the SAD * @polsec: associated policy's security context * @secid: secid from the flow * * Allocate a security structure to the x->security field; the security field * is initialized to NULL when the xfrm_state is allocated. Set the context to * correspond to secid. * * Return: Returns 0 if operation was successful. */ int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) { return call_int_hook(xfrm_state_alloc_acquire, x, polsec, secid); } /** * security_xfrm_state_delete() - Check if deleting a xfrm state is allowed * @x: xfrm state * * Authorize deletion of x->security. * * Return: Returns 0 if permission is granted. */ int security_xfrm_state_delete(struct xfrm_state *x) { return call_int_hook(xfrm_state_delete_security, x); } EXPORT_SYMBOL(security_xfrm_state_delete); /** * security_xfrm_state_free() - Free a xfrm state * @x: xfrm state * * Deallocate x->security. */ void security_xfrm_state_free(struct xfrm_state *x) { call_void_hook(xfrm_state_free_security, x); } /** * security_xfrm_policy_lookup() - Check if using a xfrm policy is allowed * @ctx: target xfrm security context * @fl_secid: flow secid used to authorize access * * Check permission when a flow selects a xfrm_policy for processing XFRMs on a * packet. The hook is called when selecting either a per-socket policy or a * generic xfrm policy. * * Return: Return 0 if permission is granted, -ESRCH otherwise, or -errno on * other errors. */ int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return call_int_hook(xfrm_policy_lookup, ctx, fl_secid); } /** * security_xfrm_state_pol_flow_match() - Check for a xfrm match * @x: xfrm state to match * @xp: xfrm policy to check for a match * @flic: flow to check for a match. * * Check @xp and @flic for a match with @x. * * Return: Returns 1 if there is a match. */ int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { struct lsm_static_call *scall; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment * becomes difficult if multiple LSMs supply this call. Fortunately, * we can use the first LSM's judgment because currently only SELinux * supplies this call. * * For speed optimization, we explicitly break the loop rather than * using the macro */ lsm_for_each_hook(scall, xfrm_state_pol_flow_match) { rc = scall->hl->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; } /** * security_xfrm_decode_session() - Determine the xfrm secid for a packet * @skb: xfrm packet * @secid: secid * * Decode the packet in @skb and return the security label in @secid. * * Return: Return 0 if all xfrms used have the same secid. */ int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return call_int_hook(xfrm_decode_session, skb, secid, 1); } void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic) { int rc = call_int_hook(xfrm_decode_session, skb, &flic->flowic_secid, 0); BUG_ON(rc); } EXPORT_SYMBOL(security_skb_classify_flow); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS /** * security_key_alloc() - Allocate and initialize a kernel key LSM blob * @key: key * @cred: credentials * @flags: allocation flags * * Permit allocation of a key and assign security data. Note that key does not * have a serial number assigned at this point. * * Return: Return 0 if permission is granted, -ve error otherwise. */ int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { int rc = lsm_key_alloc(key); if (unlikely(rc)) return rc; rc = call_int_hook(key_alloc, key, cred, flags); if (unlikely(rc)) security_key_free(key); return rc; } /** * security_key_free() - Free a kernel key LSM blob * @key: key * * Notification of destruction; free security data. */ void security_key_free(struct key *key) { kfree(key->security); key->security = NULL; } /** * security_key_permission() - Check if a kernel key operation is allowed * @key_ref: key reference * @cred: credentials of actor requesting access * @need_perm: requested permissions * * See whether a specific operational right is granted to a process on a key. * * Return: Return 0 if permission is granted, -ve error otherwise. */ int security_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { return call_int_hook(key_permission, key_ref, cred, need_perm); } /** * security_key_getsecurity() - Get the key's security label * @key: key * @buffer: security label buffer * * Get a textual representation of the security context attached to a key for * the purposes of honouring KEYCTL_GETSECURITY. This function allocates the * storage for the NUL-terminated string and the caller should free it. * * Return: Returns the length of @buffer (including terminating NUL) or -ve if * an error occurs. May also return 0 (and a NULL buffer pointer) if * there is no security label assigned to the key. */ int security_key_getsecurity(struct key *key, char **buffer) { *buffer = NULL; return call_int_hook(key_getsecurity, key, buffer); } /** * security_key_post_create_or_update() - Notification of key create or update * @keyring: keyring to which the key is linked to * @key: created or updated key * @payload: data used to instantiate or update the key * @payload_len: length of payload * @flags: key flags * @create: flag indicating whether the key was created or updated * * Notify the caller of a key creation or update. */ void security_key_post_create_or_update(struct key *keyring, struct key *key, const void *payload, size_t payload_len, unsigned long flags, bool create) { call_void_hook(key_post_create_or_update, keyring, key, payload, payload_len, flags, create); } #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT /** * security_audit_rule_init() - Allocate and init an LSM audit rule struct * @field: audit action * @op: rule operator * @rulestr: rule context * @lsmrule: receive buffer for audit rule struct * @gfp: GFP flag used for kmalloc * * Allocate and initialize an LSM audit rule structure. * * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of * an invalid rule. */ int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) { return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp); } /** * security_audit_rule_known() - Check if an audit rule contains LSM fields * @krule: audit rule * * Specifies whether given @krule contains any fields related to the current * LSM. * * Return: Returns 1 in case of relation found, 0 otherwise. */ int security_audit_rule_known(struct audit_krule *krule) { return call_int_hook(audit_rule_known, krule); } /** * security_audit_rule_free() - Free an LSM audit rule struct * @lsmrule: audit rule struct * * Deallocate the LSM audit rule structure previously allocated by * audit_rule_init(). */ void security_audit_rule_free(void *lsmrule) { call_void_hook(audit_rule_free, lsmrule); } /** * security_audit_rule_match() - Check if a label matches an audit rule * @prop: security label * @field: LSM audit field * @op: matching operator * @lsmrule: audit rule * * Determine if given @secid matches a rule previously approved by * security_audit_rule_known(). * * Return: Returns 1 if secid matches the rule, 0 if it does not, -ERRNO on * failure. */ int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *lsmrule) { return call_int_hook(audit_rule_match, prop, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL /** * security_bpf() - Check if the bpf syscall operation is allowed * @cmd: command * @attr: bpf attribute * @size: size * @kernel: whether or not call originated from kernel * * Do a initial check for all bpf syscalls after the attribute is copied into * the kernel. The actual security module can implement their own rules to * check the specific cmd they need. * * Return: Returns 0 if permission is granted. */ int security_bpf(int cmd, union bpf_attr *attr, unsigned int size, bool kernel) { return call_int_hook(bpf, cmd, attr, size, kernel); } /** * security_bpf_map() - Check if access to a bpf map is allowed * @map: bpf map * @fmode: mode * * Do a check when the kernel generates and returns a file descriptor for eBPF * maps. * * Return: Returns 0 if permission is granted. */ int security_bpf_map(struct bpf_map *map, fmode_t fmode) { return call_int_hook(bpf_map, map, fmode); } /** * security_bpf_prog() - Check if access to a bpf program is allowed * @prog: bpf program * * Do a check when the kernel generates and returns a file descriptor for eBPF * programs. * * Return: Returns 0 if permission is granted. */ int security_bpf_prog(struct bpf_prog *prog) { return call_int_hook(bpf_prog, prog); } /** * security_bpf_map_create() - Check if BPF map creation is allowed * @map: BPF map object * @attr: BPF syscall attributes used to create BPF map * @token: BPF token used to grant user access * @kernel: whether or not call originated from kernel * * Do a check when the kernel creates a new BPF map. This is also the * point where LSM blob is allocated for LSMs that need them. * * Return: Returns 0 on success, error on failure. */ int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token, bool kernel) { int rc; rc = lsm_bpf_map_alloc(map); if (unlikely(rc)) return rc; rc = call_int_hook(bpf_map_create, map, attr, token, kernel); if (unlikely(rc)) security_bpf_map_free(map); return rc; } /** * security_bpf_prog_load() - Check if loading of BPF program is allowed * @prog: BPF program object * @attr: BPF syscall attributes used to create BPF program * @token: BPF token used to grant user access to BPF subsystem * @kernel: whether or not call originated from kernel * * Perform an access control check when the kernel loads a BPF program and * allocates associated BPF program object. This hook is also responsible for * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token, bool kernel) { int rc; rc = lsm_bpf_prog_alloc(prog); if (unlikely(rc)) return rc; rc = call_int_hook(bpf_prog_load, prog, attr, token, kernel); if (unlikely(rc)) security_bpf_prog_free(prog); return rc; } /** * security_bpf_token_create() - Check if creating of BPF token is allowed * @token: BPF token object * @attr: BPF syscall attributes used to create BPF token * @path: path pointing to BPF FS mount point from which BPF token is created * * Do a check when the kernel instantiates a new BPF token object from BPF FS * instance. This is also the point where LSM blob can be allocated for LSMs. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, const struct path *path) { int rc; rc = lsm_bpf_token_alloc(token); if (unlikely(rc)) return rc; rc = call_int_hook(bpf_token_create, token, attr, path); if (unlikely(rc)) security_bpf_token_free(token); return rc; } /** * security_bpf_token_cmd() - Check if BPF token is allowed to delegate * requested BPF syscall command * @token: BPF token object * @cmd: BPF syscall command requested to be delegated by BPF token * * Do a check when the kernel decides whether provided BPF token should allow * delegation of requested BPF syscall command. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { return call_int_hook(bpf_token_cmd, token, cmd); } /** * security_bpf_token_capable() - Check if BPF token is allowed to delegate * requested BPF-related capability * @token: BPF token object * @cap: capabilities requested to be delegated by BPF token * * Do a check when the kernel decides whether provided BPF token should allow * delegation of requested BPF-related capabilities. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_capable(const struct bpf_token *token, int cap) { return call_int_hook(bpf_token_capable, token, cap); } /** * security_bpf_map_free() - Free a bpf map's LSM blob * @map: bpf map * * Clean up the security information stored inside bpf map. */ void security_bpf_map_free(struct bpf_map *map) { call_void_hook(bpf_map_free, map); kfree(map->security); map->security = NULL; } /** * security_bpf_prog_free() - Free a BPF program's LSM blob * @prog: BPF program struct * * Clean up the security information stored inside BPF program. */ void security_bpf_prog_free(struct bpf_prog *prog) { call_void_hook(bpf_prog_free, prog); kfree(prog->aux->security); prog->aux->security = NULL; } /** * security_bpf_token_free() - Free a BPF token's LSM blob * @token: BPF token struct * * Clean up the security information stored inside BPF token. */ void security_bpf_token_free(struct bpf_token *token) { call_void_hook(bpf_token_free, token); kfree(token->security); token->security = NULL; } #endif /* CONFIG_BPF_SYSCALL */ /** * security_locked_down() - Check if a kernel feature is allowed * @what: requested kernel feature * * Determine whether a kernel feature that potentially enables arbitrary code * execution in kernel space should be permitted. * * Return: Returns 0 if permission is granted. */ int security_locked_down(enum lockdown_reason what) { return call_int_hook(locked_down, what); } EXPORT_SYMBOL(security_locked_down); /** * security_bdev_alloc() - Allocate a block device LSM blob * @bdev: block device * * Allocate and attach a security structure to @bdev->bd_security. The * security field is initialized to NULL when the bdev structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_bdev_alloc(struct block_device *bdev) { int rc = 0; rc = lsm_bdev_alloc(bdev); if (unlikely(rc)) return rc; rc = call_int_hook(bdev_alloc_security, bdev); if (unlikely(rc)) security_bdev_free(bdev); return rc; } EXPORT_SYMBOL(security_bdev_alloc); /** * security_bdev_free() - Free a block device's LSM blob * @bdev: block device * * Deallocate the bdev security structure and set @bdev->bd_security to NULL. */ void security_bdev_free(struct block_device *bdev) { if (!bdev->bd_security) return; call_void_hook(bdev_free_security, bdev); kfree(bdev->bd_security); bdev->bd_security = NULL; } EXPORT_SYMBOL(security_bdev_free); /** * security_bdev_setintegrity() - Set the device's integrity data * @bdev: block device * @type: type of integrity, e.g. hash digest, signature, etc * @value: the integrity value * @size: size of the integrity value * * Register a verified integrity measurement of a bdev with LSMs. * LSMs should free the previously saved data if @value is NULL. * Please note that the new hook should be invoked every time the security * information is updated to keep these data current. For example, in dm-verity, * if the mapping table is reloaded and configured to use a different dm-verity * target with a new roothash and signing information, the previously stored * data in the LSM blob will become obsolete. It is crucial to re-invoke the * hook to refresh these data and ensure they are up to date. This necessity * arises from the design of device-mapper, where a device-mapper device is * first created, and then targets are subsequently loaded into it. These * targets can be modified multiple times during the device's lifetime. * Therefore, while the LSM blob is allocated during the creation of the block * device, its actual contents are not initialized at this stage and can change * substantially over time. This includes alterations from data that the LSMs * 'trusts' to those they do not, making it essential to handle these changes * correctly. Failure to address this dynamic aspect could potentially allow * for bypassing LSM checks. * * Return: Returns 0 on success, negative values on failure. */ int security_bdev_setintegrity(struct block_device *bdev, enum lsm_integrity_type type, const void *value, size_t size) { return call_int_hook(bdev_setintegrity, bdev, type, value, size); } EXPORT_SYMBOL(security_bdev_setintegrity); #ifdef CONFIG_PERF_EVENTS /** * security_perf_event_open() - Check if a perf event open is allowed * @type: type of event * * Check whether the @type of perf_event_open syscall is allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_open(int type) { return call_int_hook(perf_event_open, type); } /** * security_perf_event_alloc() - Allocate a perf event LSM blob * @event: perf event * * Allocate and save perf_event security info. * * Return: Returns 0 on success, error on failure. */ int security_perf_event_alloc(struct perf_event *event) { int rc; rc = lsm_blob_alloc(&event->security, blob_sizes.lbs_perf_event, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(perf_event_alloc, event); if (rc) { kfree(event->security); event->security = NULL; } return rc; } /** * security_perf_event_free() - Free a perf event LSM blob * @event: perf event * * Release (free) perf_event security info. */ void security_perf_event_free(struct perf_event *event) { kfree(event->security); event->security = NULL; } /** * security_perf_event_read() - Check if reading a perf event label is allowed * @event: perf event * * Read perf_event security info if allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_read(struct perf_event *event) { return call_int_hook(perf_event_read, event); } /** * security_perf_event_write() - Check if writing a perf event label is allowed * @event: perf event * * Write perf_event security info if allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_write(struct perf_event *event) { return call_int_hook(perf_event_write, event); } #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING /** * security_uring_override_creds() - Check if overriding creds is allowed * @new: new credentials * * Check if the current task, executing an io_uring operation, is allowed to * override it's credentials with @new. * * Return: Returns 0 if permission is granted. */ int security_uring_override_creds(const struct cred *new) { return call_int_hook(uring_override_creds, new); } /** * security_uring_sqpoll() - Check if IORING_SETUP_SQPOLL is allowed * * Check whether the current task is allowed to spawn a io_uring polling thread * (IORING_SETUP_SQPOLL). * * Return: Returns 0 if permission is granted. */ int security_uring_sqpoll(void) { return call_int_hook(uring_sqpoll); } /** * security_uring_cmd() - Check if a io_uring passthrough command is allowed * @ioucmd: command * * Check whether the file_operations uring_cmd is allowed to run. * * Return: Returns 0 if permission is granted. */ int security_uring_cmd(struct io_uring_cmd *ioucmd) { return call_int_hook(uring_cmd, ioucmd); } /** * security_uring_allowed() - Check if io_uring_setup() is allowed * * Check whether the current task is allowed to call io_uring_setup(). * * Return: Returns 0 if permission is granted. */ int security_uring_allowed(void) { return call_int_hook(uring_allowed); } #endif /* CONFIG_IO_URING */ /** * security_initramfs_populated() - Notify LSMs that initramfs has been loaded * * Tells the LSMs the initramfs has been unpacked into the rootfs. */ void security_initramfs_populated(void) { call_void_hook(initramfs_populated); } |
| 69 70 | 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-only */ #ifndef LINUX_RESUME_USER_MODE_H #define LINUX_RESUME_USER_MODE_H #include <linux/sched.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/rseq.h> #include <linux/blk-cgroup.h> /** * set_notify_resume - cause resume_user_mode_work() to be called * @task: task that will call resume_user_mode_work() * * Calling this arranges that @task will call resume_user_mode_work() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call resume_user_mode_work() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); } /** * resume_user_mode_work - Perform work before returning 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 resume_user_mode_work(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(task_work_pending(current))) 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(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_slowpath(regs); } #endif /* LINUX_RESUME_USER_MODE_H */ |
| 234 234 233 233 236 235 199 183 16 233 232 129 233 1 232 1 233 233 1 1 233 233 232 1 232 4 4 4 4 232 233 233 233 1 233 233 232 232 232 1 232 233 233 233 132 231 233 14 14 14 14 14 338 340 339 340 339 227 161 162 336 335 334 336 336 4 4 4 3 3 3 3 3 23 23 23 23 23 3 23 23 23 23 23 23 23 23 23 23 3 23 3 3 3 3 3 3 33 31 16 16 33 33 32 32 33 33 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> #include <linux/irq_work.h> #include "workqueue_internal.h" enum worker_pool_flags { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. * * As there can only be one concurrent BH execution context per CPU, a * BH pool is per-CPU and always DISASSOCIATED. */ POOL_BH = 1 << 0, /* is a BH pool */ POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ }; enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, }; enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ RESCUER_BATCH = 16, /* process items per turn */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because * msecs_to_jiffies() can't be an initializer. */ #define BH_WORKER_JIFFIES msecs_to_jiffies(2) #define BH_WORKER_RESTARTS 10 /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for * reads. * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. * * S: Only modified by worker self. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read * with READ_ONCE() without locking. * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* L: flags */ unsigned long last_progress_ts; /* L: last forward progress timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct work_struct idle_cull_work; /* L: worker idle cleanup */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ #ifdef CONFIG_PREEMPT_RT spinlock_t cb_lock; /* BH worker cancel lock */ #endif /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * Per-pool_workqueue statistics. These can be monitored using * tools/workqueue/wq_monitor.py. */ enum pool_workqueue_stats { PWQ_STAT_STARTED, /* work items started execution */ PWQ_STAT_COMPLETED, /* work items completed execution */ PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ PWQ_NR_STATS, }; /* * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate in * nr_active and all work items in pwq->inactive_works are marked with * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are * in pwq->inactive_works. Some of them are ready to run in * pool->worklist or worker->scheduled. Those work itmes are only struct * wq_barrier which is used for flush_work() and should not participate * in nr_active. For non-barrier work item, it is marked with * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ struct work_struct mayday_cursor; /* L: cursor on pool->worklist */ u64 stats[PWQ_NR_STATS]; /* * Release of unbound pwq is punted to a kthread_worker. See put_pwq() * and pwq_release_workfn() for details. pool_workqueue itself is also * RCU protected so that the first pwq can be determined without * grabbing wq->mutex. */ struct kthread_work release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * Unlike in a per-cpu workqueue where max_active limits its concurrency level * on each CPU, in an unbound workqueue, max_active applies to the whole system. * As sharing a single nr_active across multiple sockets can be very expensive, * the counting and enforcement is per NUMA node. * * The following struct is used to enforce per-node max_active. When a pwq wants * to start executing a work item, it should increment ->nr using * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in * round-robin order. */ struct wq_node_nr_active { int max; /* per-node max_active */ atomic_t nr; /* per-node nr_active */ raw_spinlock_t lock; /* nests inside pool locks */ struct list_head pending_pwqs; /* LN: pwqs with inactive works */ }; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ /* See alloc_workqueue() function comment for info on min/max_active */ int max_active; /* WO: max active works */ int min_active; /* WO: min active works */ int saved_max_active; /* WQ: saved max_active */ int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map __lockdep_map; struct lockdep_map *lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. */ struct wq_pod_type { int nr_pods; /* number of pods */ cpumask_var_t *pod_cpus; /* pod -> cpus */ int *pod_node; /* pod -> node */ int *cpu_pod; /* cpu -> pod */ }; struct work_offq_data { u32 pool_id; u32 disable; u32 flags; }; static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", [WQ_AFFN_NUMA] = "numa", [WQ_AFFN_SYSTEM] = "system", }; /* * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT static unsigned int wq_cpu_intensive_warning_thresh = 4; module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); #endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_topo_initialized __read_mostly = false; static struct kmem_cache *pwq_cache; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *unbound_wq_update_pwq_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: mirror the cpu_online_mask excluding the CPU in the midst of hotplugging */ static cpumask_var_t wq_online_cpumask; /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* PL: user requested unbound cpumask via sysfs */ static cpumask_var_t wq_requested_unbound_cpumask; /* PL: isolated cpumask to be excluded from unbound cpumask */ static cpumask_var_t wq_isolated_cpumask; /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* to raise softirq for the BH worker pools on other CPUs */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], bh_pool_irq_works); /* the BH worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], bh_worker_pools); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. */ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_percpu_wq __ro_after_init; EXPORT_SYMBOL(system_percpu_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_dfl_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_dfl_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); struct workqueue_struct *system_bh_wq; EXPORT_SYMBOL_GPL(system_bh_wq); struct workqueue_struct *system_bh_highpri_wq; EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define for_each_bh_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { timer_destroy_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } static struct pool_workqueue __rcu ** unbound_pwq_slot(struct workqueue_struct *wq, int cpu) { if (cpu >= 0) return per_cpu_ptr(wq->cpu_pwq, cpu); else return &wq->dfl_pwq; } /* @cpu < 0 for dfl_pwq */ static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) { return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), lockdep_is_held(&wq_pool_mutex) || lockdep_is_held(&wq->mutex)); } /** * unbound_effective_cpumask - effective cpumask of an unbound workqueue * @wq: workqueue of interest * * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which * is masked with wq_unbound_cpumask to determine the effective cpumask. The * default pwq is always mapped to the pool with the current effective cpumask. */ static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) { return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } static unsigned long pool_offq_flags(struct worker_pool *pool) { return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() * can be used to set the pwq, pool or clear work->data. These functions should * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long flags) { set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id, unsigned long flags) { set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { return (v >> shift) & ((1U << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { WARN_ON_ONCE(data & WORK_STRUCT_PWQ); offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS); offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, WORK_OFFQ_DISABLE_BITS); offqd->flags = data & WORK_OFFQ_FLAG_MASK; } static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | ((unsigned long)offqd->flags); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && !pool->nr_running; } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; lockdep_assert_held(&pool->lock); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } static void mayday_cursor_func(struct work_struct *work) { /* should not be processed, only for marking position */ BUG(); } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to be * scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on * @nextp. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * assign_work - assign a work item and its linked work items to a worker * @work: work to assign * @worker: worker to assign to * @nextp: out parameter for nested worklist walking * * Assign @work and its linked work items to @worker. If @work is already being * executed by another worker in the same pool, it'll be punted there. * * If @nextp is not NULL, it's updated to point to the next work of the last * scheduled work. This allows assign_work() to be nested inside * list_for_each_entry_safe(). * * Returns %true if @work was successfully assigned to @worker. %false if @work * was punted to another worker already executing it. */ static bool assign_work(struct work_struct *work, struct worker *worker, struct work_struct **nextp) { struct worker_pool *pool = worker->pool; struct worker *collision; lockdep_assert_held(&pool->lock); /* The cursor work should not be processed */ if (unlikely(work->func == mayday_cursor_func)) { /* only worker_thread() can possibly take this branch */ WARN_ON_ONCE(worker->rescue_wq); if (nextp) *nextp = list_next_entry(work, entry); list_del_init(&work->entry); return false; } /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool * while still running in the previous pool. Here, we should ensure that * @work is not executed concurrently by multiple workers from the same * pool. Check whether anyone is already processing the work. If so, * defer the work to the currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, nextp); return false; } move_linked_works(work, &worker->scheduled, nextp); return true; } static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) { int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; } static void kick_bh_pool(struct worker_pool *pool) { #ifdef CONFIG_SMP /* see drain_dead_softirq_workfn() for BH_DRAINING */ if (unlikely(pool->cpu != smp_processor_id() && !(pool->flags & POOL_BH_DRAINING))) { irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); return; } #endif if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) raise_softirq_irqoff(HI_SOFTIRQ); else raise_softirq_irqoff(TASKLET_SOFTIRQ); } /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick * * @pool may have pending work items. Wake up worker if necessary. Returns * whether a worker was woken up. */ static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; if (pool->flags & POOL_BH) { kick_bh_pool(pool); return true; } p = worker->task; #ifdef CONFIG_SMP /* * Idle @worker is about to execute @work and waking up provides an * opportunity to migrate @worker at a lower cost by setting the task's * wake_cpu field. Let's see if we want to move @worker to improve * execution locality. * * We're waking the worker that went idle the latest and there's some * chance that @worker is marked idle but hasn't gone off CPU yet. If * so, setting the wake_cpu won't do anything. As this is a best-effort * optimization and the race window is narrow, let's leave as-is for * now. If this becomes pronounced, we can skip over workers which are * still on cpu when picking an idle worker. * * If @pool has non-strict affinity, @worker might have ended up outside * its affinity scope. Repatriate. */ if (!pool->attrs->affn_strict && !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, cpu_online_mask); if (wake_cpu < nr_cpu_ids) { p->wake_cpu = wake_cpu; get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; } } #endif wake_up_process(p); return true; } #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT /* * Concurrency-managed per-cpu work items that hog CPU for longer than * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism, * which prevents them from stalling other concurrency-managed work items. If a * work function keeps triggering this mechanism, it's likely that the work item * should be using an unbound workqueue instead. * * wq_cpu_intensive_report() tracks work functions which trigger such conditions * and report them so that they can be examined and converted to use unbound * workqueues as appropriate. To avoid flooding the console, each violating work * function is tracked and reported with exponential backoff. */ #define WCI_MAX_ENTS 128 struct wci_ent { work_func_t func; atomic64_t cnt; struct hlist_node hash_node; }; static struct wci_ent wci_ents[WCI_MAX_ENTS]; static int wci_nr_ents; static DEFINE_RAW_SPINLOCK(wci_lock); static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS)); static struct wci_ent *wci_find_ent(work_func_t func) { struct wci_ent *ent; hash_for_each_possible_rcu(wci_hash, ent, hash_node, (unsigned long)func) { if (ent->func == func) return ent; } return NULL; } static void wq_cpu_intensive_report(work_func_t func) { struct wci_ent *ent; restart: ent = wci_find_ent(func); if (ent) { u64 cnt; /* * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); if (wq_cpu_intensive_warning_thresh && cnt >= wq_cpu_intensive_warning_thresh && is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); return; } /* * @func is a new violation. Allocate a new entry for it. If wcn_ents[] * is exhausted, something went really wrong and we probably made enough * noise already. */ if (wci_nr_ents >= WCI_MAX_ENTS) return; raw_spin_lock(&wci_lock); if (wci_nr_ents >= WCI_MAX_ENTS) { raw_spin_unlock(&wci_lock); return; } if (wci_find_ent(func)) { raw_spin_unlock(&wci_lock); goto restart; } ent = &wci_ents[wci_nr_ents++]; ent->func = func; atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ static void wq_cpu_intensive_report(work_func_t func) {} #endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!READ_ONCE(worker->sleeping)) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); /* * CPU intensive auto-detection cares about how long a work item hogged * CPU without sleeping. Reset the starting timestamp on wakeup. */ worker->current_at = worker->task->se.sum_exec_runtime; WRITE_ONCE(worker->sleeping, 0); } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (READ_ONCE(worker->sleeping)) return; WRITE_ONCE(worker->sleeping, 1); raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (kick_pool(pool)) worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) { struct worker *worker = kthread_data(task); struct pool_workqueue *pwq = worker->current_pwq; struct worker_pool *pool = worker->pool; if (!pwq) return; pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC; if (!wq_cpu_intensive_thresh_us) return; /* * If the current worker is concurrency managed and hogged the CPU for * longer than wq_cpu_intensive_thresh_us, it's automatically marked * CPU_INTENSIVE to avoid stalling other concurrency-managed work items. * * Set @worker->sleeping means that @worker is in the process of * switching out voluntarily and won't be contributing to * @pool->nr_running until it wakes up. As wq_worker_sleeping() also * decrements ->nr_running, setting CPU_INTENSIVE here can lead to * double decrements. The task is releasing the CPU anyway. Let's skip. * We probably want to make this prettier in the future. */ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) || worker->task->se.sum_exec_runtime - worker->current_at < wq_cpu_intensive_thresh_us * NSEC_PER_USEC) return; raw_spin_lock(&pool->lock); worker_set_flags(worker, WORKER_CPU_INTENSIVE); wq_cpu_intensive_report(worker->current_func); pwq->stats[PWQ_STAT_CPU_INTENSIVE]++; if (kick_pool(pool)) pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * wq_node_nr_active - Determine wq_node_nr_active to use * @wq: workqueue of interest * @node: NUMA node, can be %NUMA_NO_NODE * * Determine wq_node_nr_active to use for @wq on @node. Returns: * * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. * * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. * * - Otherwise, node_nr_active[@node]. */ static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, int node) { if (!(wq->flags & WQ_UNBOUND)) return NULL; if (node == NUMA_NO_NODE) node = nr_node_ids; return wq->node_nr_active[node]; } /** * wq_update_node_max_active - Update per-node max_actives to use * @wq: workqueue to update * @off_cpu: CPU that's going down, -1 if a CPU is not going down * * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is * distributed among nodes according to the proportions of numbers of online * cpus. The result is always between @wq->min_active and max_active. */ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) { struct cpumask *effective = unbound_effective_cpumask(wq); int min_active = READ_ONCE(wq->min_active); int max_active = READ_ONCE(wq->max_active); int total_cpus, node; lockdep_assert_held(&wq->mutex); if (!wq_topo_initialized) return; if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) off_cpu = -1; total_cpus = cpumask_weight_and(effective, cpu_online_mask); if (off_cpu >= 0) total_cpus--; /* If all CPUs of the wq get offline, use the default values */ if (unlikely(!total_cpus)) { for_each_node(node) wq_node_nr_active(wq, node)->max = min_active; wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; return; } for_each_node(node) { int node_cpus; node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) node_cpus--; wq_node_nr_active(wq, node)->max = clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), min_active, max_active); } wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; /* * @pwq can't be released under pool->lock, bounce to a dedicated * kthread_worker to avoid A-A deadlocks. */ kthread_queue_work(pwq_release_worker, &pwq->release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static bool pwq_is_empty(struct pool_workqueue *pwq) { return !pwq->nr_active && list_empty(&pwq->inactive_works); } static void __pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { unsigned long *wdb = work_data_bits(work); WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->last_progress_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) { int max = READ_ONCE(nna->max); int old = atomic_read(&nna->nr); do { if (old >= max) return false; } while (!atomic_try_cmpxchg_relaxed(&nna->nr, &old, old + 1)); return true; } /** * pwq_tryinc_nr_active - Try to increment nr_active for a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Try to increment nr_active for @pwq. Returns %true if an nr_active count is * successfully obtained. %false otherwise. */ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) { struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); bool obtained = false; lockdep_assert_held(&pool->lock); if (!nna) { /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } if (unlikely(pwq->plugged)) return false; /* * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is * already waiting on $nna, pwq_dec_nr_active() will maintain the * concurrency level. Don't jump the line. * * We need to ignore the pending test after max_active has increased as * pwq_dec_nr_active() can only maintain the concurrency level but not * increase it. This is indicated by @fill. */ if (!list_empty(&pwq->pending_node) && likely(!fill)) goto out; obtained = tryinc_node_nr_active(nna); if (obtained) goto out; /* * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs * and try again. The smp_mb() is paired with the implied memory barrier * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either * we see the decremented $nna->nr or they see non-empty * $nna->pending_pwqs. */ raw_spin_lock(&nna->lock); if (list_empty(&pwq->pending_node)) list_add_tail(&pwq->pending_node, &nna->pending_pwqs); else if (likely(!fill)) goto out_unlock; smp_mb(); obtained = tryinc_node_nr_active(nna); /* * If @fill, @pwq might have already been pending. Being spuriously * pending in cold paths doesn't affect anything. Let's leave it be. */ if (obtained && likely(!fill)) list_del_init(&pwq->pending_node); out_unlock: raw_spin_unlock(&nna->lock); out: if (obtained) pwq->nr_active++; return obtained; } /** * pwq_activate_first_inactive - Activate the first inactive work item on a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Activate the first inactive work item of @pwq if available and allowed by * max_active limit. * * Returns %true if an inactive work item has been activated. %false if no * inactive work item is found or max_active limit is reached. */ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) { struct work_struct *work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (work && pwq_tryinc_nr_active(pwq, fill)) { __pwq_activate_work(pwq, work); return true; } else { return false; } } /** * unplug_oldest_pwq - unplug the oldest pool_workqueue * @wq: workqueue_struct where its oldest pwq is to be unplugged * * This function should only be called for ordered workqueues where only the * oldest pwq is unplugged, the others are plugged to suspend execution to * ensure proper work item ordering:: * * dfl_pwq --------------+ [P] - plugged * | * v * pwqs -> A -> B [P] -> C [P] (newest) * | | | * 1 3 5 * | | | * 2 4 6 * * When the oldest pwq is drained and removed, this function should be called * to unplug the next oldest one to start its work item execution. Note that * pwq's are linked into wq->pwqs with the oldest first, so the first one in * the list is the oldest. */ static void unplug_oldest_pwq(struct workqueue_struct *wq) { struct pool_workqueue *pwq; lockdep_assert_held(&wq->mutex); /* Caller should make sure that pwqs isn't empty before calling */ pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, pwqs_node); raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; if (pwq_activate_first_inactive(pwq, true)) kick_pool(pwq->pool); } raw_spin_unlock_irq(&pwq->pool->lock); } /** * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active * @nna: wq_node_nr_active to activate a pending pwq for * @caller_pool: worker_pool the caller is locking * * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. * @caller_pool may be unlocked and relocked to lock other worker_pools. */ static void node_activate_pending_pwq(struct wq_node_nr_active *nna, struct worker_pool *caller_pool) { struct worker_pool *locked_pool = caller_pool; struct pool_workqueue *pwq; struct work_struct *work; lockdep_assert_held(&caller_pool->lock); raw_spin_lock(&nna->lock); retry: pwq = list_first_entry_or_null(&nna->pending_pwqs, struct pool_workqueue, pending_node); if (!pwq) goto out_unlock; /* * If @pwq is for a different pool than @locked_pool, we need to lock * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock * / lock dance. For that, we also need to release @nna->lock as it's * nested inside pool locks. */ if (pwq->pool != locked_pool) { raw_spin_unlock(&locked_pool->lock); locked_pool = pwq->pool; if (!raw_spin_trylock(&locked_pool->lock)) { raw_spin_unlock(&nna->lock); raw_spin_lock(&locked_pool->lock); raw_spin_lock(&nna->lock); goto retry; } } /* * $pwq may not have any inactive work items due to e.g. cancellations. * Drop it from pending_pwqs and see if there's another one. */ work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (!work) { list_del_init(&pwq->pending_node); goto retry; } /* * Acquire an nr_active count and activate the inactive work item. If * $pwq still has inactive work items, rotate it to the end of the * pending_pwqs so that we round-robin through them. This means that * inactive work items are not activated in queueing order which is fine * given that there has never been any ordering across different pwqs. */ if (likely(tryinc_node_nr_active(nna))) { pwq->nr_active++; __pwq_activate_work(pwq, work); if (list_empty(&pwq->inactive_works)) list_del_init(&pwq->pending_node); else list_move_tail(&pwq->pending_node, &nna->pending_pwqs); /* if activating a foreign pool, make sure it's running */ if (pwq->pool != caller_pool) kick_pool(pwq->pool); } out_unlock: raw_spin_unlock(&nna->lock); if (locked_pool != caller_pool) { raw_spin_unlock(&locked_pool->lock); raw_spin_lock(&caller_pool->lock); } } /** * pwq_dec_nr_active - Retire an active count * @pwq: pool_workqueue of interest * * Decrement @pwq's nr_active and try to activate the first inactive work item. * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. */ static void pwq_dec_nr_active(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); lockdep_assert_held(&pool->lock); /* * @pwq->nr_active should be decremented for both percpu and unbound * workqueues. */ pwq->nr_active--; /* * For a percpu workqueue, it's simple. Just need to kick the first * inactive work item on @pwq itself. */ if (!nna) { pwq_activate_first_inactive(pwq, false); return; } /* * If @pwq is for an unbound workqueue, it's more complicated because * multiple pwqs and pools may be sharing the nr_active count. When a * pwq needs to wait for an nr_active count, it puts itself on * $nna->pending_pwqs. The following atomic_dec_return()'s implied * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to * guarantee that either we see non-empty pending_pwqs or they see * decremented $nna->nr. * * $nna->max may change as CPUs come online/offline and @pwq->wq's * max_active gets updated. However, it is guaranteed to be equal to or * larger than @pwq->wq->min_active which is above zero unless freezing. * This maintains the forward progress guarantee. */ if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) return; if (!list_empty(&nna->pending_pwqs)) node_activate_pending_pwq(nna, pool); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * NOTE: * For unbound workqueues, this function may temporarily drop @pwq->pool->lock * and thus should be called after all other state updates for the in-flight * work item is complete. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*irq_flags); /* try to steal the timer if it exists */ if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If timer_delete() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(timer_delete(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { unsigned long work_data = *work_data_bits(work); debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be deleted directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Move the linked * barrier work items to the worklist when deleting the grabbed * item. Also keep WORK_STRUCT_INACTIVE in work_data, so that * it doesn't participate in nr_active management in later * pwq_dec_nr_in_flight(). */ if (work_data & WORK_STRUCT_INACTIVE) move_linked_works(work, &pwq->pool->worklist, NULL); list_del_init(&work->entry); /* * work->data points to pwq iff queued. Let's point to pool. As * this destroys work->data needed by the next step, stash it. */ set_work_pool_and_keep_pending(work, pool->id, pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*irq_flags); return -EAGAIN; } /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store IRQ state * * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * * Returns %true if @work was pending. %false if idle. */ static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { int ret; while (true) { ret = try_to_grab_pending(work, cflags, irq_flags); if (ret >= 0) return ret; cpu_relax(); } } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else { pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and_wrap(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool, *pool; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", work->func, wq->name))) { return; } rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (req_cpu == WORK_CPU_UNBOUND) { if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); else cpu = raw_smp_processor_id(); } pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. * * For ordered workqueue, work items must be queued on the newest pwq * for accurate order management. Guaranteed order also guarantees * non-reentrancy. See the comments above unplug_oldest_pwq(). */ last_pool = get_work_pool(work); if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; pool = pwq->pool; WARN_ON_ONCE(pool != last_pool); } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pool->lock); } } else { raw_spin_lock(&pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have raced * with pwq release and it could already be dead. If its refcnt is zero, * repeat pwq selection. Note that unbound pwqs never die without * another pwq replacing it in cpu_pwq or while work items are executing * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); /* * Limit the number of concurrently active work items to max_active. * @work must also queue behind existing inactive work items to maintain * ordering when max_active changes. See wq_adjust_max_active(). */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->last_progress_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { work_flags |= WORK_STRUCT_INACTIVE; insert_work(pwq, work, &pwq->inactive_works, work_flags); } out: raw_spin_unlock(&pool->lock); rcu_read_unlock(); } static bool clear_pending_if_disabled(struct work_struct *work) { unsigned long data = *work_data_bits(work); struct work_offq_data offqd; if (likely((data & WORK_STRUCT_PWQ) || !(data & WORK_OFFQ_DISABLE_MASK))) return false; work_offqd_unpack(&offqd, data); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); return true; } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * But note well that callers specifying a CPU that never has been * online will get a splat. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long irq_flags; local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * select_numa_node_cpu - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int select_numa_node_cpu(int node) { int cpu; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long irq_flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = timer_container_of(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu)); dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (housekeeping_enabled(HK_TYPE_TIMER)) { /* If the current cpu is a housekeeping cpu, use it. */ cpu = smp_processor_id(); if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); } else { if (likely(cpu == WORK_CPU_UNBOUND)) add_timer_global(timer); else add_timer_on(timer, cpu); } } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * We queue the delayed_work to a specific CPU, for non-zero delays the * caller must ensure it is online and can't go away. Callers that fail * to ensure this, may get @dwork->timer queued to an offlined CPU and * this will prevent queueing of @dwork->work unless the offlined CPU * becomes online again. * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long irq_flags; /* read the comment in __queue_work() */ local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; bool ret; ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; /* * rcu_work can't be canceled or disabled. Warn if the user reached * inside @rwork and disabled the inner work. */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { if (pool->cpu < 0 && pool->attrs->affn_strict) return pool->attrs->__pod_cpumask; else return pool->attrs->cpumask; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable * across this function. See the comments above the flag definition for * details. BH workers are, while per-CPU, always DISASSOCIATED. */ if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; } else { WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } static void unbind_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } static void detach_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); unbind_worker(worker); list_del(&worker->node); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; /* there is one permanent BH worker per CPU which should never detach */ WARN_ON_ONCE(pool->flags & POOL_BH); mutex_lock(&wq_pool_attach_mutex); detach_worker(worker); worker->pool = NULL; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); } static int format_worker_id(char *buf, size_t size, struct worker *worker, struct worker_pool *pool) { if (worker->rescue_wq) return scnprintf(buf, size, "kworker/R-%s", worker->rescue_wq->name); if (pool) { if (pool->cpu >= 0) return scnprintf(buf, size, "kworker/%d:%d%s", pool->cpu, worker->id, pool->attrs->nice < 0 ? "H" : ""); else return scnprintf(buf, size, "kworker/u%d:%d", pool->id, worker->id); } else { return scnprintf(buf, size, "kworker/dying"); } } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) { pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", ERR_PTR(id)); return NULL; } worker = alloc_worker(pool->node); if (!worker) { pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; } worker->id = id; if (!(pool->flags & POOL_BH)) { char id_buf[WORKER_ID_LEN]; format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", worker->task); } goto fail; } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); /* * @worker is waiting on a completion in kthread() and will trigger hung * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ if (worker->task) wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } static void detach_dying_workers(struct list_head *cull_list) { struct worker *worker; list_for_each_entry(worker, cull_list, entry) detach_worker(worker); } static void reap_dying_workers(struct list_head *cull_list) { struct worker *worker, *tmp; list_for_each_entry_safe(worker, tmp, cull_list, entry) { list_del_init(&worker->entry); kthread_stop_put(worker->task); kfree(worker); } } /** * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed * @list: transfer worker away from its pool->idle_list and into list * * Tag @worker for destruction and adjust @pool stats accordingly. The worker * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; worker->flags |= WORKER_DIE; list_move(&worker->entry, list); /* get an extra task struct reference for later kthread_stop_put() */ get_task_struct(worker->task); } /** * idle_worker_timeout - check if some idle workers can now be deleted. * @t: The pool's idle_timer that just expired * * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in * worker_leave_idle(), as a worker flicking between idle and active while its * pool is at the too_many_workers() tipping point would cause too much timer * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let * it expire and re-evaluate things from there. */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = timer_container_of(pool, t, idle_timer); bool do_cull = false; if (work_pending(&pool->idle_cull_work)) return; raw_spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); if (!do_cull) mod_timer(&pool->idle_timer, expires); } raw_spin_unlock_irq(&pool->lock); if (do_cull) queue_work(system_dfl_wq, &pool->idle_cull_work); } /** * idle_cull_fn - cull workers that have been idle for too long. * @work: the pool's work for handling these idle workers * * This goes through a pool's idle workers and gets rid of those that have been * idle for at least IDLE_WORKER_TIMEOUT seconds. * * We don't want to disturb isolated CPUs because of a pcpu kworker being * culled, so this also resets worker affinity. This requires a sleepable * context, hence the split between timer callback and work item. */ static void idle_cull_fn(struct work_struct *work) { struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); LIST_HEAD(cull_list); /* * Grabbing wq_pool_attach_mutex here ensures an already-running worker * cannot proceed beyong set_pf_worker() in its self-destruct path. * This is required as a previously-preempted worker could run after * set_worker_dying() has happened but before detach_dying_workers() did. */ mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); } static void send_mayday(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); pwq->stats[PWQ_STAT_MAYDAY]++; } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = timer_container_of(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(get_work_pwq(work)); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } timer_delete_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } #ifdef CONFIG_PREEMPT_RT static void worker_lock_callback(struct worker_pool *pool) { spin_lock(&pool->cb_lock); } static void worker_unlock_callback(struct worker_pool *pool) { spin_unlock(&pool->cb_lock); } static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { spin_lock(&pool->cb_lock); spin_unlock(&pool->cb_lock); } #else static void worker_lock_callback(struct worker_pool *pool) { } static void worker_unlock_callback(struct worker_pool *pool) { } static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { } #endif /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; int lockdep_start_depth, rcu_start_depth; bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; worker->current_start = jiffies; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Kick @pool if necessary. It's always noop for per-cpu worker pools * since nr_running would always be >= 1 at this point. This is used to * chain execution of the pending work items for WORKER_NOT_RUNNING * workers such as the UNBOUND and CPU_INTENSIVE ones. */ kick_pool(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); rcu_start_depth = rcu_preempt_depth(); lockdep_start_depth = lockdep_depth(current); /* see drain_dead_softirq_workfn() */ if (!bh_draining) lock_map_acquire(pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); if (!bh_draining) lock_map_release(pwq->wq->lockdep_map); if (unlikely((worker->task && in_atomic()) || lockdep_depth(current) != lockdep_start_depth || rcu_preempt_depth() != rcu_start_depth)) { pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", current->comm, task_pid_nr(current), preempt_count(), lockdep_start_depth, lockdep_depth(current), rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ if (worker->task) cond_resched(); raw_spin_lock_irq(&pool->lock); pwq->stats[PWQ_STAT_COMPLETED]++; /* * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked * CPU intensive by wq_worker_tick() if @work hogged CPU longer than * wq_cpu_intensive_thresh_us. Clear it. */ worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { struct work_struct *work; bool first = true; while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { worker->pool->last_progress_ts = jiffies; first = false; } process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); /* * The worker is dead and PF_WQ_WORKER is cleared, worker->pool * shouldn't be accessed, reset it to NULL in case otherwise. */ worker->pool = NULL; ida_free(&pool->worker_ida, worker->id); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } static bool assign_rescuer_work(struct pool_workqueue *pwq, struct worker *rescuer) { struct worker_pool *pool = pwq->pool; struct work_struct *cursor = &pwq->mayday_cursor; struct work_struct *work, *n; /* have work items to rescue? */ if (!pwq->nr_active) return false; /* need rescue? */ if (!need_to_create_worker(pool)) { /* * The pool has idle workers and doesn't need the rescuer, so it * could simply return false here. * * However, the memory pressure might not be fully relieved. * In PERCPU pool with concurrency enabled, having idle workers * does not necessarily mean memory pressure is gone; it may * simply mean regular workers have woken up, completed their * work, and gone idle again due to concurrency limits. * * In this case, those working workers may later sleep again, * the pool may run out of idle workers, and it will have to * allocate new ones and wait for the timer to send mayday, * causing unnecessary delay - especially if memory pressure * was never resolved throughout. * * Do more work if memory pressure is still on to reduce * relapse, using (pool->flags & POOL_MANAGER_ACTIVE), though * not precisely, unless there are other PWQs needing help. */ if (!(pool->flags & POOL_MANAGER_ACTIVE) || !list_empty(&pwq->wq->maydays)) return false; } /* search from the start or cursor if available */ if (list_empty(&cursor->entry)) work = list_first_entry(&pool->worklist, struct work_struct, entry); else work = list_next_entry(cursor, entry); /* find the next work item to rescue */ list_for_each_entry_safe_from(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) { pwq->stats[PWQ_STAT_RESCUED]++; /* put the cursor for next search */ list_move_tail(&cursor->entry, &n->entry); return true; } } return false; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; unsigned int count = 0; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); while (assign_rescuer_work(pwq, rescuer)) { process_scheduled_works(rescuer); /* * If the per-turn work item limit is reached and other * PWQs are in mayday, requeue mayday for this PWQ and * let the rescuer handle the other PWQs first. */ if (++count > RESCUER_BATCH && !list_empty(&pwq->wq->maydays) && pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); send_mayday(pwq); raw_spin_unlock(&wq_mayday_lock); break; } } /* The cursor can not be left behind without the rescuer watching it. */ if (!list_empty(&pwq->mayday_cursor.entry) && list_empty(&pwq->mayday_node)) list_del_init(&pwq->mayday_cursor.entry); /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); /* * Put the reference grabbed by send_mayday(). @pool might * go away any time after it. */ put_pwq_unlocked(pwq); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } static void bh_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; int nr_restarts = BH_WORKER_RESTARTS; unsigned long end = jiffies + BH_WORKER_JIFFIES; worker_lock_callback(pool); raw_spin_lock_irq(&pool->lock); worker_leave_idle(worker); /* * This function follows the structure of worker_thread(). See there for * explanations on each step. */ if (!need_more_worker(pool)) goto done; WARN_ON_ONCE(!list_empty(&worker->scheduled)); worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool) && --nr_restarts && time_before(jiffies, end)); worker_set_flags(worker, WORKER_PREP); done: worker_enter_idle(worker); kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_unlock_callback(pool); } /* * TODO: Convert all tasklet users to workqueue and use softirq directly. * * This is currently called from tasklet[_hi]action() and thus is also called * whenever there are tasklets to run. Let's do an early exit if there's nothing * queued. Once conversion from tasklet is complete, the need_more_worker() test * can be dropped. * * After full conversion, we'll add worker->softirq_action, directly use the * softirq action and obtain the worker pointer from the softirq_action pointer. */ void workqueue_softirq_action(bool highpri) { struct worker_pool *pool = &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; if (need_more_worker(pool)) bh_worker(list_first_entry(&pool->workers, struct worker, node)); } struct wq_drain_dead_softirq_work { struct work_struct work; struct worker_pool *pool; struct completion done; }; static void drain_dead_softirq_workfn(struct work_struct *work) { struct wq_drain_dead_softirq_work *dead_work = container_of(work, struct wq_drain_dead_softirq_work, work); struct worker_pool *pool = dead_work->pool; bool repeat; /* * @pool's CPU is dead and we want to execute its still pending work * items from this BH work item which is running on a different CPU. As * its CPU is dead, @pool can't be kicked and, as work execution path * will be nested, a lockdep annotation needs to be suppressed. Mark * @pool with %POOL_BH_DRAINING for the special treatments. */ raw_spin_lock_irq(&pool->lock); pool->flags |= POOL_BH_DRAINING; raw_spin_unlock_irq(&pool->lock); bh_worker(list_first_entry(&pool->workers, struct worker, node)); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_BH_DRAINING; repeat = need_more_worker(pool); raw_spin_unlock_irq(&pool->lock); /* * bh_worker() might hit consecutive execution limit and bail. If there * still are pending work items, reschedule self and return so that we * don't hog this CPU's BH. */ if (repeat) { if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, work); else queue_work(system_bh_wq, work); } else { complete(&dead_work->done); } } /* * @cpu is dead. Drain the remaining BH work items on the current CPU. It's * possible to allocate dead_work per CPU and avoid flushing. However, then we * have to worry about draining overlapping with CPU coming back online or * nesting (one CPU's dead_work queued on another CPU which is also dead and so * on). Let's keep it simple and drain them synchronously. These are BH work * items which shouldn't be requeued on the same pool. Shouldn't take long. */ void workqueue_softirq_dead(unsigned int cpu) { int i; for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; struct wq_drain_dead_softirq_work dead_work; if (!need_more_worker(pool)) continue; INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, &dead_work.work); else queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); destroy_work_on_stack(&dead_work.work); } } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. * If this is not the cancel path (which implies work being flushed is either * already running, or will not be at all), check if @target_wq doesn't have * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work, bool from_cancel) { work_func_t target_func; struct worker *worker; if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. * * BH and threaded workqueues need separate lockdep keys to avoid * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} * usage". */ INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; struct worker_pool *current_pool = NULL; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } /* * For unbound workqueue, pwqs will map to only a few pools. * Most of the time, pwqs within the same pool will be linked * sequentially to wq->pwqs by cpu index. So in the majority * of pwq iters, the pool is the same, only doing lock/unlock * if the pool has changed. This can largely reduce expensive * lock operations. */ for_each_pwq(pwq, wq) { if (current_pool != pwq->pool) { if (likely(current_pool)) raw_spin_unlock_irq(¤t_pool->lock); current_pool = pwq->pool; raw_spin_lock_irq(¤t_pool->lock); } if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } } if (current_pool) raw_spin_unlock_irq(¤t_pool->lock); if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } static void touch_wq_lockdep_map(struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (unlikely(!wq->lockdep_map)) return; if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(wq->lockdep_map); lock_map_release(wq->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, (*wq->lockdep_map)), }; int next_color; if (WARN_ON(!wq_online)) return; touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; struct workqueue_struct *wq; rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } wq = pwq->wq; check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); touch_work_lockdep_map(work, wq); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) touch_wq_lockdep_map(wq); rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; if (!start_flush_work(work, &barr, from_cancel)) return false; /* * start_flush_work() returned %true. If @from_cancel is set, we know * that @work must have been executing during start_flush_work() and * can't currently be queued. Its data must contain OFFQ bits. If @work * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ if (from_cancel) { unsigned long data = *work_data_bits(work); if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { /* * On RT, prevent a live lock when %current preempted * soft interrupt processing by blocking on lock which * is owned by the thread invoking the callback. */ while (!try_wait_for_completion(&barr.done)) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { struct worker_pool *pool; guard(rcu)(); pool = get_work_pool(work); if (pool) workqueue_callback_cancel_wait_running(pool); } else { cpu_relax(); } } goto out_destroy; } } wait_for_completion(&barr.done); out_destroy: destroy_work_on_stack(&barr.work); return true; } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (timer_delete_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static void work_offqd_disable(struct work_offq_data *offqd) { const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; if (likely(offqd->disable < max)) offqd->disable++; else WARN_ONCE(true, "workqueue: work disable count overflowed\n"); } static void work_offqd_enable(struct work_offq_data *offqd) { if (likely(offqd->disable > 0)) offqd->disable--; else WARN_ONCE(true, "workqueue: work disable count underflowed\n"); } static bool __cancel_work(struct work_struct *work, u32 cflags) { struct work_offq_data offqd; unsigned long irq_flags; int ret; ret = work_grab_pending(work, cflags, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); if (cflags & WORK_CANCEL_DISABLE) work_offqd_disable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { bool ret; ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); if (*work_data_bits(work) & WORK_OFFQ_BH) WARN_ON_ONCE(in_hardirq()); else might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't * executing. This allows canceling during early boot. */ if (wq_online) __flush_work(work, true); if (!(cflags & WORK_CANCEL_DISABLE)) enable_work(work); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function can be used * even if the work re-queues itself or migrates to another workqueue. On return * from this function, @work is guaranteed to be not pending or executing on any * CPU as long as there aren't racing enqueues. * * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. * Use cancel_delayed_work_sync() instead. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_sync(work, 0); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * disable_work - Disable and cancel a work item * @work: work item to disable * * Disable @work by incrementing its disable count and cancel it if currently * pending. As long as the disable count is non-zero, any attempt to queue @work * will fail and return %false. The maximum supported disable depth is 2 to the * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. * * Can be called from any context. Returns %true if @work was pending, %false * otherwise. */ bool disable_work(struct work_struct *work) { return __cancel_work(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work); /** * disable_work_sync - Disable, cancel and drain a work item * @work: work item to disable * * Similar to disable_work() but also wait for @work to finish if currently * executing. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool disable_work_sync(struct work_struct *work) { return __cancel_work_sync(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work_sync); /** * enable_work - Enable a work item * @work: work item to enable * * Undo disable_work[_sync]() by decrementing @work's disable count. @work can * only be queued if its disable count is 0. * * Can be called from any context. Returns %true if the disable count reached 0. * Otherwise, %false. */ bool enable_work(struct work_struct *work) { struct work_offq_data offqd; unsigned long irq_flags; work_grab_pending(work, 0, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); work_offqd_enable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return !offqd.disable; } EXPORT_SYMBOL_GPL(enable_work); /** * disable_delayed_work - Disable and cancel a delayed work item * @dwork: delayed work item to disable * * disable_work() for delayed work items. */ bool disable_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work); /** * disable_delayed_work_sync - Disable, cancel and drain a delayed work item * @dwork: delayed work item to disable * * disable_work_sync() for delayed work items. */ bool disable_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work_sync); /** * enable_delayed_work - Enable a delayed work item * @dwork: delayed work item to enable * * enable_work() for delayed work items. */ bool enable_delayed_work(struct delayed_work *dwork) { return enable_work(&dwork->work); } EXPORT_SYMBOL_GPL(enable_delayed_work); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs_noprof(void) { struct workqueue_attrs *attrs; attrs = kzalloc_obj(*attrs); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only * fields as copying is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears the fields. */ to->affn_scope = from->affn_scope; to->ordered = from->ordered; } /* * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the * comments in 'struct workqueue_attrs' definition. */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; if (attrs->affn_strict) cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); if (!attrs->affn_strict) hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /* Update @attrs with actually available CPUs */ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, const cpumask_t *unbound_cpumask) { /* * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to * @unbound_cpumask. */ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(attrs->cpumask))) cpumask_copy(attrs->cpumask, unbound_cpumask); } /* find wq_pod_type to use for @attrs */ static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { enum wq_affn_scope scope; struct wq_pod_type *pt; /* to synchronize access to wq_affn_dfl */ lockdep_assert_held(&wq_pool_mutex); if (attrs->affn_scope == WQ_AFFN_DFL) scope = wq_affn_dfl; else scope = attrs->affn_scope; pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) return pt; /* * Before workqueue_init_topology(), only SYSTEM is available which is * initialized in workqueue_init_early(). */ pt = &wq_pod_types[WQ_AFFN_SYSTEM]; BUG_ON(!pt->nr_pods); return pt; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->last_progress_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; #ifdef CONFIG_PREEMPT_RT spin_lock_init(&pool->cb_lock); #endif /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; wqattrs_clear_for_pool(pool->attrs); return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; wq->lockdep_map = &wq->__lockdep_map; lockdep_init_map(wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void free_node_nr_active(struct wq_node_nr_active **nna_ar) { int node; for_each_node(node) { kfree(nna_ar[node]); nna_ar[node] = NULL; } kfree(nna_ar[nr_node_ids]); nna_ar[nr_node_ids] = NULL; } static void init_node_nr_active(struct wq_node_nr_active *nna) { nna->max = WQ_DFL_MIN_ACTIVE; atomic_set(&nna->nr, 0); raw_spin_lock_init(&nna->lock); INIT_LIST_HEAD(&nna->pending_pwqs); } /* * Each node's nr_active counter will be accessed mostly from its own node and * should be allocated in the node. */ static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) { struct wq_node_nr_active *nna; int node; for_each_node(node) { nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[node] = nna; } /* [nr_node_ids] is used as the fallback */ nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[nr_node_ids] = nna; return 0; err_free: free_node_nr_active(nna_ar); return -ENOMEM; } static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { struct worker *worker; LIST_HEAD(cull_list); lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * * Having a concurrent manager is quite unlikely to happen as we can * only get here with * pwq->refcnt == pool->refcnt == 0 * which implies no work queued to the pool, which implies no worker can * become the manager. However a worker could have taken the role of * manager before the refcnts dropped to 0, since maybe_create_worker() * drops pool->lock */ while (true) { rcuwait_wait_event(&manager_wait, !(pool->flags & POOL_MANAGER_ACTIVE), TASK_UNINTERRUPTIBLE); mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); if (!(pool->flags & POOL_MANAGER_ACTIVE)) { pool->flags |= POOL_MANAGER_ACTIVE; break; } raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); } while ((worker = first_idle_worker(pool))) set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); /* shut down the timers */ timer_delete_sync(&pool->idle_timer); cancel_work_sync(&pool->idle_cull_work); timer_delete_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } /* * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero * refcnt and needs to be destroyed. */ static void pwq_release_workfn(struct kthread_work *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * When @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); /* * For ordered workqueue with a plugged dfl_pwq, restart it now. */ if (!is_last && (wq->flags & __WQ_ORDERED)) unplug_oldest_pwq(wq); mutex_unlock(&wq->mutex); } if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); } if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); raw_spin_lock_irq(&nna->lock); list_del_init(&pwq->pending_node); raw_spin_unlock_irq(&nna->lock); } kfree_rcu(pwq, rcu); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); /* * Set the dummy cursor work with valid function and get_work_pwq(). * * The cursor work should only be in the pwq->pool->worklist, and * should not be treated as a processable work item. * * WORK_STRUCT_PENDING and WORK_STRUCT_INACTIVE just make it less * surprise for kernel debugging tools and reviewers. */ INIT_WORK(&pwq->mayday_cursor, mayday_cursor_func); atomic_long_set(&pwq->mayday_cursor.data, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | WORK_STRUCT_INACTIVE); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* link in @pwq */ list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } static void apply_wqattrs_lock(void) { mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); } /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * * Calculate the cpumask a workqueue with @attrs should use on @pod. * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the * intersection of the possible CPUs of @pod and @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* calculate possible CPUs in @pod that @attrs wants */ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); /* does @pod have any online CPUs @attrs wants? */ if (!cpumask_intersects(attrs->__pod_cpumask, wq_online_cpumask)) { cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } } /* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(*slot); rcu_assign_pointer(*slot, pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int cpu; for_each_possible_cpu(cpu) put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); if (WARN_ON(attrs->affn_scope < 0 || attrs->affn_scope >= WQ_AFFN_NR_TYPES)) return ERR_PTR(-EINVAL); ctx = kzalloc_flex(*ctx, pwq_tbl, nr_cpu_ids); new_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs) goto out_free; /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { wq_calc_pod_cpumask(new_attrs, cpu); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; /* * For initialized ordered workqueues, there should only be one pwq * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution * of newly queued work items until execution of older work items in * the old pwq's have completed. */ if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) ctx->dfl_pwq->plugged = true; ctx->wq = wq; return ctx; out_free: free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); /* update node_nr_active->max */ wq_update_node_max_active(ctx->wq, -1); mutex_unlock(&ctx->wq->mutex); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that * work items are affine to the pod it was issued on. Older pwqs are released as * in-flight work items finish. Note that a work item which repeatedly requeues * itself back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * unbound_wq_update_pwq - update a pwq slot for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU to update the pwq slot for * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is in the same pod of the CPU being hot[un]plugged. * * * If pod affinity can't be adjusted due to memory allocation failure, it falls * back to @wq->dfl_pwq which may not be optimal but is always correct. * * Note that when the last allowed CPU of a pod goes offline for a workqueue * with a cpumask spanning multiple pods, the workers which were already * executing the work items for the workqueue will lose their CPU affinity and * may execute on any CPU. This is similar to how per-cpu workqueues behave on * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's * responsibility to flush the work item from CPU_DOWN_PREPARE. */ static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu) { struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = unbound_wq_update_pwq_attrs_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu); if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); pwq = unbound_pwq(wq, -1); raw_spin_lock_irq(&pwq->pool->lock); get_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; lockdep_assert_held(&wq_pool_mutex); wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; if (!(wq->flags & WQ_UNBOUND)) { struct worker_pool __percpu *pools; if (wq->flags & WQ_BH) pools = bh_worker_pools; else pools = cpu_worker_pools; for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p; struct worker_pool *pool; pool = &(per_cpu_ptr(pools, cpu)[highpri]); pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!*pwq_p) goto enomem; init_pwq(*pwq_p, wq, pool); mutex_lock(&wq->mutex); link_pwq(*pwq_p); mutex_unlock(&wq->mutex); } return 0; } if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } return ret; enomem: if (wq->cpu_pwq) { for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); if (pwq) kmem_cache_free(pwq_cache, pwq); } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } return -ENOMEM; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, WQ_MAX_ACTIVE); return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; char id_buf[WORKER_ID_LEN]; int ret; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) { pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", wq->name); return -ENOMEM; } rescuer->rescue_wq = wq; format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } wq->rescuer = rescuer; /* initial cpumask is consistent with the detached rescuer and unbind_worker() */ if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) kthread_bind_mask(rescuer->task, wq_unbound_cpumask); else kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } /** * wq_adjust_max_active - update a wq's max_active to the current setting * @wq: target workqueue * * If @wq isn't freezing, set @wq->max_active to the saved_max_active and * activate inactive work items accordingly. If @wq is freezing, clear * @wq->max_active to zero. */ static void wq_adjust_max_active(struct workqueue_struct *wq) { bool activated; int new_max, new_min; lockdep_assert_held(&wq->mutex); if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { new_max = 0; new_min = 0; } else { new_max = wq->saved_max_active; new_min = wq->saved_min_active; } if (wq->max_active == new_max && wq->min_active == new_min) return; /* * Update @wq->max/min_active and then kick inactive work items if more * active work items are allowed. This doesn't break work item ordering * because new work items are always queued behind existing inactive * work items if there are any. */ WRITE_ONCE(wq->max_active, new_max); WRITE_ONCE(wq->min_active, new_min); if (wq->flags & WQ_UNBOUND) wq_update_node_max_active(wq, -1); if (new_max == 0) return; /* * Round-robin through pwq's activating the first inactive work item * until max_active is filled. */ do { struct pool_workqueue *pwq; activated = false; for_each_pwq(pwq, wq) { unsigned long irq_flags; /* can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (pwq_activate_first_inactive(pwq, true)) { activated = true; kick_pool(pwq->pool); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); } } while (activated); } __printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) { struct workqueue_struct *wq; size_t wq_size; int name_len; if (flags & WQ_BH) { if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) return NULL; if (WARN_ON_ONCE(max_active)) return NULL; } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); else wq_size = sizeof(*wq); wq = kzalloc_noprof(wq_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs_noprof(); if (!wq->unbound_attrs) goto err_free_wq; } name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); if (flags & WQ_BH) { /* * BH workqueues always share a single execution context per CPU * and don't impose any max_active limit. */ max_active = INT_MAX; } else { max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); } /* init wq */ wq->flags = flags; wq->max_active = max_active; wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); wq->saved_max_active = wq->max_active; wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); INIT_LIST_HEAD(&wq->list); if (flags & WQ_UNBOUND) { if (alloc_node_nr_active(wq->node_nr_active) < 0) goto err_free_wq; } /* * wq_pool_mutex protects the workqueues list, allocations of PWQs, * and the global freeze state. */ apply_wqattrs_lock(); if (alloc_and_link_pwqs(wq) < 0) goto err_unlock_free_node_nr_active; mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); if (wq_online && init_rescuer(wq) < 0) goto err_unlock_destroy; apply_wqattrs_unlock(); if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; return wq; err_unlock_free_node_nr_active: apply_wqattrs_unlock(); /* * Failed alloc_and_link_pwqs() may leave pending pwq->release_work, * flushing the pwq_release_worker ensures that the pwq_release_workfn() * completes before calling kfree(wq). */ if (wq->flags & WQ_UNBOUND) { kthread_flush_worker(pwq_release_worker); free_node_nr_active(wq->node_nr_active); } err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_unlock_destroy: apply_wqattrs_unlock(); err_destroy: destroy_workqueue(wq); return NULL; } __printf(1, 4) struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; va_start(args, max_active); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq_init_lockdep(wq); return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_noprof); #ifdef CONFIG_LOCKDEP __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...) { struct workqueue_struct *wq; va_list args; va_start(args, lockdep_map); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq->lockdep_map = lockdep_map; return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_lockdep_map); #endif static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; if (!pwq_is_empty(pwq)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. * * This function does NOT guarantee that non-pending work that has been * submitted with queue_delayed_work() and similar functions will be done * before destroying the workqueue. The fundamental problem is that, currently, * the workqueue has no way of accessing non-pending delayed_work. delayed_work * is only linked on the timer-side. All delayed_work must, therefore, be * canceled before calling this function. * * TODO: It would be better if the problem described above wouldn't exist and * destroy_workqueue() would cleanly cancel all pending and non-pending * delayed_work. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* mark the workqueue destruction is in progress */ mutex_lock(&wq->mutex); wq->flags |= __WQ_DESTROYING; mutex_unlock(&wq->mutex); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { /* rescuer will empty maydays list before exiting */ kthread_stop(wq->rescuer->task); kfree(wq->rescuer); wq->rescuer = NULL; } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); /* * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq * to put the base refs. @wq will be auto-destroyed from the last * pwq_put. RCU read lock prevents @wq from going away from under us. */ rcu_read_lock(); for_each_possible_cpu(cpu) { put_pwq_unlocked(unbound_pwq(wq, cpu)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } put_pwq_unlocked(unbound_pwq(wq, -1)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. See the alloc_workqueue() function * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { /* max_active doesn't mean anything for BH workqueues */ if (WARN_ON(wq->flags & WQ_BH)) return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->saved_max_active = max_active; if (wq->flags & WQ_UNBOUND) wq->saved_min_active = min(wq->saved_min_active, max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_set_min_active - adjust min_active of an unbound workqueue * @wq: target unbound workqueue * @min_active: new min_active value * * Set min_active of an unbound workqueue. Unlike other types of workqueues, an * unbound workqueue is not guaranteed to be able to process max_active * interdependent work items. Instead, an unbound workqueue is guaranteed to be * able to process min_active number of interdependent work items which is * %WQ_DFL_MIN_ACTIVE by default. * * Use this function to adjust the min_active value between 0 and the current * max_active. */ void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) { /* min_active is only meaningful for non-ordered unbound workqueues */ if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != WQ_UNBOUND)) return; mutex_lock(&wq->mutex); wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * * With the exception of ordered workqueues, all workqueues have per-cpu * pool_workqueues, each with its own congested state. A workqueue being * congested on one CPU doesn't mean that the workqueue is contested on any * other CPUs. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x", pool->flags); if (pool->flags & POOL_BH) pr_cont(" bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont(" nice=%d", pool->attrs->nice); } static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont("%d%s", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { bool comma; work_func_t func; long ctr; }; static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) { if (!pcwsp->ctr) goto out_record; if (func == pcwsp->func) { pcwsp->ctr++; return; } if (pcwsp->ctr == 1) pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); else pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); pcwsp->ctr = 0; out_record: if ((long)func == -1L) return; pcwsp->comma = comma; pcwsp->func = func; pcwsp->ctr = 1; } static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { if (!comma) pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d refcnt=%d%s\n", pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); pr_cont(" for %us", jiffies_to_msecs(jiffies - worker->current_start) / 1000); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long irq_flags; for_each_pwq(pwq, wq) { if (!pwq_is_empty(pwq)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long irq_flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s", first ? "idle: " : ""); pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /** * show_freezable_workqueues - dump freezable workqueue state * * Called from try_to_freeze_tasks() and prints out all freezable workqueues * still busy. */ void show_freezable_workqueues(void) { struct workqueue_struct *wq; rcu_read_lock(); pr_info("Showing freezable workqueues that are still busy:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; show_one_workqueue(wq); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; int off; off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } else { strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); cpumask_set_cpu(cpu, wq_online_cpumask); for_each_pool(pool, pi) { /* BH pools aren't affected by hotplug */ if (pool->flags & POOL_BH) continue; mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); cpumask_clear_cpu(cpu, wq_online_cpumask); list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, cpu); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { int cpu; struct worker_pool *pool; struct worker *worker; mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); /* rescuer needs to respect cpumask changes when it is not attached */ list_for_each_entry(wq, &workqueues, list) { if (wq->rescuer && !wq->rescuer->pool) unbind_worker(wq->rescuer); } /* DISASSOCIATED worker needs to respect wq_unbound_cpumask */ for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { if (!(pool->flags & POOL_DISASSOCIATED)) continue; for_each_pool_worker(worker, pool) unbind_worker(worker); } } mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_unbound_housekeeping_update - Propagate housekeeping cpumask update * @hk: the new housekeeping cpumask * * Update the unbound workqueue cpumask on top of the new housekeeping cpumask such * that the effective unbound affinity is the intersection of the new housekeeping * with the requested affinity set via nohz_full=/isolcpus= or sysfs. * * Return: 0 on success and -errno on failure. */ int workqueue_unbound_housekeeping_update(const struct cpumask *hk) { cpumask_var_t cpumask; int ret = 0; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; mutex_lock(&wq_pool_mutex); /* * If the operation fails, it will fall back to * wq_requested_unbound_cpumask which is initially set to * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten * by any subsequent write to workqueue/cpumask sysfs file. */ if (!cpumask_and(cpumask, wq_requested_unbound_cpumask, hk)) cpumask_copy(cpumask, wq_requested_unbound_cpumask); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); /* Save the current isolated cpumask & export it via sysfs */ if (!ret) cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask, hk); mutex_unlock(&wq_pool_mutex); free_cpumask_var(cpumask); return ret; } static int parse_affn_scope(const char *val) { int i; for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) { if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i]))) return i; } return -EINVAL; } static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { struct workqueue_struct *wq; int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; if (affn == WQ_AFFN_DFL) return -EINVAL; cpus_read_lock(); mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); } mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); return 0; } static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); } static const struct kernel_param_ops wq_affn_dfl_ops = { .set = wq_affn_dfl_set, .get = wq_affn_dfl_get, }; module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affn_scope_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", wq_affn_names[WQ_AFFN_DFL], wq_affn_names[wq_affn_dfl]); else written = scnprintf(buf, PAGE_SIZE, "%s\n", wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_affn_scope_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int affn, ret = -ENOMEM; affn = parse_affn_scope(buf); if (affn < 0) return affn; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_scope = affn; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affinity_strict_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->affn_strict); } static ssize_t wq_affinity_strict_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; if (sscanf(buf, "%d", &v) != 1) return -EINVAL; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_strict = (bool)v; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { ret = 0; apply_wqattrs_lock(); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); if (!ret) cpumask_copy(wq_requested_unbound_cpumask, cpumask); apply_wqattrs_unlock(); } return ret; } static ssize_t __wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } static DEVICE_ATTR_RO(cpumask_requested); static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } static DEVICE_ATTR_RO(cpumask_isolated); static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static DEVICE_ATTR_RW(cpumask); static struct attribute *wq_sysfs_cpumask_attrs[] = { &dev_attr_cpumask.attr, &dev_attr_cpumask_requested.attr, &dev_attr_cpumask_isolated.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active breaks ordering guarantee. Disallow exposing * ordered workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc_obj(*wq_dev); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static unsigned int wq_panic_on_stall = CONFIG_BOOTPARAM_WQ_STALL_PANIC; module_param_named(panic_on_stall, wq_panic_on_stall, uint, 0644); static unsigned int wq_panic_on_stall_time; module_param_named(panic_on_stall_time, wq_panic_on_stall_time, uint, 0644); MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds (0=disabled)"); /* * Show workers that might prevent the processing of pending work items. * A busy worker that is not running on the CPU (e.g. sleeping in * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as * effectively as a CPU-bound one, so dump every in-flight worker. */ static void show_cpu_pool_busy_workers(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; int bkt; raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); pr_info("pool %d:\n", pool->id); sched_show_task(worker->task); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_busy_workers(void) { struct worker_pool *pool; int pi; pr_info("Showing backtraces of busy workers in stalled worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) show_cpu_pool_busy_workers(pool); } rcu_read_unlock(); } /* * It triggers a panic in two scenarios: when the total number of stalls * exceeds a threshold, and when a stall lasts longer than * wq_panic_on_stall_time */ static void panic_on_wq_watchdog(unsigned int stall_time_sec) { static unsigned int wq_stall; if (wq_panic_on_stall) { wq_stall++; if (wq_stall >= wq_panic_on_stall) panic("workqueue: %u stall(s) exceeded threshold %u\n", wq_stall, wq_panic_on_stall); } if (wq_panic_on_stall_time && stall_time_sec >= wq_panic_on_stall_time) panic("workqueue: stall lasted %us, exceeding threshold %us\n", stall_time_sec, wq_panic_on_stall_time); } static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned int max_stall_time = 0; bool lockup_detected = false; bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; unsigned int stall_time; int pi; if (!thresh) return; for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->last_progress_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; stall_time = jiffies_to_msecs(now - pool_ts) / 1000; max_stall_time = max(max_stall_time, stall_time); if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", stall_time); } } if (lockup_detected) show_all_workqueues(); if (cpu_pool_stall) show_cpu_pools_busy_workers(); if (lockup_detected) panic_on_wq_watchdog(max_stall_time); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; timer_delete_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void bh_pool_kick_normal(struct irq_work *irq_work) { raise_softirq_irqoff(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { raise_softirq_irqoff(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); return; } cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = nice; pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first step of three-staged workqueue subsystem initialization and * invoked as soon as the bare basics - memory allocation, cpumasks and idr are * up. It sets up all the data structures and system workqueues and allows early * boot code to create workqueues and queue/cancel work items. Actual work item * execution starts only after kthreads can be created and scheduled right * before early initcalls. */ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal, bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_online_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); cpumask_copy(wq_online_cpumask, cpu_online_mask); cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!unbound_wq_update_pwq_attrs_buf); /* * If nohz_full is enabled, set power efficient workqueue as unbound. * This allows workqueue items to be moved to HK CPUs. */ if (housekeeping_enabled(HK_TYPE_TICK)) wq_power_efficient = true; /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kzalloc_objs(pt->pod_cpus[0], 1); pt->pod_node = kzalloc_objs(pt->pod_node[0], 1); pt->cpu_pod = kzalloc_objs(pt->cpu_pod[0], nr_cpu_ids); BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_bh_worker_pool(pool, cpu) { init_cpu_worker_pool(pool, cpu, std_nice[i]); pool->flags |= POOL_BH; init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); i++; } i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->ordered = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", WQ_PERCPU, 0); system_percpu_wq = alloc_workqueue("events", WQ_PERCPU, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI | WQ_PERCPU, 0); system_long_wq = alloc_workqueue("events_long", WQ_PERCPU, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE | WQ_PERCPU, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT | WQ_PERCPU, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0); system_bh_wq = alloc_workqueue("events_bh", WQ_BH | WQ_PERCPU, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI | WQ_PERCPU, 0); BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_dfl_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) { unsigned long thresh; unsigned long bogo; pwq_release_worker = kthread_run_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what * most consider human-perceivable. However, the kernel also runs on a * lot slower CPUs including microcontrollers where the threshold is way * too low. * * Let's scale up the threshold upto 1 second if BogoMips is below 4000. * This is by no means accurate but it doesn't have to be. The mechanism * is still useful even when the threshold is fully scaled up. Also, as * the reports would usually be applicable to everyone, some machines * operating on longer thresholds won't significantly diminish their * usefulness. */ thresh = 10 * USEC_PER_MSEC; /* see init/calibrate.c for lpj -> BogoMIPS calculation */ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); if (bogo < 4000) thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", loops_per_jiffy, bogo, thresh); wq_cpu_intensive_thresh_us = thresh; } /** * workqueue_init - bring workqueue subsystem fully online * * This is the second step of three-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. Workqueues have * been created and work items queued on them, but there are no kworkers * executing the work items yet. Populate the worker pools with the initial * workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; wq_cpu_intensive_thresh_init(); mutex_lock(&wq_pool_mutex); /* * Per-cpu pools created earlier could be missing node hint. Fix them * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { for_each_bh_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); } list_for_each_entry(wq, &workqueues, list) { WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* * Create the initial workers. A BH pool has one pseudo worker that * represents the shared BH execution context and thus doesn't get * affected by hotplug events. Create the BH pseudo workers for all * possible CPUs here. */ for_each_possible_cpu(cpu) for_each_bh_worker_pool(pool, cpu) BUG_ON(!create_worker(pool)); for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique * and consecutive pod ID. The rest of @pt is initialized accordingly. */ static void __init init_pod_type(struct wq_pod_type *pt, bool (*cpus_share_pod)(int, int)) { int cur, pre, cpu, pod; pt->nr_pods = 0; /* init @pt->cpu_pod[] according to @cpus_share_pod() */ pt->cpu_pod = kzalloc_objs(pt->cpu_pod[0], nr_cpu_ids); BUG_ON(!pt->cpu_pod); for_each_possible_cpu(cur) { for_each_possible_cpu(pre) { if (pre >= cur) { pt->cpu_pod[cur] = pt->nr_pods++; break; } if (cpus_share_pod(cur, pre)) { pt->cpu_pod[cur] = pt->cpu_pod[pre]; break; } } } /* init the rest to match @pt->cpu_pod[] */ pt->pod_cpus = kzalloc_objs(pt->pod_cpus[0], pt->nr_pods); pt->pod_node = kzalloc_objs(pt->pod_node[0], pt->nr_pods); BUG_ON(!pt->pod_cpus || !pt->pod_node); for (pod = 0; pod < pt->nr_pods; pod++) BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL)); for_each_possible_cpu(cpu) { cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]); pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu); } } static bool __init cpus_dont_share(int cpu0, int cpu1) { return false; } static bool __init cpus_share_smt(int cpu0, int cpu1) { #ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); #else return false; #endif } static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); } /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ void __init workqueue_init_topology(void) { struct workqueue_struct *wq; int cpu; init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); wq_topo_initialized = true; mutex_lock(&wq_pool_mutex); /* * Workqueues allocated earlier would have all CPUs sharing the default * worker pool. Explicitly call unbound_wq_update_pwq() on all workqueue * and CPU combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) { pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n"); dump_stack(); } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); static int __init workqueue_unbound_cpus_setup(char *str) { if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) { cpumask_clear(&wq_cmdline_cpumask); pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n"); } return 1; } __setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup); |
| 1 1 2 7 5 2 6 6 220 220 29 29 7 1 6 11 1 9 5 4 5 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * KVM coalesced MMIO * * Copyright (c) 2008 Bull S.A.S. * Copyright 2009 Red Hat, Inc. and/or its affiliates. * * Author: Laurent Vivier <Laurent.Vivier@bull.net> * */ #include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/slab.h> #include <linux/kvm.h> #include "coalesced_mmio.h" static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev) { return container_of(dev, struct kvm_coalesced_mmio_dev, dev); } static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, gpa_t addr, int len) { /* is it in a batchable area ? * (addr,len) is fully included in * (zone->addr, zone->size) */ if (len < 0) return 0; if (addr + len < addr) return 0; if (addr < dev->zone.addr) return 0; if (addr + len > dev->zone.addr + dev->zone.size) return 0; return 1; } static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring; __u32 insert; if (!coalesced_mmio_in_range(dev, addr, len)) return -EOPNOTSUPP; spin_lock(&dev->kvm->ring_lock); /* * last is the index of the entry to fill. Verify userspace hasn't * set last to be out of range, and that there is room in the ring. * Leave one entry free in the ring so that userspace can differentiate * between an empty ring and a full ring. */ insert = READ_ONCE(ring->last); if (insert >= KVM_COALESCED_MMIO_MAX || (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } /* copy data in first free entry of the ring */ ring->coalesced_mmio[insert].phys_addr = addr; ring->coalesced_mmio[insert].len = len; memcpy(ring->coalesced_mmio[insert].data, val, len); ring->coalesced_mmio[insert].pio = dev->zone.pio; smp_wmb(); ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX; spin_unlock(&dev->kvm->ring_lock); return 0; } static void coalesced_mmio_destructor(struct kvm_io_device *this) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); list_del(&dev->list); kfree(dev); } static const struct kvm_io_device_ops coalesced_mmio_ops = { .write = coalesced_mmio_write, .destructor = coalesced_mmio_destructor, }; int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) return -ENOMEM; kvm->coalesced_mmio_ring = page_address(page); /* * We're using this spinlock to sync access to the coalesced ring. * The list doesn't need its own lock since device registration and * unregistration should only happen when kvm->slots_lock is held. */ spin_lock_init(&kvm->ring_lock); INIT_LIST_HEAD(&kvm->coalesced_zones); return 0; } void kvm_coalesced_mmio_free(struct kvm *kvm) { if (kvm->coalesced_mmio_ring) free_page((unsigned long)kvm->coalesced_mmio_ring); } int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { int ret; struct kvm_coalesced_mmio_dev *dev; if (zone->pio != 1 && zone->pio != 0) return -EINVAL; dev = kzalloc_obj(struct kvm_coalesced_mmio_dev, GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops); dev->kvm = kvm; dev->zone = *zone; mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, zone->addr, zone->size, &dev->dev); if (ret < 0) goto out_free_dev; list_add_tail(&dev->list, &kvm->coalesced_zones); mutex_unlock(&kvm->slots_lock); return 0; out_free_dev: mutex_unlock(&kvm->slots_lock); kfree(dev); return ret; } int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { struct kvm_coalesced_mmio_dev *dev, *tmp; int r; if (zone->pio != 1 && zone->pio != 0) return -EINVAL; mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) { if (zone->pio == dev->zone.pio && coalesced_mmio_in_range(dev, zone->addr, zone->size)) { r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); /* * On failure, unregister destroys all devices on the * bus, including the target device. There's no need * to restart the walk as there aren't any zones left. */ if (r) break; } } mutex_unlock(&kvm->slots_lock); /* * Ignore the result of kvm_io_bus_unregister_dev(), from userspace's * perspective, the coalesced MMIO is most definitely unregistered. */ return 0; } |
| 30 215 390 264 7 354 94 93 94 98 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/include/asm/kvm_host.h: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_HOST_H__ #define __ARM64_KVM_HOST_H__ #include <linux/arm-smccc.h> #include <linux/bitmap.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kvm_types.h> #include <linux/maple_tree.h> #include <linux/percpu.h> #include <linux/psci.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/vncr_mapping.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED #define KVM_HALT_POLL_NS_DEFAULT 500000 #include <kvm/arm_vgic.h> #include <kvm/arm_arch_timer.h> #include <kvm/arm_pmu.h> #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS #define KVM_VCPU_MAX_FEATURES 9 #define KVM_VCPU_VALID_FEATURES (BIT(KVM_VCPU_MAX_FEATURES) - 1) #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) #define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5) #define KVM_REQ_SUSPEND KVM_ARCH_REQ(6) #define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7) #define KVM_REQ_NESTED_S2_UNMAP KVM_ARCH_REQ(8) #define KVM_REQ_GUEST_HYP_IRQ_PENDING KVM_ARCH_REQ(9) #define KVM_REQ_MAP_L1_VNCR_EL2 KVM_ARCH_REQ(10) #define KVM_REQ_VGIC_PROCESS_UPDATE KVM_ARCH_REQ(11) #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) #define KVM_HAVE_MMU_RWLOCK /* * Mode of operation configurable with kvm-arm.mode early param. * See Documentation/admin-guide/kernel-parameters.txt for more information. */ enum kvm_mode { KVM_MODE_DEFAULT, KVM_MODE_PROTECTED, KVM_MODE_NV, KVM_MODE_NONE, }; #ifdef CONFIG_KVM enum kvm_mode kvm_get_mode(void); #else static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; #endif extern unsigned int __ro_after_init kvm_sve_max_vl; extern unsigned int __ro_after_init kvm_host_sve_max_vl; int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); void kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); struct kvm_hyp_memcache { phys_addr_t head; unsigned long nr_pages; struct pkvm_mapping *mapping; /* only used from EL1 */ #define HYP_MEMCACHE_ACCOUNT_STAGE2 BIT(1) unsigned long flags; }; static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, phys_addr_t *p, phys_addr_t (*to_pa)(void *virt)) { *p = mc->head; mc->head = to_pa(p); mc->nr_pages++; } static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, void *(*to_va)(phys_addr_t phys)) { phys_addr_t *p = to_va(mc->head & PAGE_MASK); if (!mc->nr_pages) return NULL; mc->head = *p; mc->nr_pages--; return p; } static inline int __topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, void *(*alloc_fn)(void *arg), phys_addr_t (*to_pa)(void *virt), void *arg) { while (mc->nr_pages < min_pages) { phys_addr_t *p = alloc_fn(arg); if (!p) return -ENOMEM; push_hyp_memcache(mc, p, to_pa); } return 0; } static inline void __free_hyp_memcache(struct kvm_hyp_memcache *mc, void (*free_fn)(void *virt, void *arg), void *(*to_va)(phys_addr_t phys), void *arg) { while (mc->nr_pages) free_fn(pop_hyp_memcache(mc, to_va), arg); } void free_hyp_memcache(struct kvm_hyp_memcache *mc); int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages); struct kvm_vmid { atomic64_t id; }; struct kvm_s2_mmu { struct kvm_vmid vmid; /* * stage2 entry level table * * Two kvm_s2_mmu structures in the same VM can point to the same * pgd here. This happens when running a guest using a * translation regime that isn't affected by its own stage-2 * translation, such as a non-VHE hypervisor running at vEL2, or * for vEL1/EL0 with vHCR_EL2.VM == 0. In that case, we use the * canonical stage-2 page tables. */ phys_addr_t pgd_phys; struct kvm_pgtable *pgt; /* * VTCR value used on the host. For a non-NV guest (or a NV * guest that runs in a context where its own S2 doesn't * apply), its T0SZ value reflects that of the IPA size. * * For a shadow S2 MMU, T0SZ reflects the PARange exposed to * the guest. */ u64 vtcr; /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; #define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT 0 /* * Memory cache used to split * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It * is used to allocate stage2 page tables while splitting huge * pages. The choice of KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE * influences both the capacity of the split page cache, and * how often KVM reschedules. Be wary of raising CHUNK_SIZE * too high. * * Protected by kvm->slots_lock. */ struct kvm_mmu_memory_cache split_page_cache; uint64_t split_page_chunk_size; struct kvm_arch *arch; /* * For a shadow stage-2 MMU, the virtual vttbr used by the * host to parse the guest S2. * This either contains: * - the virtual VTTBR programmed by the guest hypervisor with * CnP cleared * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid * * We also cache the full VTCR which gets used for TLB invalidation, * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted * to be cached in a TLB" to the letter. */ u64 tlb_vttbr; u64 tlb_vtcr; /* * true when this represents a nested context where virtual * HCR_EL2.VM == 1 */ bool nested_stage2_enabled; #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS struct dentry *shadow_pt_debugfs_dentry; #endif /* * true when this MMU needs to be unmapped before being used for a new * purpose. */ bool pending_unmap; /* * 0: Nobody is currently using this, check vttbr for validity * >0: Somebody is actively using this. */ atomic_t refcnt; }; struct kvm_arch_memory_slot { }; /** * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests * * @std_bmap: Bitmap of standard secure service calls * @std_hyp_bmap: Bitmap of standard hypervisor service calls * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls */ struct kvm_smccc_features { unsigned long std_bmap; unsigned long std_hyp_bmap; unsigned long vendor_hyp_bmap; /* Function numbers 0-63 */ unsigned long vendor_hyp_bmap_2; /* Function numbers 64-127 */ }; typedef u16 pkvm_handle_t; struct kvm_protected_vm { pkvm_handle_t handle; struct kvm_hyp_memcache teardown_mc; struct kvm_hyp_memcache stage2_teardown_mc; bool is_protected; bool is_created; /* * True when the guest is being torn down. When in this state, the * guest's vCPUs can't be loaded anymore, but its pages can be * reclaimed by the host. */ bool is_dying; }; struct kvm_mpidr_data { u64 mpidr_mask; DECLARE_FLEX_ARRAY(u16, cmpidr_to_idx); }; static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr) { unsigned long index = 0, mask = data->mpidr_mask; unsigned long aff = mpidr & MPIDR_HWID_BITMASK; bitmap_gather(&index, &aff, &mask, fls(mask)); return index; } struct kvm_sysreg_masks; enum fgt_group_id { __NO_FGT_GROUP__, HFGRTR_GROUP, HFGWTR_GROUP = HFGRTR_GROUP, HDFGRTR_GROUP, HDFGWTR_GROUP = HDFGRTR_GROUP, HFGITR_GROUP, HAFGRTR_GROUP, HFGRTR2_GROUP, HFGWTR2_GROUP = HFGRTR2_GROUP, HDFGRTR2_GROUP, HDFGWTR2_GROUP = HDFGRTR2_GROUP, HFGITR2_GROUP, ICH_HFGRTR_GROUP, ICH_HFGWTR_GROUP = ICH_HFGRTR_GROUP, ICH_HFGITR_GROUP, /* Must be last */ __NR_FGT_GROUP_IDS__ }; struct kvm_arch { struct kvm_s2_mmu mmu; /* * Fine-Grained UNDEF, mimicking the FGT layout defined by the * architecture. We track them globally, as we present the * same feature-set to all vcpus. * * Index 0 is currently spare. */ u64 fgu[__NR_FGT_GROUP_IDS__]; /* * Stage 2 paging state for VMs with nested S2 using a virtual * VMID. */ struct kvm_s2_mmu *nested_mmus; size_t nested_mmus_size; int nested_mmus_next; /* Interrupt controller */ struct vgic_dist vgic; /* Timers */ struct arch_timer_vm_data timer_data; /* Mandated version of PSCI */ u32 psci_version; /* Protects VM-scoped configuration data */ struct mutex config_lock; /* * If we encounter a data abort without valid instruction syndrome * information, report this to user space. User space can (and * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is * supported. */ #define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER 0 /* Memory Tagging Extension enabled for the guest */ #define KVM_ARCH_FLAG_MTE_ENABLED 1 /* At least one vCPU has ran in the VM */ #define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 /* The vCPU feature set for the VM is configured */ #define KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED 3 /* PSCI SYSTEM_SUSPEND enabled for the guest */ #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 4 /* VM counter offset */ #define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 5 /* Timer PPIs made immutable */ #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 6 /* Initial ID reg values loaded */ #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7 /* Fine-Grained UNDEF initialised */ #define KVM_ARCH_FLAG_FGU_INITIALIZED 8 /* SVE exposed to guest */ #define KVM_ARCH_FLAG_GUEST_HAS_SVE 9 /* MIDR_EL1, REVIDR_EL1, and AIDR_EL1 are writable from userspace */ #define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS 10 /* Unhandled SEAs are taken to userspace */ #define KVM_ARCH_FLAG_EXIT_SEA 11 unsigned long flags; /* VM-wide vCPU feature set */ DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES); /* MPIDR to vcpu index mapping, optional */ struct kvm_mpidr_data *mpidr_data; /* * VM-wide PMU filter, implemented as a bitmap and big enough for * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+). */ unsigned long *pmu_filter; struct arm_pmu *arm_pmu; cpumask_var_t supported_cpus; /* Maximum number of counters for the guest */ u8 nr_pmu_counters; /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; struct maple_tree smccc_filter; /* * Emulated CPU ID registers per VM * (Op0, Op1, CRn, CRm, Op2) of the ID registers to be saved in it * is (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8. * * These emulated idregs are VM-wide, but accessed from the context of a vCPU. * Atomic access to multiple idregs are guarded by kvm_arch.config_lock. */ #define IDREG_IDX(id) (((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id)) #define KVM_ARM_ID_REG_NUM (IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1) u64 id_regs[KVM_ARM_ID_REG_NUM]; u64 midr_el1; u64 revidr_el1; u64 aidr_el1; u64 ctr_el0; /* Masks for VNCR-backed and general EL2 sysregs */ struct kvm_sysreg_masks *sysreg_masks; /* Count the number of VNCR_EL2 currently mapped */ atomic_t vncr_map_count; /* * For an untrusted host VM, 'pkvm.handle' is used to lookup * the associated pKVM instance in the hypervisor. */ struct kvm_protected_vm pkvm; #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS /* Nested virtualization info */ struct dentry *debugfs_nv_dentry; #endif }; struct kvm_vcpu_fault_info { u64 esr_el2; /* Hyp Syndrom Register */ u64 far_el2; /* Hyp Fault Address Register */ u64 hpfar_el2; /* Hyp IPA Fault Address Register */ u64 disr_el1; /* Deferred [SError] Status Register */ }; /* * VNCR() just places the VNCR_capable registers in the enum after * __VNCR_START__, and the value (after correction) to be an 8-byte offset * from the VNCR base. As we don't require the enum to be otherwise ordered, * we need the terrible hack below to ensure that we correctly size the * sys_regs array, no matter what. * * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful * treasure trove of bit hacks: * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax */ #define __MAX__(x,y) ((x) ^ (((x) ^ (y)) & -((x) < (y)))) #define VNCR(r) \ __before_##r, \ r = __VNCR_START__ + ((VNCR_ ## r) / 8), \ __after_##r = __MAX__(__before_##r - 1, r) #define MARKER(m) \ m, __after_##m = m - 1 enum vcpu_sysreg { __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ CLIDR_EL1, /* Cache Level ID Register */ CSSELR_EL1, /* Cache Size Selection Register */ TPIDR_EL0, /* Thread ID, User R/W */ TPIDRRO_EL0, /* Thread ID, User R/O */ TPIDR_EL1, /* Thread ID, Privileged */ CNTKCTL_EL1, /* Timer Control Register (EL1) */ PAR_EL1, /* Physical Address Register */ MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */ OSLSR_EL1, /* OS Lock Status Register */ DISR_EL1, /* Deferred Interrupt Status Register */ /* Performance Monitors Registers */ PMCR_EL0, /* Control Register */ PMSELR_EL0, /* Event Counter Selection Register */ PMEVCNTR0_EL0, /* Event Counter Register (0-30) */ PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30, PMCCNTR_EL0, /* Cycle Counter Register */ PMEVTYPER0_EL0, /* Event Type Register (0-30) */ PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30, PMCCFILTR_EL0, /* Cycle Count Filter Register */ PMCNTENSET_EL0, /* Count Enable Set Register */ PMINTENSET_EL1, /* Interrupt Enable Set Register */ PMOVSSET_EL0, /* Overflow Flag Status Set Register */ PMUSERENR_EL0, /* User Enable Register */ /* Pointer Authentication Registers in a strict increasing order. */ APIAKEYLO_EL1, APIAKEYHI_EL1, APIBKEYLO_EL1, APIBKEYHI_EL1, APDAKEYLO_EL1, APDAKEYHI_EL1, APDBKEYLO_EL1, APDBKEYHI_EL1, APGAKEYLO_EL1, APGAKEYHI_EL1, /* Memory Tagging Extension registers */ RGSR_EL1, /* Random Allocation Tag Seed Register */ GCR_EL1, /* Tag Control Register */ TFSRE0_EL1, /* Tag Fault Status Register (EL0) */ POR_EL0, /* Permission Overlay Register 0 (EL0) */ /* FP/SIMD/SVE */ SVCR, FPMR, /* 32bit specific registers. */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ FPEXC32_EL2, /* Floating-Point Exception Control Register */ DBGVCR32_EL2, /* Debug Vector Catch Register */ /* EL2 registers */ ACTLR_EL2, /* Auxiliary Control Register (EL2) */ CPTR_EL2, /* Architectural Feature Trap Register (EL2) */ HACR_EL2, /* Hypervisor Auxiliary Control Register */ ZCR_EL2, /* SVE Control Register (EL2) */ TTBR0_EL2, /* Translation Table Base Register 0 (EL2) */ TTBR1_EL2, /* Translation Table Base Register 1 (EL2) */ TCR_EL2, /* Translation Control Register (EL2) */ PIRE0_EL2, /* Permission Indirection Register 0 (EL2) */ PIR_EL2, /* Permission Indirection Register 1 (EL2) */ POR_EL2, /* Permission Overlay Register 2 (EL2) */ SPSR_EL2, /* EL2 saved program status register */ ELR_EL2, /* EL2 exception link register */ AFSR0_EL2, /* Auxiliary Fault Status Register 0 (EL2) */ AFSR1_EL2, /* Auxiliary Fault Status Register 1 (EL2) */ ESR_EL2, /* Exception Syndrome Register (EL2) */ FAR_EL2, /* Fault Address Register (EL2) */ HPFAR_EL2, /* Hypervisor IPA Fault Address Register */ MAIR_EL2, /* Memory Attribute Indirection Register (EL2) */ AMAIR_EL2, /* Auxiliary Memory Attribute Indirection Register (EL2) */ VBAR_EL2, /* Vector Base Address Register (EL2) */ RVBAR_EL2, /* Reset Vector Base Address Register */ CONTEXTIDR_EL2, /* Context ID Register (EL2) */ SP_EL2, /* EL2 Stack Pointer */ CNTHP_CTL_EL2, CNTHP_CVAL_EL2, CNTHV_CTL_EL2, CNTHV_CVAL_EL2, /* Anything from this can be RES0/RES1 sanitised */ MARKER(__SANITISED_REG_START__), SCTLR_EL2, /* System Control Register (EL2) */ TCR2_EL2, /* Extended Translation Control Register (EL2) */ SCTLR2_EL2, /* System Control Register 2 (EL2) */ MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ /* Any VNCR-capable reg goes after this point */ MARKER(__VNCR_START__), VNCR(SCTLR_EL1),/* System Control Register */ VNCR(ACTLR_EL1),/* Auxiliary Control Register */ VNCR(CPACR_EL1),/* Coprocessor Access Control */ VNCR(ZCR_EL1), /* SVE Control */ VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */ VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */ VNCR(TCR_EL1), /* Translation Control Register */ VNCR(TCR2_EL1), /* Extended Translation Control Register */ VNCR(SCTLR2_EL1), /* System Control Register 2 */ VNCR(ESR_EL1), /* Exception Syndrome Register */ VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */ VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */ VNCR(FAR_EL1), /* Fault Address Register */ VNCR(MAIR_EL1), /* Memory Attribute Indirection Register */ VNCR(VBAR_EL1), /* Vector Base Address Register */ VNCR(CONTEXTIDR_EL1), /* Context ID Register */ VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */ VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */ VNCR(ELR_EL1), VNCR(SP_EL1), VNCR(SPSR_EL1), VNCR(TFSR_EL1), /* Tag Fault Status Register (EL1) */ VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */ VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */ VNCR(HCR_EL2), /* Hypervisor Configuration Register */ VNCR(HSTR_EL2), /* Hypervisor System Trap Register */ VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */ VNCR(VTCR_EL2), /* Virtualization Translation Control Register */ VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */ VNCR(HCRX_EL2), /* Extended Hypervisor Configuration Register */ /* Permission Indirection Extension registers */ VNCR(PIR_EL1), /* Permission Indirection Register 1 (EL1) */ VNCR(PIRE0_EL1), /* Permission Indirection Register 0 (EL1) */ VNCR(POR_EL1), /* Permission Overlay Register 1 (EL1) */ /* FEAT_RAS registers */ VNCR(VDISR_EL2), VNCR(VSESR_EL2), VNCR(HFGRTR_EL2), VNCR(HFGWTR_EL2), VNCR(HFGITR_EL2), VNCR(HDFGRTR_EL2), VNCR(HDFGWTR_EL2), VNCR(HAFGRTR_EL2), VNCR(HFGRTR2_EL2), VNCR(HFGWTR2_EL2), VNCR(HFGITR2_EL2), VNCR(HDFGRTR2_EL2), VNCR(HDFGWTR2_EL2), VNCR(VNCR_EL2), VNCR(CNTVOFF_EL2), VNCR(CNTV_CVAL_EL0), VNCR(CNTV_CTL_EL0), VNCR(CNTP_CVAL_EL0), VNCR(CNTP_CTL_EL0), VNCR(ICH_LR0_EL2), VNCR(ICH_LR1_EL2), VNCR(ICH_LR2_EL2), VNCR(ICH_LR3_EL2), VNCR(ICH_LR4_EL2), VNCR(ICH_LR5_EL2), VNCR(ICH_LR6_EL2), VNCR(ICH_LR7_EL2), VNCR(ICH_LR8_EL2), VNCR(ICH_LR9_EL2), VNCR(ICH_LR10_EL2), VNCR(ICH_LR11_EL2), VNCR(ICH_LR12_EL2), VNCR(ICH_LR13_EL2), VNCR(ICH_LR14_EL2), VNCR(ICH_LR15_EL2), VNCR(ICH_AP0R0_EL2), VNCR(ICH_AP0R1_EL2), VNCR(ICH_AP0R2_EL2), VNCR(ICH_AP0R3_EL2), VNCR(ICH_AP1R0_EL2), VNCR(ICH_AP1R1_EL2), VNCR(ICH_AP1R2_EL2), VNCR(ICH_AP1R3_EL2), VNCR(ICH_HCR_EL2), VNCR(ICH_VMCR_EL2), VNCR(ICH_HFGRTR_EL2), VNCR(ICH_HFGWTR_EL2), VNCR(ICH_HFGITR_EL2), NR_SYS_REGS /* Nothing after this line! */ }; struct resx { u64 res0; u64 res1; }; struct kvm_sysreg_masks { struct resx mask[NR_SYS_REGS - __SANITISED_REG_START__]; }; static inline struct resx __kvm_get_sysreg_resx(struct kvm_arch *arch, enum vcpu_sysreg sr) { struct kvm_sysreg_masks *masks; masks = arch->sysreg_masks; if (likely(masks && sr >= __SANITISED_REG_START__ && sr < NR_SYS_REGS)) return masks->mask[sr - __SANITISED_REG_START__]; return (struct resx){}; } #define kvm_get_sysreg_resx(k, sr) __kvm_get_sysreg_resx(&(k)->arch, (sr)) static inline void __kvm_set_sysreg_resx(struct kvm_arch *arch, enum vcpu_sysreg sr, struct resx resx) { arch->sysreg_masks->mask[sr - __SANITISED_REG_START__] = resx; } #define kvm_set_sysreg_resx(k, sr, resx) \ __kvm_set_sysreg_resx(&(k)->arch, (sr), (resx)) struct fgt_masks { const char *str; u64 mask; u64 nmask; u64 res0; u64 res1; }; extern struct fgt_masks hfgrtr_masks; extern struct fgt_masks hfgwtr_masks; extern struct fgt_masks hfgitr_masks; extern struct fgt_masks hdfgrtr_masks; extern struct fgt_masks hdfgwtr_masks; extern struct fgt_masks hafgrtr_masks; extern struct fgt_masks hfgrtr2_masks; extern struct fgt_masks hfgwtr2_masks; extern struct fgt_masks hfgitr2_masks; extern struct fgt_masks hdfgrtr2_masks; extern struct fgt_masks hdfgwtr2_masks; extern struct fgt_masks ich_hfgrtr_masks; extern struct fgt_masks ich_hfgwtr_masks; extern struct fgt_masks ich_hfgitr_masks; extern struct fgt_masks kvm_nvhe_sym(hfgrtr_masks); extern struct fgt_masks kvm_nvhe_sym(hfgwtr_masks); extern struct fgt_masks kvm_nvhe_sym(hfgitr_masks); extern struct fgt_masks kvm_nvhe_sym(hdfgrtr_masks); extern struct fgt_masks kvm_nvhe_sym(hdfgwtr_masks); extern struct fgt_masks kvm_nvhe_sym(hafgrtr_masks); extern struct fgt_masks kvm_nvhe_sym(hfgrtr2_masks); extern struct fgt_masks kvm_nvhe_sym(hfgwtr2_masks); extern struct fgt_masks kvm_nvhe_sym(hfgitr2_masks); extern struct fgt_masks kvm_nvhe_sym(hdfgrtr2_masks); extern struct fgt_masks kvm_nvhe_sym(hdfgwtr2_masks); extern struct fgt_masks kvm_nvhe_sym(ich_hfgrtr_masks); extern struct fgt_masks kvm_nvhe_sym(ich_hfgwtr_masks); extern struct fgt_masks kvm_nvhe_sym(ich_hfgitr_masks); struct kvm_cpu_context { struct user_pt_regs regs; /* sp = sp_el0 */ u64 spsr_abt; u64 spsr_und; u64 spsr_irq; u64 spsr_fiq; struct user_fpsimd_state fp_regs; u64 sys_regs[NR_SYS_REGS]; struct kvm_vcpu *__hyp_running_vcpu; /* This pointer has to be 4kB aligned. */ u64 *vncr_array; }; struct cpu_sve_state { __u64 zcr_el1; /* * Ordering is important since __sve_save_state/__sve_restore_state * relies on it. */ __u32 fpsr; __u32 fpcr; /* Must be SVE_VQ_BYTES (128 bit) aligned. */ __u8 sve_regs[]; }; /* * This structure is instantiated on a per-CPU basis, and contains * data that is: * * - tied to a single physical CPU, and * - either have a lifetime that does not extend past vcpu_put() * - or is an invariant for the lifetime of the system * * Use host_data_ptr(field) as a way to access a pointer to such a * field. */ struct kvm_host_data { #define KVM_HOST_DATA_FLAG_HAS_SPE 0 #define KVM_HOST_DATA_FLAG_HAS_TRBE 1 #define KVM_HOST_DATA_FLAG_TRBE_ENABLED 2 #define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 3 #define KVM_HOST_DATA_FLAG_VCPU_IN_HYP_CONTEXT 4 #define KVM_HOST_DATA_FLAG_L1_VNCR_MAPPED 5 #define KVM_HOST_DATA_FLAG_HAS_BRBE 6 unsigned long flags; struct kvm_cpu_context host_ctxt; /* * Hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ struct cpu_sve_state *sve_state; /* Used by pKVM only. */ u64 fpmr; /* Ownership of the FP regs */ enum { FP_STATE_FREE, FP_STATE_HOST_OWNED, FP_STATE_GUEST_OWNED, } fp_owner; /* * host_debug_state contains the host registers which are * saved and restored during world switches. */ struct { /* {Break,watch}point registers */ struct kvm_guest_debug_arch regs; /* Statistical profiling extension */ u64 pmscr_el1; u64 pmblimitr_el1; /* Self-hosted trace */ u64 trfcr_el1; u64 trblimitr_el1; /* Values of trap registers for the host before guest entry. */ u64 mdcr_el2; u64 brbcr_el1; } host_debug_state; /* Guest trace filter value */ u64 trfcr_while_in_guest; /* Number of programmable event counters (PMCR_EL0.N) for this CPU */ unsigned int nr_event_counters; /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */ unsigned int debug_brps; unsigned int debug_wrps; /* Last vgic_irq part of the AP list recorded in an LR */ struct vgic_irq *last_lr_irq; /* PPI state tracking for GICv5-based guests */ struct { DECLARE_BITMAP(pendr, VGIC_V5_NR_PRIVATE_IRQS); /* The saved state of the regs when leaving the guest */ DECLARE_BITMAP(activer_exit, VGIC_V5_NR_PRIVATE_IRQS); } vgic_v5_ppi_state; }; struct kvm_host_psci_config { /* PSCI version used by host. */ u32 version; u32 smccc_version; /* Function IDs used by host if version is v0.1. */ struct psci_0_1_function_ids function_ids_0_1; bool psci_0_1_cpu_suspend_implemented; bool psci_0_1_cpu_on_implemented; bool psci_0_1_cpu_off_implemented; bool psci_0_1_migrate_implemented; }; extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config); #define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config) extern s64 kvm_nvhe_sym(hyp_physvirt_offset); #define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset) extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS]; #define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map) struct vcpu_reset_state { unsigned long pc; unsigned long r0; bool be; bool reset; }; struct vncr_tlb; struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; /* * Guest floating point state * * The architecture has two main floating point extensions, * the original FPSIMD and SVE. These have overlapping * register views, with the FPSIMD V registers occupying the * low 128 bits of the SVE Z registers. When the core * floating point code saves the register state of a task it * records which view it saved in fp_type. */ void *sve_state; enum fp_type fp_type; unsigned int sve_max_vl; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; /* Values of trap registers for the guest. */ u64 hcr_el2; u64 hcrx_el2; u64 mdcr_el2; struct { u64 r; u64 w; } fgt[__NR_FGT_GROUP_IDS__]; /* Exception Information */ struct kvm_vcpu_fault_info fault; /* Configuration flags, set once and for all before the vcpu can run */ u8 cflags; /* Input flags to the hypervisor code, potentially cleared after use */ u8 iflags; /* State flags for kernel bookkeeping, unused by the hypervisor code */ u16 sflags; /* * Don't run the guest (internal implementation need). * * Contrary to the flags above, this is set/cleared outside of * a vcpu context, and thus cannot be mixed with the flags * themselves (or the flag accesses need to be made atomic). */ bool pause; /* * We maintain more than a single set of debug registers to support * debugging the guest from the host and to maintain separate host and * guest state during world switches. vcpu_debug_state are the debug * registers of the vcpu as the guest sees them. * * external_debug_state contains the debug values we want to debug the * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl. */ struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; u64 external_mdscr_el1; enum { VCPU_DEBUG_FREE, VCPU_DEBUG_HOST_OWNED, VCPU_DEBUG_GUEST_OWNED, } debug_owner; /* VGIC state */ struct vgic_cpu vgic_cpu; struct arch_timer_cpu timer_cpu; struct kvm_pmu pmu; /* vcpu power state */ struct kvm_mp_state mp_state; spinlock_t mp_state_lock; /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; /* Pages to top-up the pKVM/EL2 guest pool */ struct kvm_hyp_memcache pkvm_memcache; /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; /* Additional reset state */ struct vcpu_reset_state reset_state; /* Guest PV state */ struct { u64 last_steal; gpa_t base; } steal; /* Per-vcpu CCSIDR override or NULL */ u32 *ccsidr; /* Per-vcpu TLB for VNCR_EL2 -- NULL when !NV */ struct vncr_tlb *vncr_tlb; /* Hyp-readable copy of kvm_vcpu::pid */ pid_t pid; }; /* * Each 'flag' is composed of a comma-separated triplet: * * - the flag-set it belongs to in the vcpu->arch structure * - the value for that flag * - the mask for that flag * * __vcpu_single_flag() builds such a triplet for a single-bit flag. * unpack_vcpu_flag() extract the flag value from the triplet for * direct use outside of the flag accessors. */ #define __vcpu_single_flag(_set, _f) _set, (_f), (_f) #define __unpack_flag(_set, _f, _m) _f #define unpack_vcpu_flag(...) __unpack_flag(__VA_ARGS__) #define __build_check_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *_fset; \ \ /* Check that the flags fit in the mask */ \ BUILD_BUG_ON(HWEIGHT(m) != HWEIGHT((f) | (m))); \ /* Check that the flags fit in the type */ \ BUILD_BUG_ON((sizeof(*_fset) * 8) <= __fls(m)); \ } while (0) #define __vcpu_get_flag(v, flagset, f, m) \ ({ \ __build_check_flag(v, flagset, f, m); \ \ READ_ONCE(v->arch.flagset) & (m); \ }) /* * Note that the set/clear accessors must be preempt-safe in order to * avoid nesting them with load/put which also manipulate flags... */ #ifdef __KVM_NVHE_HYPERVISOR__ /* the nVHE hypervisor is always non-preemptible */ #define __vcpu_flags_preempt_disable() #define __vcpu_flags_preempt_enable() #else #define __vcpu_flags_preempt_disable() preempt_disable() #define __vcpu_flags_preempt_enable() preempt_enable() #endif #define __vcpu_set_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *fset; \ \ __build_check_flag(v, flagset, f, m); \ \ fset = &v->arch.flagset; \ __vcpu_flags_preempt_disable(); \ if (HWEIGHT(m) > 1) \ *fset &= ~(m); \ *fset |= (f); \ __vcpu_flags_preempt_enable(); \ } while (0) #define __vcpu_clear_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *fset; \ \ __build_check_flag(v, flagset, f, m); \ \ fset = &v->arch.flagset; \ __vcpu_flags_preempt_disable(); \ *fset &= ~(m); \ __vcpu_flags_preempt_enable(); \ } while (0) #define __vcpu_test_and_clear_flag(v, flagset, f, m) \ ({ \ typeof(v->arch.flagset) set; \ \ set = __vcpu_get_flag(v, flagset, f, m); \ __vcpu_clear_flag(v, flagset, f, m); \ \ set; \ }) #define vcpu_get_flag(v, ...) __vcpu_get_flag((v), __VA_ARGS__) #define vcpu_set_flag(v, ...) __vcpu_set_flag((v), __VA_ARGS__) #define vcpu_clear_flag(v, ...) __vcpu_clear_flag((v), __VA_ARGS__) #define vcpu_test_and_clear_flag(v, ...) \ __vcpu_test_and_clear_flag((v), __VA_ARGS__) /* KVM_ARM_VCPU_INIT completed */ #define VCPU_INITIALIZED __vcpu_single_flag(cflags, BIT(0)) /* SVE config completed */ #define VCPU_SVE_FINALIZED __vcpu_single_flag(cflags, BIT(1)) /* pKVM VCPU setup completed */ #define VCPU_PKVM_FINALIZED __vcpu_single_flag(cflags, BIT(2)) /* Exception pending */ #define PENDING_EXCEPTION __vcpu_single_flag(iflags, BIT(0)) /* * PC increment. Overlaps with EXCEPT_MASK on purpose so that it can't * be set together with an exception... */ #define INCREMENT_PC __vcpu_single_flag(iflags, BIT(1)) /* Target EL/MODE (not a single flag, but let's abuse the macro) */ #define EXCEPT_MASK __vcpu_single_flag(iflags, GENMASK(3, 1)) /* Helpers to encode exceptions with minimum fuss */ #define __EXCEPT_MASK_VAL unpack_vcpu_flag(EXCEPT_MASK) #define __EXCEPT_SHIFT __builtin_ctzl(__EXCEPT_MASK_VAL) #define __vcpu_except_flags(_f) iflags, (_f << __EXCEPT_SHIFT), __EXCEPT_MASK_VAL /* * When PENDING_EXCEPTION is set, EXCEPT_MASK can take the following * values: * * For AArch32 EL1: */ #define EXCEPT_AA32_UND __vcpu_except_flags(0) #define EXCEPT_AA32_IABT __vcpu_except_flags(1) #define EXCEPT_AA32_DABT __vcpu_except_flags(2) /* For AArch64: */ #define EXCEPT_AA64_EL1_SYNC __vcpu_except_flags(0) #define EXCEPT_AA64_EL1_IRQ __vcpu_except_flags(1) #define EXCEPT_AA64_EL1_FIQ __vcpu_except_flags(2) #define EXCEPT_AA64_EL1_SERR __vcpu_except_flags(3) /* For AArch64 with NV: */ #define EXCEPT_AA64_EL2_SYNC __vcpu_except_flags(4) #define EXCEPT_AA64_EL2_IRQ __vcpu_except_flags(5) #define EXCEPT_AA64_EL2_FIQ __vcpu_except_flags(6) #define EXCEPT_AA64_EL2_SERR __vcpu_except_flags(7) /* Physical CPU not in supported_cpus */ #define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(0)) /* WFIT instruction trapped */ #define IN_WFIT __vcpu_single_flag(sflags, BIT(1)) /* vcpu system registers loaded on physical CPU */ #define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(2)) /* Software step state is Active-pending for external debug */ #define HOST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(3)) /* Software step state is Active pending for guest debug */ #define GUEST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(4)) /* PMUSERENR for the guest EL0 is on physical CPU */ #define PMUSERENR_ON_CPU __vcpu_single_flag(sflags, BIT(5)) /* WFI instruction trapped */ #define IN_WFI __vcpu_single_flag(sflags, BIT(6)) /* KVM is currently emulating a nested ERET */ #define IN_NESTED_ERET __vcpu_single_flag(sflags, BIT(7)) /* SError pending for nested guest */ #define NESTED_SERROR_PENDING __vcpu_single_flag(sflags, BIT(8)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) + \ sve_ffr_offset((vcpu)->arch.sve_max_vl)) #define vcpu_sve_max_vq(vcpu) sve_vq_from_vl((vcpu)->arch.sve_max_vl) #define vcpu_sve_zcr_elx(vcpu) \ (unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1) #define sve_state_size_from_vl(sve_max_vl) ({ \ size_t __size_ret; \ unsigned int __vq; \ \ if (WARN_ON(!sve_vl_valid(sve_max_vl))) { \ __size_ret = 0; \ } else { \ __vq = sve_vq_from_vl(sve_max_vl); \ __size_ret = SVE_SIG_REGS_SIZE(__vq); \ } \ \ __size_ret; \ }) #define vcpu_sve_state_size(vcpu) sve_state_size_from_vl((vcpu)->arch.sve_max_vl) #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_USE_HW | \ KVM_GUESTDBG_SINGLESTEP) #define kvm_has_sve(kvm) (system_supports_sve() && \ test_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &(kvm)->arch.flags)) #ifdef __KVM_NVHE_HYPERVISOR__ #define vcpu_has_sve(vcpu) kvm_has_sve(kern_hyp_va((vcpu)->kvm)) #else #define vcpu_has_sve(vcpu) kvm_has_sve((vcpu)->kvm) #endif #ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && \ (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || \ vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC))) #else #define vcpu_has_ptrauth(vcpu) false #endif #define vcpu_on_unsupported_cpu(vcpu) \ vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_set_on_unsupported_cpu(vcpu) \ vcpu_set_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_clear_on_unsupported_cpu(vcpu) \ vcpu_clear_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_gp_regs(v) (&(v)->arch.ctxt.regs) /* * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the * memory backed version of a register, and not the one most recently * accessed by a running VCPU. For example, for userspace access or * for system registers that are never context switched, but only * emulated. * * Don't bother with VNCR-based accesses in the nVHE code, it has no * business dealing with NV. */ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) { #if !defined (__KVM_NVHE_HYPERVISOR__) if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && r >= __VNCR_START__ && ctxt->vncr_array)) return &ctxt->vncr_array[r - __VNCR_START__]; #endif return (u64 *)&ctxt->sys_regs[r]; } #define __ctxt_sys_reg(c,r) \ ({ \ BUILD_BUG_ON(__builtin_constant_p(r) && \ (r) >= NR_SYS_REGS); \ ___ctxt_sys_reg(c, r); \ }) #define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64); #define __vcpu_assign_sys_reg(v, r, val) \ do { \ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ u64 __v = (val); \ if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \ __v = kvm_vcpu_apply_reg_masks((v), (r), __v); \ \ ctxt_sys_reg(ctxt, (r)) = __v; \ } while (0) #define __vcpu_rmw_sys_reg(v, r, op, val) \ do { \ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ u64 __v = ctxt_sys_reg(ctxt, (r)); \ __v op (val); \ if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \ __v = kvm_vcpu_apply_reg_masks((v), (r), __v); \ \ ctxt_sys_reg(ctxt, (r)) = __v; \ } while (0) #define __vcpu_sys_reg(v,r) \ ({ \ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ u64 __v = ctxt_sys_reg(ctxt, (r)); \ if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \ __v = kvm_vcpu_apply_reg_masks((v), (r), __v); \ __v; \ }) u64 vcpu_read_sys_reg(const struct kvm_vcpu *, enum vcpu_sysreg); void vcpu_write_sys_reg(struct kvm_vcpu *, u64, enum vcpu_sysreg); struct kvm_vm_stat { struct kvm_vm_stat_generic generic; }; struct kvm_vcpu_stat { struct kvm_vcpu_stat_generic generic; u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; u64 mmio_exit_kernel; u64 signal_exits; u64 exits; }; unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); #define vcpu_has_run_once(vcpu) (!!READ_ONCE((vcpu)->pid)) #ifndef __KVM_NVHE_HYPERVISOR__ #define kvm_call_hyp_nvhe(f, ...) \ ({ \ struct arm_smccc_res res; \ \ arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(f), \ ##__VA_ARGS__, &res); \ WARN_ON(res.a0 != SMCCC_RET_SUCCESS); \ \ res.a1; \ }) /* * The isb() below is there to guarantee the same behaviour on VHE as on !VHE, * where the eret to EL1 acts as a context synchronization event. */ #define kvm_call_hyp(f, ...) \ do { \ if (has_vhe()) { \ f(__VA_ARGS__); \ isb(); \ } else { \ kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ } while(0) #define kvm_call_hyp_ret(f, ...) \ ({ \ typeof(f(__VA_ARGS__)) ret; \ \ if (has_vhe()) { \ ret = f(__VA_ARGS__); \ } else { \ ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ \ ret; \ }) #else /* __KVM_NVHE_HYPERVISOR__ */ #define kvm_call_hyp(f, ...) f(__VA_ARGS__) #define kvm_call_hyp_ret(f, ...) f(__VA_ARGS__) #define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__) #endif /* __KVM_NVHE_HYPERVISOR__ */ int handle_exit(struct kvm_vcpu *vcpu, int exception_index); void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index); int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu); int kvm_handle_cp14_32(struct kvm_vcpu *vcpu); int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_sys_regs_create_debugfs(struct kvm *kvm); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); int __init kvm_sys_reg_table_init(void); struct sys_reg_desc; int __init populate_sysreg_config(const struct sys_reg_desc *sr, unsigned int idx); int __init populate_nv_trap_config(void); void kvm_calculate_traps(struct kvm_vcpu *vcpu); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); int kvm_handle_mmio_return(struct kvm_vcpu *vcpu); int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa); /* * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, * arrived in guest context. For arm64, any event that arrives while a vCPU is * loaded is considered to be "in guest". */ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) { return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); void kvm_update_stolen_time(struct kvm_vcpu *vcpu); bool kvm_arm_pvtime_supported(void); int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); extern unsigned int __ro_after_init kvm_arm_vmid_bits; int __init kvm_arm_vmid_alloc_init(void); void __init kvm_arm_vmid_alloc_free(void); void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); void kvm_arm_vmid_clear_active(void); static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) { vcpu_arch->steal.base = INVALID_GPA; } static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) { return (vcpu_arch->steal.base != INVALID_GPA); } struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data); /* * How we access per-CPU host data depends on the where we access it from, * and the mode we're in: * * - VHE and nVHE hypervisor bits use their locally defined instance * * - the rest of the kernel use either the VHE or nVHE one, depending on * the mode we're running in. * * Unless we're in protected mode, fully deprivileged, and the nVHE * per-CPU stuff is exclusively accessible to the protected EL2 code. * In this case, the EL1 code uses the *VHE* data as its private state * (which makes sense in a way as there shouldn't be any shared state * between the host and the hypervisor). * * Yes, this is all totally trivial. Shoot me now. */ #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) #define host_data_ptr(f) (&this_cpu_ptr(&kvm_host_data)->f) #else #define host_data_ptr(f) \ (static_branch_unlikely(&kvm_protected_mode_initialized) ? \ &this_cpu_ptr(&kvm_host_data)->f : \ &this_cpu_ptr_hyp_sym(kvm_host_data)->f) #endif #define host_data_test_flag(flag) \ (test_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))) #define host_data_set_flag(flag) \ set_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) #define host_data_clear_flag(flag) \ clear_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) /* Check whether the FP regs are owned by the guest */ static inline bool guest_owns_fp_regs(void) { return *host_data_ptr(fp_owner) == FP_STATE_GUEST_OWNED; } /* Check whether the FP regs are owned by the host */ static inline bool host_owns_fp_regs(void) { return *host_data_ptr(fp_owner) == FP_STATE_HOST_OWNED; } static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } static inline bool kvm_system_needs_idmapped_vectors(void) { return cpus_have_final_cap(ARM64_SPECTRE_V3A); } void kvm_init_host_debug_data(void); void kvm_debug_init_vhe(void); void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu); void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu); void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu); void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val); #define kvm_vcpu_os_lock_enabled(vcpu) \ (!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK)) #define kvm_debug_regs_in_use(vcpu) \ ((vcpu)->arch.debug_owner != VCPU_DEBUG_FREE) #define kvm_host_owns_debug_regs(vcpu) \ ((vcpu)->arch.debug_owner == VCPU_DEBUG_HOST_OWNED) #define kvm_guest_owns_debug_regs(vcpu) \ ((vcpu)->arch.debug_owner == VCPU_DEBUG_GUEST_OWNED) int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, struct kvm_arm_counter_offset *offset); int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range); /* Guest/host FPSIMD coordination helpers */ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) { return (!has_vhe() && attr->exclude_host); } #ifdef CONFIG_KVM void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u64 clr); bool kvm_set_pmuserenr(u64 val); void kvm_enable_trbe(void); void kvm_disable_trbe(void); void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest); #else static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u64 clr) {} static inline bool kvm_set_pmuserenr(u64 val) { return false; } static inline void kvm_enable_trbe(void) {} static inline void kvm_disable_trbe(void) {} static inline void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) {} #endif void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu); void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu); int __init kvm_set_ipa_limit(void); u32 kvm_get_pa_bits(struct kvm *kvm); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE #define kvm_vm_is_protected(kvm) (is_protected_kvm_enabled() && (kvm)->arch.pkvm.is_protected) #define vcpu_is_protected(vcpu) kvm_vm_is_protected((vcpu)->kvm) int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED) #define kvm_has_mte(kvm) \ (system_supports_mte() && \ test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags)) #define kvm_supports_32bit_el0() \ (system_supports_32bit_el0() && \ !static_branch_unlikely(&arm64_mismatched_32bit_el0)) #define kvm_vm_has_ran_once(kvm) \ (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags)) static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature) { return test_bit(feature, ka->vcpu_features); } #define kvm_vcpu_has_feature(k, f) __vcpu_has_feature(&(k)->arch, (f)) #define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f)) #define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED) int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM extern phys_addr_t hyp_mem_base; extern phys_addr_t hyp_mem_size; void __init kvm_hyp_reserve(void); #else static inline void kvm_hyp_reserve(void) { } #endif void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); static inline u64 *__vm_id_reg(struct kvm_arch *ka, u32 reg) { switch (reg) { case sys_reg(3, 0, 0, 1, 0) ... sys_reg(3, 0, 0, 7, 7): return &ka->id_regs[IDREG_IDX(reg)]; case SYS_CTR_EL0: return &ka->ctr_el0; case SYS_MIDR_EL1: return &ka->midr_el1; case SYS_REVIDR_EL1: return &ka->revidr_el1; case SYS_AIDR_EL1: return &ka->aidr_el1; default: WARN_ON_ONCE(1); return NULL; } } #define kvm_read_vm_id_reg(kvm, reg) \ ({ u64 __val = *__vm_id_reg(&(kvm)->arch, reg); __val; }) void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); #define __expand_field_sign_unsigned(id, fld, val) \ ((u64)SYS_FIELD_VALUE(id, fld, val)) #define __expand_field_sign_signed(id, fld, val) \ ({ \ u64 __val = SYS_FIELD_VALUE(id, fld, val); \ sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) #define get_idreg_field_unsigned(kvm, id, fld) \ ({ \ u64 __val = kvm_read_vm_id_reg((kvm), SYS_##id); \ FIELD_GET(id##_##fld##_MASK, __val); \ }) #define get_idreg_field_signed(kvm, id, fld) \ ({ \ u64 __val = get_idreg_field_unsigned(kvm, id, fld); \ sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) #define get_idreg_field_enum(kvm, id, fld) \ get_idreg_field_unsigned(kvm, id, fld) #define kvm_cmp_feat_signed(kvm, id, fld, op, limit) \ (get_idreg_field_signed((kvm), id, fld) op __expand_field_sign_signed(id, fld, limit)) #define kvm_cmp_feat_unsigned(kvm, id, fld, op, limit) \ (get_idreg_field_unsigned((kvm), id, fld) op __expand_field_sign_unsigned(id, fld, limit)) #define kvm_cmp_feat(kvm, id, fld, op, limit) \ (id##_##fld##_SIGNED ? \ kvm_cmp_feat_signed(kvm, id, fld, op, limit) : \ kvm_cmp_feat_unsigned(kvm, id, fld, op, limit)) #define __kvm_has_feat(kvm, id, fld, limit) \ kvm_cmp_feat(kvm, id, fld, >=, limit) #define kvm_has_feat(kvm, ...) __kvm_has_feat(kvm, __VA_ARGS__) #define __kvm_has_feat_enum(kvm, id, fld, val) \ kvm_cmp_feat_unsigned(kvm, id, fld, ==, val) #define kvm_has_feat_enum(kvm, ...) __kvm_has_feat_enum(kvm, __VA_ARGS__) #define kvm_has_feat_range(kvm, id, fld, min, max) \ (kvm_cmp_feat(kvm, id, fld, >=, min) && \ kvm_cmp_feat(kvm, id, fld, <=, max)) /* Check for a given level of PAuth support */ #define kvm_has_pauth(k, l) \ ({ \ bool pa, pi, pa3; \ \ pa = kvm_has_feat((k), ID_AA64ISAR1_EL1, APA, l); \ pa &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPA, IMP); \ pi = kvm_has_feat((k), ID_AA64ISAR1_EL1, API, l); \ pi &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPI, IMP); \ pa3 = kvm_has_feat((k), ID_AA64ISAR2_EL1, APA3, l); \ pa3 &= kvm_has_feat((k), ID_AA64ISAR2_EL1, GPA3, IMP); \ \ (pa + pi + pa3) == 1; \ }) #define kvm_has_fpmr(k) \ (system_supports_fpmr() && \ kvm_has_feat((k), ID_AA64PFR2_EL1, FPMR, IMP)) #define kvm_has_tcr2(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, TCRX, IMP)) #define kvm_has_s1pie(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP)) #define kvm_has_s1poe(k) \ (system_supports_poe() && \ kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP)) #define kvm_has_ras(k) \ (kvm_has_feat((k), ID_AA64PFR0_EL1, RAS, IMP)) #define kvm_has_sctlr2(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, SCTLRX, IMP)) static inline bool kvm_arch_has_irq_bypass(void) { return true; } void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt); struct resx get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg); void check_feature_map(void); void kvm_vcpu_load_fgt(struct kvm_vcpu *vcpu); static __always_inline enum fgt_group_id __fgt_reg_to_group_id(enum vcpu_sysreg reg) { switch (reg) { case HFGRTR_EL2: case HFGWTR_EL2: return HFGRTR_GROUP; case HFGITR_EL2: return HFGITR_GROUP; case HDFGRTR_EL2: case HDFGWTR_EL2: return HDFGRTR_GROUP; case HAFGRTR_EL2: return HAFGRTR_GROUP; case HFGRTR2_EL2: case HFGWTR2_EL2: return HFGRTR2_GROUP; case HFGITR2_EL2: return HFGITR2_GROUP; case HDFGRTR2_EL2: case HDFGWTR2_EL2: return HDFGRTR2_GROUP; case ICH_HFGRTR_EL2: case ICH_HFGWTR_EL2: return ICH_HFGRTR_GROUP; case ICH_HFGITR_EL2: return ICH_HFGITR_GROUP; default: BUILD_BUG_ON(1); } } #define vcpu_fgt(vcpu, reg) \ ({ \ enum fgt_group_id id = __fgt_reg_to_group_id(reg); \ u64 *p; \ switch (reg) { \ case HFGWTR_EL2: \ case HDFGWTR_EL2: \ case HFGWTR2_EL2: \ case HDFGWTR2_EL2: \ case ICH_HFGWTR_EL2: \ p = &(vcpu)->arch.fgt[id].w; \ break; \ default: \ p = &(vcpu)->arch.fgt[id].r; \ break; \ } \ \ p; \ }) long kvm_get_cap_for_kvm_ioctl(unsigned int ioctl, long *ext); #endif /* __ARM64_KVM_HOST_H__ */ |
| 194 239 239 6 5 6 6 8 6 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/xarray.h> /** * idr_alloc_u32() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @nextid: Pointer to an ID. * @max: The maximum ID to allocate (inclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @nextid and @max. * Note that @max is inclusive whereas the @end parameter to idr_alloc() * is exclusive. The new ID is assigned to @nextid before the pointer * is inserted into the IDR, so if @nextid points into the object pointed * to by @ptr, a concurrent lookup will not find an uninitialised ID. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. If an error occurred, * @nextid is unchanged. */ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, unsigned long max, gfp_t gfp) { struct radix_tree_iter iter; void __rcu **slot; unsigned int base = idr->idr_base; unsigned int id = *nextid; if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) idr->idr_rt.xa_flags |= IDR_RT_MARKER; if (max < base) return -ENOSPC; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base); if (IS_ERR(slot)) return PTR_ERR(slot); *nextid = iter.index + base; /* there is a memory barrier inside radix_tree_iter_replace() */ radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); return 0; } EXPORT_SYMBOL_GPL(idr_alloc_u32); /** * idr_alloc() - Allocate an ID. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = start; int ret; if (WARN_ON_ONCE(start < 0)) return -EINVAL; ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp); if (ret) return ret; return id; } EXPORT_SYMBOL_GPL(idr_alloc); /** * idr_alloc_cyclic() - Allocate an ID cyclically. * @idr: IDR handle. * @ptr: Pointer to be associated with the new ID. * @start: The minimum ID (inclusive). * @end: The maximum ID (exclusive). * @gfp: Memory allocation flags. * * Allocates an unused ID in the range specified by @start and @end. If * @end is <= 0, it is treated as one larger than %INT_MAX. This allows * callers to use @start + N as @end as long as N is within integer range. * The search for an unused ID will start at the last ID allocated and will * wrap around to @start if no free IDs are found before reaching @end. * * The caller should provide their own locking to ensure that two * concurrent modifications to the IDR are not possible. Read-only * accesses to the IDR may be done under the RCU read lock or may * exclude simultaneous writers. * * Return: The newly allocated ID, -ENOMEM if memory allocation failed, * or -ENOSPC if no free IDs could be found. */ int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { u32 id = idr->idr_next; int err, max = end > 0 ? end - 1 : INT_MAX; if ((int)id < start) id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); if ((err == -ENOSPC) && (id > start)) { id = start; err = idr_alloc_u32(idr, ptr, &id, max, gfp); } if (err) return err; idr->idr_next = id + 1; return id; } EXPORT_SYMBOL(idr_alloc_cyclic); /** * idr_remove() - Remove an ID from the IDR. * @idr: IDR handle. * @id: Pointer ID. * * Removes this ID from the IDR. If the ID was not previously in the IDR, * this function returns %NULL. * * Since this function modifies the IDR, the caller should provide their * own locking to ensure that concurrent modification of the same IDR is * not possible. * * Return: The pointer formerly associated with this ID. */ void *idr_remove(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL); } EXPORT_SYMBOL_GPL(idr_remove); /** * idr_find() - Return pointer for given ID. * @idr: IDR handle. * @id: Pointer ID. * * Looks up the pointer associated with this ID. A %NULL pointer may * indicate that @id is not allocated or that the %NULL pointer was * associated with this ID. * * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. * * Return: The pointer associated with this ID. */ void *idr_find(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base); } EXPORT_SYMBOL_GPL(idr_find); /** * idr_for_each() - Iterate through all stored pointers. * @idr: IDR handle. * @fn: Function to be called for each pointer. * @data: Data passed to callback function. * * The callback function will be called for each entry in @idr, passing * the ID, the entry and @data. * * If @fn returns anything other than %0, the iteration stops and that * value is returned from this function. * * idr_for_each() can be called concurrently with idr_alloc() and * idr_remove() if protected by RCU. Newly added entries may not be * seen and deleted entries may be seen, but adding and removing entries * will not cause other entries to be skipped, nor spurious ones to be seen. */ int idr_for_each(const struct idr *idr, int (*fn)(int id, void *p, void *data), void *data) { struct radix_tree_iter iter; void __rcu **slot; int base = idr->idr_base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; unsigned long id = iter.index + base; if (WARN_ON_ONCE(id > INT_MAX)) break; ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } return 0; } EXPORT_SYMBOL(idr_for_each); /** * idr_get_next_ul() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { entry = rcu_dereference_raw(*slot); if (!entry) continue; if (!xa_is_internal(entry)) break; if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) break; slot = radix_tree_iter_retry(&iter); } if (!slot) return NULL; *nextid = iter.index + base; return entry; } EXPORT_SYMBOL(idr_get_next_ul); /** * idr_get_next() - Find next populated entry. * @idr: IDR handle. * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated * to the ID of the found value. To use in a loop, the value pointed to by * nextid must be incremented by the user. */ void *idr_get_next(struct idr *idr, int *nextid) { unsigned long id = *nextid; void *entry = idr_get_next_ul(idr, &id); if (WARN_ON_ONCE(id > INT_MAX)) return NULL; *nextid = id; return entry; } EXPORT_SYMBOL(idr_get_next); /** * idr_replace() - replace pointer for given ID. * @idr: IDR handle. * @ptr: New pointer to associate with the ID. * @id: ID to change. * * Replace the pointer registered with an ID and return the old value. * This function can be called under the RCU read lock concurrently with * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * * Returns: the old value on success. %-ENOENT indicates that @id was not * found. %-EINVAL indicates that @ptr was not valid. */ void *idr_replace(struct idr *idr, void *ptr, unsigned long id) { struct radix_tree_node *node; void __rcu **slot = NULL; void *entry; id -= idr->idr_base; entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); __radix_tree_replace(&idr->idr_rt, node, slot, ptr); return entry; } EXPORT_SYMBOL(idr_replace); /** * DOC: IDA description * * The IDA is an ID allocator which does not provide the ability to * associate an ID with a pointer. As such, it only needs to store one * bit per ID, and so is more space efficient than an IDR. To use an IDA, * define it using DEFINE_IDA() (or embed a &struct ida in a data structure, * then initialise it using ida_init()). To allocate a new ID, call * ida_alloc(), ida_alloc_min(), ida_alloc_max() or ida_alloc_range(). * To free an ID, call ida_free(). * * ida_destroy() can be used to dispose of an IDA without needing to * free the individual IDs in it. You can use ida_is_empty() to find * out whether the IDA has any IDs currently allocated. * * The IDA handles its own locking. It is safe to call any of the IDA * functions without synchronisation in your code. * * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward * limitation, it should be quite straightforward to raise the maximum. */ /* * Developer's notes: * * The IDA uses the functionality provided by the XArray to store bitmaps in * each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap * have been set. * * I considered telling the XArray that each slot is an order-10 node * and indexing by bit number, but the XArray can't allow a single multi-index * entry in the head, which would significantly increase memory consumption * for the IDA. So instead we divide the index by the number of bits in the * leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given * leaf, instead of allocating a 128-byte bitmap, we store the bits * as a value entry. Value entries never have the XA_FREE_MARK cleared * because we can always convert them into a bitmap entry. * * It would be possible to optimise further; once we've run out of a * single 128-byte bitmap, we currently switch to a 576-byte node, put * the 128-byte bitmap in the first entry and then start allocating extra * 128-byte entries. We could instead use the 512 bytes of the node's * data as a bitmap before moving to that scheme. I do not believe this * is a worthwhile optimisation; Rasmus Villemoes surveyed the current * users of the IDA and almost none of them use more than 1024 entries. * Those that do use more than the 8192 IDs that the 512 bytes would * provide. * * The IDA always uses a lock to alloc/free. If we add a 'test_bit' * equivalent, it will still need locking. Going to RCU lookup would require * using RCU to free bitmaps, and that's not trivial without embedding an * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte * bitmap, which is excessive. */ /** * ida_alloc_range() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and @max, inclusive. The allocated ID will * not exceed %INT_MAX, even if @max is larger. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, gfp_t gfp) { XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS); unsigned bit = min % IDA_BITMAP_BITS; unsigned long flags; struct ida_bitmap *bitmap, *alloc = NULL; if ((int)min < 0) return -ENOSPC; if ((int)max < 0) max = INT_MAX; retry: xas_lock_irqsave(&xas, flags); next: bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK); if (xas.xa_index > min / IDA_BITMAP_BITS) bit = 0; if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (xa_is_value(bitmap)) { unsigned long tmp = xa_to_value(bitmap); if (bit < BITS_PER_XA_VALUE) { bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit < BITS_PER_XA_VALUE) { tmp |= 1UL << bit; xas_store(&xas, xa_mk_value(tmp)); goto out; } } bitmap = alloc; if (!bitmap) bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); if (!bitmap) goto alloc; bitmap->bitmap[0] = tmp; xas_store(&xas, bitmap); if (xas_error(&xas)) { bitmap->bitmap[0] = 0; goto out; } } if (bitmap) { bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); if (xas.xa_index * IDA_BITMAP_BITS + bit > max) goto nospc; if (bit == IDA_BITMAP_BITS) goto next; __set_bit(bit, bitmap->bitmap); if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) xas_clear_mark(&xas, XA_FREE_MARK); } else { if (bit < BITS_PER_XA_VALUE) { bitmap = xa_mk_value(1UL << bit); } else { bitmap = alloc; if (!bitmap) bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT); if (!bitmap) goto alloc; __set_bit(bit, bitmap->bitmap); } xas_store(&xas, bitmap); } out: xas_unlock_irqrestore(&xas, flags); if (xas_nomem(&xas, gfp)) { xas.xa_index = min / IDA_BITMAP_BITS; bit = min % IDA_BITMAP_BITS; goto retry; } if (bitmap != alloc) kfree(alloc); if (xas_error(&xas)) return xas_error(&xas); return xas.xa_index * IDA_BITMAP_BITS + bit; alloc: xas_unlock_irqrestore(&xas, flags); alloc = kzalloc_obj(*bitmap, gfp); if (!alloc) return -ENOMEM; xas_set(&xas, min / IDA_BITMAP_BITS); bit = min % IDA_BITMAP_BITS; goto retry; nospc: xas_unlock_irqrestore(&xas, flags); kfree(alloc); return -ENOSPC; } EXPORT_SYMBOL(ida_alloc_range); /** * ida_find_first_range - Get the lowest used ID. * @ida: IDA handle. * @min: Lowest ID to get. * @max: Highest ID to get. * * Get the lowest used ID between @min and @max, inclusive. The returned * ID will not exceed %INT_MAX, even if @max is larger. * * Context: Any context. Takes and releases the xa_lock. * Return: The lowest used ID, or errno if no used ID is found. */ int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max) { unsigned long index = min / IDA_BITMAP_BITS; unsigned int offset = min % IDA_BITMAP_BITS; unsigned long *addr, size, bit; unsigned long tmp = 0; unsigned long flags; void *entry; int ret; if ((int)min < 0) return -EINVAL; if ((int)max < 0) max = INT_MAX; xa_lock_irqsave(&ida->xa, flags); entry = xa_find(&ida->xa, &index, max / IDA_BITMAP_BITS, XA_PRESENT); if (!entry) { ret = -ENOENT; goto err_unlock; } if (index > min / IDA_BITMAP_BITS) offset = 0; if (index * IDA_BITMAP_BITS + offset > max) { ret = -ENOENT; goto err_unlock; } if (xa_is_value(entry)) { tmp = xa_to_value(entry); addr = &tmp; size = BITS_PER_XA_VALUE; } else { addr = ((struct ida_bitmap *)entry)->bitmap; size = IDA_BITMAP_BITS; } bit = find_next_bit(addr, size, offset); xa_unlock_irqrestore(&ida->xa, flags); if (bit == size || index * IDA_BITMAP_BITS + bit > max) return -ENOENT; return index * IDA_BITMAP_BITS + bit; err_unlock: xa_unlock_irqrestore(&ida->xa, flags); return ret; } EXPORT_SYMBOL(ida_find_first_range); /** * ida_free() - Release an allocated ID. * @ida: IDA handle. * @id: Previously allocated ID. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_free(struct ida *ida, unsigned int id) { XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS); unsigned bit = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; unsigned long flags; if ((int)id < 0) return; xas_lock_irqsave(&xas, flags); bitmap = xas_load(&xas); if (xa_is_value(bitmap)) { unsigned long v = xa_to_value(bitmap); if (bit >= BITS_PER_XA_VALUE) goto err; if (!(v & (1UL << bit))) goto err; v &= ~(1UL << bit); if (!v) goto delete; xas_store(&xas, xa_mk_value(v)); } else { if (!bitmap || !test_bit(bit, bitmap->bitmap)) goto err; __clear_bit(bit, bitmap->bitmap); xas_set_mark(&xas, XA_FREE_MARK); if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { kfree(bitmap); delete: xas_store(&xas, NULL); } } xas_unlock_irqrestore(&xas, flags); return; err: xas_unlock_irqrestore(&xas, flags); WARN(1, "ida_free called for id=%d which is not allocated.\n", id); } EXPORT_SYMBOL(ida_free); /** * ida_destroy() - Free all IDs. * @ida: IDA handle. * * Calling this function frees all IDs and releases all resources used * by an IDA. When this call returns, the IDA is empty and can be reused * or freed. If the IDA is already empty, there is no need to call this * function. * * Context: Any context. It is safe to call this function without * locking in your code. */ void ida_destroy(struct ida *ida) { XA_STATE(xas, &ida->xa, 0); struct ida_bitmap *bitmap; unsigned long flags; xas_lock_irqsave(&xas, flags); xas_for_each(&xas, bitmap, ULONG_MAX) { if (!xa_is_value(bitmap)) kfree(bitmap); xas_store(&xas, NULL); } xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(ida_destroy); #ifndef __KERNEL__ extern void xa_dump_index(unsigned long index, unsigned int shift); #define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS) static void ida_dump_entry(void *entry, unsigned long index) { unsigned long i; if (!entry) return; if (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); unsigned int shift = node->shift + IDA_CHUNK_SHIFT + XA_CHUNK_SHIFT; xa_dump_index(index * IDA_BITMAP_BITS, shift); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) ida_dump_entry(node->slots[i], index | (i << node->shift)); } else if (xa_is_value(entry)) { xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG)); pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry); } else { struct ida_bitmap *bitmap = entry; xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT); pr_cont("bitmap: %p data", bitmap); for (i = 0; i < IDA_BITMAP_LONGS; i++) pr_cont(" %lx", bitmap->bitmap[i]); pr_cont("\n"); } } static void ida_dump(struct ida *ida) { struct xarray *xa = &ida->xa; pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head, xa->xa_flags >> ROOT_TAG_SHIFT); ida_dump_entry(xa->xa_head, 0); } #endif |
| 239 2 2 6 6 6 6 6 6 2 6 6 6 1 6 1 6 6 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #define CREATE_TRACE_POINTS #include <trace/events/readahead.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio); filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { struct folio *folio; folio = filemap_alloc_folio(gfp_mask, order, NULL); if (folio && ractl->dropbehind) __folio_set_dropbehind(folio); return folio; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller, and ractl->mapping->invalidate_lock * must be held by the caller at least in shared mode. Mutexes may be held by * caller. May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); lockdep_assert_held(&mapping->invalidate_lock); trace_page_cache_ra_unbounded(mapping->host, index, nr_to_read, lookahead_size); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = ractl_alloc_folio(ractl, gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(mapping->host); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; filemap_invalidate_lock_shared(mapping); page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); filemap_invalidate_unlock_shared(mapping); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readahead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int new_order = ra->order; trace_page_cache_ra_order(mapping->host, start, ra); if (!mapping_large_folio_support(mapping)) { ra->order = 0; goto fallback; } limit = min(limit, index + ra->size - 1); new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); ra->order = new_order; /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation below. */ if (!err) return; fallback: /* * ->readahead() may have updated readahead window size so we have to * check there's still something to read. */ if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; trace_page_cache_sync_ra(ractl->mapping->host, index, ra, req_count); /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ra->order = 0; ractl->_index = ra->start; page_cache_ra_order(ractl, ra); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start, end, aligned_end, align; /* no readahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; trace_page_cache_async_ra(ractl->mapping->host, index, ra, req_count); folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, folio_nr_pages(folio)); if (index == expected) { ra->start += ra->size; /* * In the case of MADV_HUGEPAGE, the actual size might exceed * the readahead window. */ ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); readit: ra->order += 2; align = 1UL << min(ra->order, ffs(max_pages) - 1); end = ra->start + ra->size; aligned_end = round_down(end, align); if (aligned_end > ra->start) ra->size -= end - aligned_end; ra->async_size = ra->size; ractl->_index = ra->start; page_cache_ra_order(ractl, ra); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { struct file *file; const struct inode *inode; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; file = fd_file(f); if (!(file->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!file->f_mapping) return -EINVAL; if (!file->f_mapping->a_ops) return -EINVAL; inode = file_inode(file); if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; if (IS_ANON_FILE(inode)) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* include/net/xdp.h * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ #include <linux/bitfield.h> #include <linux/filter.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* skb_shared_info */ #include <net/page_pool/types.h> /** * DOC: XDP RX-queue information * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how * the driver has configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. * * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally needs to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; }; struct page_pool; struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; struct xdp_mem_info mem; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; enum xdp_buff_flags { XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under * pressure */ /* frags have unreadable mem, this can't be true for real XDP packets, * but drivers may use XDP helpers to construct Rx pkt state even when * XDP program is not attached. */ XDP_FLAGS_FRAGS_UNREADABLE = BIT(2), }; struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; union { struct { /* frame size to deduce data_hard_end/tailroom */ u32 frame_sz; /* supported values defined in xdp_buff_flags */ u32 flags; }; #ifdef __LITTLE_ENDIAN /* Used to micro-optimize xdp_init_buff(), don't use directly */ u64 frame_sz_flags_init; #endif }; }; static __always_inline bool xdp_buff_has_frags(const struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_buff_set_frag_unreadable(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_UNREADABLE; } static __always_inline u32 xdp_buff_get_skb_flags(const struct xdp_buff *xdp) { return xdp->flags; } static __always_inline void xdp_buff_clear_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->rxq = rxq; #ifdef __LITTLE_ENDIAN /* * Force the compilers to initialize ::flags and assign ::frame_sz with * one write on 64-bit LE architectures as they're often unable to do * it themselves. */ xdp->frame_sz_flags_init = frame_sz; #else xdp->frame_sz = frame_sz; xdp->flags = 0; #endif } static __always_inline void xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, int headroom, int data_len, const bool meta_valid) { unsigned char *data = hard_start + headroom; xdp->data_hard_start = hard_start; xdp->data = data; xdp->data_end = data + data_len; xdp->data_meta = meta_valid ? data : data + 1; } /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the * XDP/BPF data access to data_hard_end. Notice same area (and size) * is used for XDP_PASS, when constructing the SKB via build_skb(). */ #define xdp_data_hard_end(xdp) \ ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * xdp_get_shared_info_from_buff(const struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } static __always_inline unsigned int xdp_get_buff_len(const struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; const struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); len += sinfo->xdp_frags_size; out: return len; } void xdp_return_frag(netmem_ref netmem, const struct xdp_buff *xdp); /** * __xdp_buff_add_frag - attach frag to &xdp_buff * @xdp: XDP buffer to attach the frag to * @netmem: network memory containing the frag * @offset: offset at which the frag starts * @size: size of the frag * @truesize: total memory size occupied by the frag * @try_coalesce: whether to try coalescing the frags (not valid for XSk) * * Attach frag to the XDP buffer. If it currently has no frags attached, * initialize the related fields, otherwise check that the frag number * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing * the frag with the previous one. * The function doesn't check/update the pfmemalloc bit. Please use the * non-underscored wrapper in drivers. * * Return: true on success, false if there's no space for the frag in * the shared info struct. */ static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, u32 offset, u32 size, u32 truesize, bool try_coalesce) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *prev; u32 nr_frags; if (!xdp_buff_has_frags(xdp)) { xdp_buff_set_frags_flag(xdp); nr_frags = 0; sinfo->xdp_frags_size = 0; sinfo->xdp_frags_truesize = 0; goto fill; } nr_frags = sinfo->nr_frags; prev = &sinfo->frags[nr_frags - 1]; if (try_coalesce && netmem == skb_frag_netmem(prev) && offset == skb_frag_off(prev) + skb_frag_size(prev)) { skb_frag_size_add(prev, size); /* Guaranteed to only decrement the refcount */ xdp_return_frag(netmem, xdp); } else if (unlikely(nr_frags == MAX_SKB_FRAGS)) { return false; } else { fill: __skb_fill_netmem_desc_noacc(sinfo, nr_frags++, netmem, offset, size); } sinfo->nr_frags = nr_frags; sinfo->xdp_frags_size += size; sinfo->xdp_frags_truesize += truesize; return true; } /** * xdp_buff_add_frag - attach frag to &xdp_buff * @xdp: XDP buffer to attach the frag to * @netmem: network memory containing the frag * @offset: offset at which the frag starts * @size: size of the frag * @truesize: total memory size occupied by the frag * * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit. * * Return: true on success, false if there's no space for the frag in * the shared info struct. */ static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, netmem_ref netmem, u32 offset, u32 size, u32 truesize) { if (!__xdp_buff_add_frag(xdp, netmem, offset, size, truesize, true)) return false; if (unlikely(netmem_is_pfmemalloc(netmem))) xdp_buff_set_frag_pfmemalloc(xdp); if (unlikely(netmem_is_net_iov(netmem))) xdp_buff_set_frag_unreadable(xdp); return true; } struct xdp_frame { void *data; u32 len; u32 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem_type is valid on remote CPU. */ enum xdp_mem_type mem_type:32; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_frame_has_frags(const struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline u32 xdp_frame_get_skb_flags(const struct xdp_frame *frame) { return frame->flags; } #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; netmem_ref q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { bq->count = 0; } static inline struct skb_shared_info * xdp_get_shared_info_from_frame(const struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } struct xdp_cpumap_stats { unsigned int redirect; unsigned int pass; unsigned int drop; }; /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { frame->data = NULL; frame->dev_rx = NULL; } static inline void xdp_update_skb_frags_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, u32 xdp_flags) { struct skb_shared_info *sinfo = skb_shinfo(skb); sinfo->nr_frags = nr_frags; /* * ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``, * reset it after that these fields aren't used anymore. */ sinfo->destructor_arg = NULL; skb->len += size; skb->data_len += size; skb->truesize += truesize; skb->pfmemalloc |= !!(xdp_flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); skb->unreadable |= !!(xdp_flags & XDP_FLAGS_FRAGS_UNREADABLE); } /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct sk_buff *xdp_build_skb_from_buff(const struct xdp_buff *xdp); struct sk_buff *xdp_build_skb_from_zc(struct xdp_buff *xdp); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(const struct xdp_frame *frame, struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; xdp->flags = frame->flags; } static inline int xdp_update_frame_from_buff(const struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); return -ENOSPC; } xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; xdp_frame->flags = xdp->flags; return 0; } /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; /* rxq only valid until napi_schedule ends, convert to xdp_mem_type */ xdp_frame->mem_type = xdp->rxq->mem.type; return xdp_frame; } void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type, bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); static inline void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq) { if (unlikely(!bq->count)) return; page_pool_put_netmem_bulk(bq->q, bq->count); bq->count = 0; } static __always_inline unsigned int xdp_get_frame_len(const struct xdp_frame *xdpf) { const struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); len += sinfo->xdp_frags_size; out: return len; } int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); static inline int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id) { return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); int xdp_reg_page_pool(struct page_pool *pool); void xdp_unreg_page_pool(const struct page_pool *pool); void xdp_rxq_info_attach_page_pool(struct xdp_rxq_info *xdp_rxq, const struct page_pool *pool); /** * xdp_rxq_info_attach_mem_model - attach registered mem info to RxQ info * @xdp_rxq: XDP RxQ info to attach the memory info to * @mem: already registered memory info * * If the driver registers its memory providers manually, it must use this * function instead of xdp_rxq_info_reg_mem_model(). */ static inline void xdp_rxq_info_attach_mem_model(struct xdp_rxq_info *xdp_rxq, const struct xdp_mem_info *mem) { xdp_rxq->mem = *mem; } /** * xdp_rxq_info_detach_mem_model - detach registered mem info from RxQ info * @xdp_rxq: XDP RxQ info to detach the memory info from * * If the driver registers its memory providers manually and then attaches it * via xdp_rxq_info_attach_mem_model(), it must call this function before * xdp_rxq_info_unreg(). */ static inline void xdp_rxq_info_detach_mem_model(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->mem = (struct xdp_mem_info){ }; } /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. */ static __always_inline void xdp_set_data_meta_invalid(struct xdp_buff *xdp) { xdp->data_meta = xdp->data + 1; } static __always_inline bool xdp_data_meta_unsupported(const struct xdp_buff *xdp) { return unlikely(xdp->data_meta > xdp->data); } static inline bool xdp_metalen_invalid(unsigned long metalen) { unsigned long meta_max; meta_max = type_max(typeof_member(struct skb_shared_info, meta_len)); BUILD_BUG_ON(!__builtin_constant_p(meta_max)); return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max; } struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; }; struct netdev_bpf; void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE /* Define the relationship between xdp-rx-metadata kfunc and * various other entities: * - xdp_rx_metadata enum * - netdev netlink enum (Documentation/netlink/specs/netdev.yaml) * - kfunc name * - xdp_metadata_ops field */ #define XDP_METADATA_KFUNC_xxx \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \ NETDEV_XDP_RX_METADATA_TIMESTAMP, \ bpf_xdp_metadata_rx_timestamp, \ xmo_rx_timestamp) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \ NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ NETDEV_XDP_RX_METADATA_VLAN_TAG, \ bpf_xdp_metadata_rx_vlan_tag, \ xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC MAX_XDP_METADATA_KFUNC, }; enum xdp_rss_hash_type { /* First part: Individual bits for L3/L4 types */ XDP_RSS_L3_IPV4 = BIT(0), XDP_RSS_L3_IPV6 = BIT(1), /* The fixed (L3) IPv4 and IPv6 headers can both be followed by * variable/dynamic headers, IPv4 called Options and IPv6 called * Extension Headers. HW RSS type can contain this info. */ XDP_RSS_L3_DYNHDR = BIT(2), /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in * addition to the protocol specific bit. This ease interaction with * SKBs and avoids reserving a fixed mask for future L4 protocol bits. */ XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ XDP_RSS_L4_TCP = BIT(4), XDP_RSS_L4_UDP = BIT(5), XDP_RSS_L4_SCTP = BIT(6), XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ XDP_RSS_L4_ICMP = BIT(8), /* Second part: RSS hash type combinations used for driver HW mapping */ XDP_RSS_TYPE_NONE = 0, XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV4_ICMP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV6_ICMP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, }; struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci); }; #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val); void xdp_set_features_flag_locked(struct net_device *dev, xdp_features_t val); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); void xdp_features_set_redirect_target_locked(struct net_device *dev, bool support_sg); void xdp_features_clear_redirect_target(struct net_device *dev); void xdp_features_clear_redirect_target_locked(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } static inline void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { } static inline void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { } static inline void xdp_features_clear_redirect_target(struct net_device *dev) { } #endif static inline void xdp_clear_features_flag(struct net_device *dev) { xdp_set_features_flag(dev, 0); } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) act = xdp_master_redirect(xdp); } return act; } #endif /* __LINUX_NET_XDP_H__ */ |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Pieter Beyens <pieter.beyens@eia.be> // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2018 Protonic, // Robin van der Gracht <robin@protonic.nl> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* Core of can-j1939 that links j1939 to CAN. */ #include <linux/can/can-ml.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/if_arp.h> #include <linux/module.h> #include "j1939-priv.h" MODULE_DESCRIPTION("PF_CAN SAE J1939"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("EIA Electronics (Kurt Van Dijck & Pieter Beyens)"); MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); /* LOWLEVEL CAN interface */ /* CAN_HDR: #bytes before can_frame data part */ #define J1939_CAN_HDR (offsetof(struct can_frame, data)) /* lowest layer */ static void j1939_can_recv(struct sk_buff *iskb, void *data) { struct j1939_priv *priv = data; struct sk_buff *skb; struct j1939_sk_buff_cb *skcb, *iskcb; struct can_frame *cf; /* make sure we only get Classical CAN frames */ if (!can_is_can_skb(iskb)) return; /* create a copy of the skb * j1939 only delivers the real data bytes, * the header goes into sockaddr. * j1939 may not touch the incoming skb in such way */ skb = skb_clone(iskb, GFP_ATOMIC); if (!skb) return; j1939_priv_get(priv); can_skb_set_owner(skb, iskb->sk); /* get a pointer to the header of the skb * the skb payload (pointer) is moved, so that the next skb_data * returns the actual payload */ cf = (void *)skb->data; skb_pull(skb, J1939_CAN_HDR); /* fix length, set to dlc, with 8 maximum */ skb_trim(skb, min_t(uint8_t, cf->len, 8)); /* set addr */ skcb = j1939_skb_to_cb(skb); memset(skcb, 0, sizeof(*skcb)); iskcb = j1939_skb_to_cb(iskb); skcb->tskey = iskcb->tskey; skcb->priority = (cf->can_id >> 26) & 0x7; skcb->addr.sa = cf->can_id; skcb->addr.pgn = (cf->can_id >> 8) & J1939_PGN_MAX; /* set default message type */ skcb->addr.type = J1939_TP; if (!j1939_address_is_valid(skcb->addr.sa)) { netdev_err_once(priv->ndev, "%s: sa is broadcast address, ignoring!\n", __func__); goto done; } if (j1939_pgn_is_pdu1(skcb->addr.pgn)) { /* Type 1: with destination address */ skcb->addr.da = skcb->addr.pgn; /* normalize pgn: strip dst address */ skcb->addr.pgn &= 0x3ff00; } else { /* set broadcast address */ skcb->addr.da = J1939_NO_ADDR; } /* update localflags */ read_lock_bh(&priv->lock); if (j1939_address_is_unicast(skcb->addr.sa) && priv->ents[skcb->addr.sa].nusers) skcb->flags |= J1939_ECU_LOCAL_SRC; if (j1939_address_is_unicast(skcb->addr.da) && priv->ents[skcb->addr.da].nusers) skcb->flags |= J1939_ECU_LOCAL_DST; read_unlock_bh(&priv->lock); /* deliver into the j1939 stack ... */ j1939_ac_recv(priv, skb); if (j1939_tp_recv(priv, skb)) /* this means the transport layer processed the message */ goto done; j1939_simple_recv(priv, skb); j1939_sk_recv(priv, skb); done: j1939_priv_put(priv); kfree_skb(skb); } /* NETDEV MANAGEMENT */ /* values for can_rx_(un)register */ #define J1939_CAN_ID CAN_EFF_FLAG #define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) static DEFINE_MUTEX(j1939_netdev_lock); static struct j1939_priv *j1939_priv_create(struct net_device *ndev) { struct j1939_priv *priv; priv = kzalloc_obj(*priv); if (!priv) return NULL; rwlock_init(&priv->lock); INIT_LIST_HEAD(&priv->ecus); priv->ndev = ndev; kref_init(&priv->kref); kref_init(&priv->rx_kref); dev_hold(ndev); netdev_dbg(priv->ndev, "%s : 0x%p\n", __func__, priv); return priv; } static inline void j1939_priv_set(struct net_device *ndev, struct j1939_priv *priv) { struct can_ml_priv *can_ml = can_get_ml_priv(ndev); can_ml->j1939_priv = priv; } static void __j1939_priv_release(struct kref *kref) { struct j1939_priv *priv = container_of(kref, struct j1939_priv, kref); struct net_device *ndev = priv->ndev; netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); WARN_ON_ONCE(!list_empty(&priv->active_session_list)); WARN_ON_ONCE(!list_empty(&priv->ecus)); WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); dev_put(ndev); kfree(priv); } void j1939_priv_put(struct j1939_priv *priv) { kref_put(&priv->kref, __j1939_priv_release); } void j1939_priv_get(struct j1939_priv *priv) { kref_get(&priv->kref); } static int j1939_can_rx_register(struct j1939_priv *priv) { struct net_device *ndev = priv->ndev; int ret; j1939_priv_get(priv); ret = can_rx_register(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv, "j1939", NULL); if (ret < 0) { j1939_priv_put(priv); return ret; } return 0; } static void j1939_can_rx_unregister(struct j1939_priv *priv) { struct net_device *ndev = priv->ndev; can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv); /* The last reference of priv is dropped by the RCU deferred * j1939_sk_sock_destruct() of the last socket, so we can * safely drop this reference here. */ j1939_priv_put(priv); } static void __j1939_rx_release(struct kref *kref) __releases(&j1939_netdev_lock) { struct j1939_priv *priv = container_of(kref, struct j1939_priv, rx_kref); j1939_can_rx_unregister(priv); j1939_ecu_unmap_all(priv); j1939_priv_set(priv->ndev, NULL); mutex_unlock(&j1939_netdev_lock); } /* get pointer to priv without increasing ref counter */ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { struct can_ml_priv *can_ml = can_get_ml_priv(ndev); return can_ml->j1939_priv; } static struct j1939_priv *j1939_priv_get_by_ndev_locked(struct net_device *ndev) { struct j1939_priv *priv; lockdep_assert_held(&j1939_netdev_lock); priv = j1939_ndev_to_priv(ndev); if (priv) j1939_priv_get(priv); return priv; } static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) { struct j1939_priv *priv; mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); mutex_unlock(&j1939_netdev_lock); return priv; } struct j1939_priv *j1939_netdev_start(struct net_device *ndev) { struct j1939_priv *priv, *priv_new; int ret; mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); mutex_unlock(&j1939_netdev_lock); return priv; } mutex_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) return ERR_PTR(-ENOMEM); j1939_tp_init(priv); rwlock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); mutex_lock(&j1939_netdev_lock); priv_new = j1939_priv_get_by_ndev_locked(ndev); if (priv_new) { /* Someone was faster than us, use their priv and roll * back our's. */ kref_get(&priv_new->rx_kref); mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return priv_new; } j1939_priv_set(ndev, priv); ret = j1939_can_rx_register(priv); if (ret < 0) goto out_priv_put; mutex_unlock(&j1939_netdev_lock); return priv; out_priv_put: j1939_priv_set(ndev, NULL); mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return ERR_PTR(ret); } void j1939_netdev_stop(struct j1939_priv *priv) { kref_put_mutex(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); j1939_priv_put(priv); } int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) { int ret, dlc; canid_t canid; struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); struct can_frame *cf; /* apply sanity checks */ if (j1939_pgn_is_pdu1(skcb->addr.pgn)) skcb->addr.pgn &= J1939_PGN_PDU1_MAX; else skcb->addr.pgn &= J1939_PGN_MAX; if (skcb->priority > 7) skcb->priority = 6; ret = j1939_ac_fixup(priv, skb); if (unlikely(ret)) goto failed; dlc = skb->len; /* re-claim the CAN_HDR from the SKB */ cf = skb_push(skb, J1939_CAN_HDR); /* initialize header structure */ memset(cf, 0, J1939_CAN_HDR); /* make it a full can frame again */ skb_put_zero(skb, 8 - dlc); canid = CAN_EFF_FLAG | (skcb->priority << 26) | (skcb->addr.pgn << 8) | skcb->addr.sa; if (j1939_pgn_is_pdu1(skcb->addr.pgn)) canid |= skcb->addr.da << 8; cf->can_id = canid; cf->len = dlc; return can_send(skb, 1); failed: kfree_skb(skb); return ret; } static int j1939_netdev_notify(struct notifier_block *nb, unsigned long msg, void *data) { struct net_device *ndev = netdev_notifier_info_to_dev(data); struct can_ml_priv *can_ml = can_get_ml_priv(ndev); struct j1939_priv *priv; if (!can_ml) goto notify_done; priv = j1939_priv_get_by_ndev(ndev); if (!priv) goto notify_done; switch (msg) { case NETDEV_DOWN: j1939_cancel_active_session(priv, NULL); j1939_sk_netdev_event_netdown(priv); j1939_ecu_unmap_all(priv); break; case NETDEV_UNREGISTER: j1939_cancel_active_session(priv, NULL); j1939_sk_netdev_event_netdown(priv); j1939_sk_netdev_event_unregister(priv); break; } j1939_priv_put(priv); notify_done: return NOTIFY_DONE; } static struct notifier_block j1939_netdev_notifier = { .notifier_call = j1939_netdev_notify, }; /* MODULE interface */ static __init int j1939_module_init(void) { int ret; pr_info("can: SAE J1939\n"); ret = register_netdevice_notifier(&j1939_netdev_notifier); if (ret) goto fail_notifier; ret = can_proto_register(&j1939_can_proto); if (ret < 0) { pr_err("can: registration of j1939 protocol failed\n"); goto fail_sk; } return 0; fail_sk: unregister_netdevice_notifier(&j1939_netdev_notifier); fail_notifier: return ret; } static __exit void j1939_module_exit(void) { can_proto_unregister(&j1939_can_proto); unregister_netdevice_notifier(&j1939_netdev_notifier); } module_init(j1939_module_init); module_exit(j1939_module_exit); |
| 1175 1175 13 235 235 235 1175 1175 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/atomic.h> #include <linux/bitmap.h> #include <linux/cleanup.h> #include <linux/cpumask_types.h> #include <linux/gfp_types.h> #include <linux/numa.h> #include <linux/threads.h> #include <linux/types.h> #include <asm/bug.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern unsigned int __num_possible_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_andnot - return the first cpu from *srcp1 & ~*srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no such cpu found. */ static __always_inline unsigned int cpumask_first_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_andnot(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from * @n+1. If nothing found, wrap around and start from * the beginning * @n: the cpu prior to the place to search (i.e. search starts from @n+1) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty. */ static __always_inline unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing * found, wrap around and start from the beginning * @n: the cpu prior to the place to search (i.e. search starts from @n+1) * @src: cpumask pointer * * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty. */ static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *src) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1); } /** * cpumask_random - get random cpu in *src. * @src: cpumask pointer * * Return: random set bit, or >= nr_cpu_ids if @src is empty. */ static __always_inline unsigned int cpumask_random(const struct cpumask *src) { return find_random_bit(cpumask_bits(src), nr_cpu_ids); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * If @cpu == -1, the function is equivalent to cpumask_any(). * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, int cpu) { unsigned int i; /* -1 is a legal arg here. */ if (cpu != -1) cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * If @cpu == -1, the function is equivalent to cpumask_any_and(). * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, int cpu) { unsigned int i; /* -1 is a legal arg here. */ if (cpu != -1) cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_any_andnot_but - pick an arbitrary cpu from *mask1 & ~*mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * If @cpu == -1, the function returns the first matching cpu. * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_andnot_but(const struct cpumask *mask1, const struct cpumask *mask2, int cpu) { unsigned int i; /* -1 is a legal arg here. */ if (cpu != -1) cpumask_check(cpu); i = cpumask_first_andnot(mask1, mask2); if (i != cpu) return i; return cpumask_next_andnot(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpus - clear cpus in a cpumask * @dstp: the cpumask pointer * @cpu: cpu number (< nr_cpu_ids) * @ncpus: number of cpus to clear (< nr_cpu_ids) */ static __always_inline void cpumask_clear_cpus(struct cpumask *dstp, unsigned int cpu, unsigned int ncpus) { cpumask_check(cpu + ncpus - 1); bitmap_clear(cpumask_bits(dstp), cpumask_check(cpu), ncpus); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_weighted_or - *dstp = *src1p | *src2p and return the weight of the result * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: The number of bits set in the resulting cpumask @dstp */ static __always_inline unsigned int cpumask_weighted_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_weighted_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly #define CPUMASK_VAR_NULL NULL bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly #define CPUMASK_VAR_NULL {} static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_possible_cpu_wrap(cpu, start) \ for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu_wrap(cpu, start) \ for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #define for_each_possible_cpu_wrap(cpu, start) \ for_each_cpu_wrap((cpu), cpu_possible_mask, (start)) #define for_each_online_cpu_wrap(cpu, start) \ for_each_cpu_wrap((cpu), cpu_online_mask, (start)) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define __assign_cpu(cpu, mask, val) \ __assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); void set_cpu_possible(unsigned int cpu, bool possible); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } static __always_inline unsigned int num_possible_cpus(void) { return __num_possible_cpus; } #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 260 261 32 7 134 143 57 162 1 2 103 75 115 11 153 544 377 376 153 148 140 116 109 141 114 114 113 115 4 252 252 4 216 245 269 274 274 260 252 295 274 271 295 6 2 75 59 55 312 55 59 264 466 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_HOST_H #define __KVM_HOST_H #include <linux/entry-virt.h> #include <linux/types.h> #include <linux/hardirq.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/bug.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/preempt.h> #include <linux/msi.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/rcupdate.h> #include <linux/ratelimit.h> #include <linux/err.h> #include <linux/irqflags.h> #include <linux/context_tracking.h> #include <linux/irqbypass.h> #include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> #include <linux/ftrace.h> #include <linux/hashtable.h> #include <linux/instrumentation.h> #include <linux/interval_tree.h> #include <linux/rbtree.h> #include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <asm/kvm_host.h> #include <linux/kvm_dirty_ring.h> #ifndef KVM_MAX_VCPU_IDS #define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally * used in kvm, other bits are visible for userspace which are defined in * include/uapi/linux/kvm.h. */ #define KVM_MEMSLOT_INVALID (1UL << 16) #define KVM_MEMSLOT_GMEM_ONLY (1UL << 17) /* * Bit 63 of the memslot generation number is an "update in-progress flag", * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. * * This is necessary because the actual memslots update is not atomic with * respect to the generation number update. Updating the generation number * first would allow a vCPU to cache a spte from the old memslots using the * new generation number, and updating the generation number after switching * to the new memslots would allow cache hits using the old generation number * to reference the defunct memslots. * * This mechanism is used to prevent getting hits in KVM's caches while a * memslot update is in-progress, and to prevent cache hits *after* updating * the actual generation number against accesses that were inserted into the * cache *before* the memslots were updated. */ #define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS BIT_ULL(63) /* Two fragments for cross MMIO pages. */ #define KVM_MAX_MMIO_FRAGMENTS 2 #ifndef KVM_MAX_NR_ADDRESS_SPACES #define KVM_MAX_NR_ADDRESS_SPACES 1 #endif /* * For the normal pfn, the highest 12 bits should be zero, * so we can mask bit 62 ~ bit 52 to indicate the error pfn, * mask bit 63 to indicate the noslot pfn. */ #define KVM_PFN_ERR_MASK (0x7ffULL << 52) #define KVM_PFN_ERR_NOSLOT_MASK (0xfffULL << 52) #define KVM_PFN_NOSLOT (0x1ULL << 63) #define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK) #define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1) #define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2) #define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3) #define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4) /* * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ static inline bool is_error_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_MASK); } /* * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted * by a pending signal. Note, the signal may or may not be fatal. */ static inline bool is_sigpending_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_ERR_SIGPENDING; } /* * error_noslot pfns indicate that the gfn can not be * translated to pfn - it is not in slot or failed to * translate it to pfn. */ static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK); } /* noslot pfn indicates that the gfn is not in slot. */ static inline bool is_noslot_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_NOSLOT; } /* * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390) * provide own defines and kvm_is_error_hva */ #ifndef KVM_HVA_ERR_BAD #define KVM_HVA_ERR_BAD (PAGE_OFFSET) #define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE) static inline bool kvm_is_error_hva(unsigned long addr) { return addr >= PAGE_OFFSET; } #endif static inline bool kvm_is_error_gpa(gpa_t gpa) { return gpa == INVALID_GPA; } #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) #define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members * Bits 3-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_DIRTY_RING_SOFT_FULL 3 #define KVM_REQUEST_ARCH_BASE 8 /* * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no * guarantee the vCPU received an IPI and has actually exited guest mode. */ #define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 #define KVM_PIT_IRQ_SOURCE_ID 2 extern struct mutex kvm_lock; extern struct list_head vm_list; struct kvm_io_range { gpa_t addr; int len; struct kvm_io_device *dev; }; #define NR_IOBUS_DEVS 1000 struct kvm_io_bus { int dev_count; int ioeventfd_count; struct rcu_head rcu; struct kvm_io_range range[]; }; enum kvm_bus { KVM_MMIO_BUS, KVM_PIO_BUS, KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_FAST_MMIO_BUS, KVM_IOCSR_BUS, KVM_NR_BUSES }; int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val); int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie); int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { struct work_struct work; struct list_head link; struct list_head queue; struct kvm_vcpu *vcpu; gpa_t cr2_or_gpa; unsigned long addr; struct kvm_arch_async_pf arch; bool wakeup_all; bool notpresent_injected; }; void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, unsigned long hva, struct kvm_arch_async_pf *arch); int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif union kvm_mmu_notifier_arg { unsigned long attributes; }; enum kvm_gfn_range_filter { KVM_FILTER_SHARED = BIT(0), KVM_FILTER_PRIVATE = BIT(1), }; struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; enum kvm_gfn_range_filter attr_filter; bool may_block; bool lockless; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, EXITING_GUEST_MODE, READING_SHADOW_PAGE_TABLES, }; struct kvm_host_map { /* * Only valid if the 'pfn' is managed by the host kernel (i.e. There is * a 'struct page' for it. When using mem= kernel parameter some memory * can be used as guest memory but they are not managed by host * kernel). */ struct page *pinned_page; struct page *page; void *hva; kvm_pfn_t pfn; kvm_pfn_t gfn; bool writable; }; /* * Used to check if the mapping is valid or not. Never use 'kvm_host_map' * directly to check for that. */ static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) { return !!map->hva; } static inline bool kvm_vcpu_can_poll(ktime_t cur, ktime_t stop) { return single_task_running() && !need_resched() && ktime_before(cur, stop); } /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. */ struct kvm_mmio_fragment { gpa_t gpa; void *data; unsigned len; }; struct kvm_vcpu { struct kvm *kvm; #ifdef CONFIG_PREEMPT_NOTIFIERS struct preempt_notifier preempt_notifier; #endif int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index into kvm->vcpu_array */ int ____srcu_idx; /* Don't use this directly. You've been warned. */ #ifdef CONFIG_PROVE_RCU int srcu_depth; #endif int mode; u64 requests; unsigned long guest_debug; struct mutex mutex; struct kvm_run *run; #ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; #endif struct pid *pid; rwlock_t pid_lock; int sigset_active; sigset_t sigset; unsigned int halt_poll_ns; bool valid_wakeup; #ifdef CONFIG_HAS_IOMEM int mmio_needed; int mmio_read_completed; int mmio_is_write; int mmio_cur_fragment; int mmio_nr_fragments; struct kvm_mmio_fragment mmio_fragments[KVM_MAX_MMIO_FRAGMENTS]; #endif #ifdef CONFIG_KVM_ASYNC_PF struct { u32 queued; struct list_head queue; struct list_head done; spinlock_t lock; } async_pf; #endif #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT /* * Cpu relax intercept or pause loop exit optimization * in_spin_loop: set when a vcpu does a pause loop exit * or cpu relax intercepted. * dy_eligible: indicates whether vcpu is eligible for directed yield. */ struct { bool in_spin_loop; bool dy_eligible; } spin_loop; #endif bool wants_to_run; bool preempted; bool ready; bool scheduled_out; struct kvm_vcpu_arch arch; struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; struct kvm_dirty_ring dirty_ring; /* * The most recently used memslot by this vCPU and the slots generation * for which it is valid. * No wraparound protection is needed since generations won't overflow in * thousands of years, even assuming 1M memslot operations per second. */ struct kvm_memory_slot *last_used_slot; u64 last_used_slot_gen; }; /* * Start accounting time towards a guest. * Must be called before entering guest context. */ static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the * stime pending cputime to flush. */ instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); } /* * Enter guest context and enter an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_enter_irqoff(void) { /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspace from rcu point of view. In * addition CPU may stay in a guest mode for quite a long time (up to * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ if (!context_tracking_guest_enter()) { instrumentation_begin(); rcu_virt_note_context_switch(); instrumentation_end(); } } /* * Deprecated. Architectures should move to guest_timing_enter_irqoff() and * guest_state_enter_irqoff(). */ static __always_inline void guest_enter_irqoff(void) { guest_timing_enter_irqoff(); guest_context_enter_irqoff(); } /** * guest_state_enter_irqoff - Fixup state when entering a guest * * Entry to a guest will enable interrupts, but the kernel state is interrupts * disabled when this is invoked. Also tell RCU about it. * * 1) Trace interrupts on state * 2) Invoke context tracking if enabled to adjust RCU state * 3) Tell lockdep that interrupts are enabled * * Invoked from architecture specific code before entering a guest. * Must be called with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_enter_irqoff() before this. * * Note: this is analogous to exit_to_user_mode(). */ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); lockdep_hardirqs_on(CALLER_ADDR0); } /* * Exit guest context and exit an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_exit_irqoff(void) { /* * Guest mode is treated as a quiescent state, see * guest_context_enter_irqoff() for more details. */ if (!context_tracking_guest_exit()) { instrumentation_begin(); rcu_virt_note_context_switch(); instrumentation_end(); } } /* * Stop accounting time towards a guest. * Must be called after exiting guest context. */ static __always_inline void guest_timing_exit_irqoff(void) { instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } /* * Deprecated. Architectures should move to guest_state_exit_irqoff() and * guest_timing_exit_irqoff(). */ static __always_inline void guest_exit_irqoff(void) { guest_context_exit_irqoff(); guest_timing_exit_irqoff(); } static inline void guest_exit(void) { unsigned long flags; local_irq_save(flags); guest_exit_irqoff(); local_irq_restore(flags); } /** * guest_state_exit_irqoff - Establish state when returning from guest mode * * Entry from a guest disables interrupts, but guest mode is traced as * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. * * 1) Tell lockdep that interrupts are disabled * 2) Invoke context tracking if enabled to reactivate RCU * 3) Trace interrupts off state * * Invoked from architecture specific code after exiting a guest. * Must be invoked with interrupts disabled and the caller must be * non-instrumentable. * The caller has to invoke guest_timing_exit_irqoff() after this. * * Note: this is analogous to enter_from_user_mode(). */ static __always_inline void guest_state_exit_irqoff(void) { lockdep_hardirqs_off(CALLER_ADDR0); guest_context_exit_irqoff(); instrumentation_begin(); trace_hardirqs_off_finish(); instrumentation_end(); } static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* * The memory barrier ensures a previous write to vcpu->requests cannot * be reordered with the read of vcpu->mode. It pairs with the general * memory barrier following the write of vcpu->mode in VCPU RUN. */ smp_mb__before_atomic(); return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE); } /* * Some of the bitops functions do not support too long bitmaps. * This number must be determined not to exceed such limits. */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) /* * Since at idle each memslot belongs to two memslot sets it has to contain * two embedded nodes for each data structure that it forms a part of. * * Two memslot sets (one active and one inactive) are necessary so the VM * continues to run on one memslot set while the other is being modified. * * These two memslot sets normally point to the same set of memslots. * They can, however, be desynchronized when performing a memslot management * operation by replacing the memslot to be modified by its copy. * After the operation is complete, both memslot sets once again point to * the same, common set of memslot data. * * The memslots themselves are independent of each other so they can be * individually added or deleted. */ struct kvm_memory_slot { struct hlist_node id_node[2]; struct interval_tree_node hva_node[2]; struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; struct kvm_arch_memory_slot arch; unsigned long userspace_addr; u32 flags; short id; u16 as_id; #ifdef CONFIG_KVM_GUEST_MEMFD struct { /* * Writes protected by kvm->slots_lock. Acquiring a * reference via kvm_gmem_get_file() is protected by * either kvm->slots_lock or kvm->srcu. */ struct file *file; pgoff_t pgoff; } gmem; #endif }; static inline bool kvm_slot_has_gmem(const struct kvm_memory_slot *slot) { return slot && (slot->flags & KVM_MEM_GUEST_MEMFD); } static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) { return ALIGN(memslot->npages, BITS_PER_LONG) / 8; } static inline unsigned long *kvm_second_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long len = kvm_dirty_bitmap_bytes(memslot); return memslot->dirty_bitmap + len / sizeof(*memslot->dirty_bitmap); } #ifndef KVM_DIRTY_LOG_MANUAL_CAPS #define KVM_DIRTY_LOG_MANUAL_CAPS KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE #endif struct kvm_s390_adapter_int { u64 ind_addr; u64 ind_gaddr; u64 summary_addr; u64 summary_gaddr; u64 ind_offset; u32 summary_offset; u32 adapter_id; }; struct kvm_hv_sint { u32 vcpu; u32 sint; }; struct kvm_xen_evtchn { u32 port; u32 vcpu_id; int vcpu_idx; u32 priority; }; struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); union { struct { unsigned irqchip; unsigned pin; } irqchip; struct { u32 address_lo; u32 address_hi; u32 data; u32 flags; u32 devid; } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING struct kvm_irq_routing_table { int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; u32 nr_rt_entries; /* * Array indexed by gsi. Each entry contains list of irq chips * the gsi is connected to. */ struct hlist_head map[] __counted_by(nr_rt_entries); }; #endif bool kvm_arch_irqchip_in_kernel(struct kvm *kvm); #ifndef KVM_INTERNAL_MEM_SLOTS #define KVM_INTERNAL_MEM_SLOTS 0 #endif #define KVM_MEM_SLOTS_NUM SHRT_MAX #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS) #if KVM_MAX_NR_ADDRESS_SPACES == 1 static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm) { return KVM_MAX_NR_ADDRESS_SPACES; } static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) { return 0; } #endif #ifndef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES static inline bool kvm_arch_has_private_mem(struct kvm *kvm) { return false; } #endif #ifdef CONFIG_KVM_GUEST_MEMFD bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm); static inline u64 kvm_gmem_get_supported_flags(struct kvm *kvm) { u64 flags = GUEST_MEMFD_FLAG_MMAP; if (!kvm || kvm_arch_supports_gmem_init_shared(kvm)) flags |= GUEST_MEMFD_FLAG_INIT_SHARED; return flags; } #endif #ifndef kvm_arch_has_readonly_mem static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) { return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); } #endif struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; struct rb_root_cached hva_tree; struct rb_root gfn_tree; /* * The mapping table from slot id to memslot. * * 7-bit bucket count matches the size of the old id to index array for * 512 slots, while giving good performance with this slot count. * Higher bucket counts bring only small performance improvements but * always result in higher memory usage (even for lower memslot counts). */ DECLARE_HASHTABLE(id_hash, 7); int node_idx; }; struct kvm { #ifdef KVM_HAVE_MMU_RWLOCK rwlock_t mmu_lock; #else spinlock_t mmu_lock; #endif /* KVM_HAVE_MMU_RWLOCK */ struct mutex slots_lock; /* * Protects the arch-specific fields of struct kvm_memory_slots in * use by the VM. To be used under the slots_lock (above) or in a * kvm->srcu critical section where acquiring the slots_lock would * lead to deadlock with the synchronize_srcu in * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ unsigned long nr_memslot_pages; /* The two memslot sets - active and inactive (per address space) */ struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2]; /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES]; struct xarray vcpu_array; /* * Protected by slots_lock, but can be read outside if an * incorrect answer is acceptable. */ atomic_t nr_memslots_dirty_logging; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; unsigned long mn_active_invalidate_count; struct rcuwait mn_memslots_update_rcuwait; /* For management / invalidation of gfn_to_pfn_caches */ spinlock_t gpc_lock; struct list_head gpc_list; /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only * incremented after storing the kvm_vcpu pointer in vcpus, * and is accessed atomically. */ atomic_t online_vcpus; int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_IRQCHIP struct { spinlock_t lock; struct list_head items; /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; #endif struct list_head ioeventfds; struct kvm_vm_stat stat; struct kvm_arch arch; refcount_t users_count; #ifdef CONFIG_KVM_MMIO struct kvm_coalesced_mmio_ring *coalesced_mmio_ring; spinlock_t ring_lock; struct list_head coalesced_zones; #endif struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP /* * Update side is protected by irq_lock. */ struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head irq_ack_notifier_list; #endif struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; gfn_t mmu_invalidate_range_start; gfn_t mmu_invalidate_range_end; struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; struct kvm_stat_data **debugfs_stat_data; struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; bool override_halt_poll_ns; unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool dirty_ring_with_bitmap; bool vm_bugged; bool vm_dead; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; #endif #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES /* Protected by slots_lock (for writes) and RCU (for reads) */ struct xarray mem_attr_array; #endif char stats_id[KVM_STATS_NAME_SIZE]; }; #define kvm_err(fmt, ...) \ pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_info(fmt, ...) \ pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug(fmt, ...) \ pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug_ratelimited(fmt, ...) \ pr_debug_ratelimited("kvm [%i]: " fmt, task_pid_nr(current), \ ## __VA_ARGS__) #define kvm_pr_unimpl(fmt, ...) \ pr_err_ratelimited("kvm [%i]: " fmt, \ task_tgid_nr(current), ## __VA_ARGS__) /* The guest did something we don't support. */ #define vcpu_unimpl(vcpu, fmt, ...) \ kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt, \ (vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__) #define vcpu_debug(vcpu, fmt, ...) \ kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) #define vcpu_debug_ratelimited(vcpu, fmt, ...) \ kvm_debug_ratelimited("vcpu%i " fmt, (vcpu)->vcpu_id, \ ## __VA_ARGS__) #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) static inline void kvm_vm_dead(struct kvm *kvm) { kvm->vm_dead = true; kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); } static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; kvm_vm_dead(kvm); } #define KVM_BUG(cond, kvm, fmt...) \ ({ \ bool __ret = !!(cond); \ \ if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) #define KVM_BUG_ON(cond, kvm) \ ({ \ bool __ret = !!(cond); \ \ if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) /* * Note, "data corruption" refers to corruption of host kernel data structures, * not guest data. Guest data corruption, suspected or confirmed, that is tied * and contained to a single VM should *never* BUG() and potentially panic the * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure * is corrupted and that corruption can have a cascading effect to other parts * of the hosts and/or to other VMs. */ #define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm) \ ({ \ bool __ret = !!(cond); \ \ if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) \ BUG_ON(__ret); \ else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged)) \ kvm_vm_bugged(kvm); \ unlikely(__ret); \ }) static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) { #ifdef CONFIG_PROVE_RCU WARN_ONCE(vcpu->srcu_depth++, "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); #endif vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); } static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); #ifdef CONFIG_PROVE_RCU WARN_ONCE(--vcpu->srcu_depth, "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); #endif } static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); } /* * Get a bus reference under the update-side lock. No long-term SRCU reader * references are permitted, to avoid stale reads vs concurrent IO * registrations. */ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) { return rcu_dereference_protected(kvm->buses[idx], lockdep_is_held(&kvm->slots_lock)); } static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { int num_vcpus = atomic_read(&kvm->online_vcpus); /* * Explicitly verify the target vCPU is online, as the anti-speculation * logic only limits the CPU's ability to speculate, e.g. given a "bad" * index, clamping the index to 0 would return vCPU0, not NULL. */ if (i >= num_vcpus) return NULL; i = array_index_nospec(i, num_vcpus); /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return xa_load(&kvm->vcpu_array, i); } #define kvm_for_each_vcpu(idx, vcpup, kvm) \ if (atomic_read(&kvm->online_vcpus)) \ xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; unsigned long i; if (id < 0) return NULL; if (id < KVM_MAX_VCPUS) vcpu = kvm_get_vcpu(kvm, id); if (vcpu && vcpu->vcpu_id == id) return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) if (vcpu->vcpu_id == id) return vcpu; return NULL; } void kvm_destroy_vcpus(struct kvm *kvm); int kvm_trylock_all_vcpus(struct kvm *kvm); int kvm_lock_all_vcpus(struct kvm *kvm); void kvm_unlock_all_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_IOAPIC void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm); #else static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { } #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else static inline int kvm_irqfd_init(void) { return 0; } static inline void kvm_irqfd_exit(void) { } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); bool file_is_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) { return __kvm_memslots(kvm, 0); } static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) { int as_id = kvm_arch_vcpu_memslots_id(vcpu); return __kvm_memslots(vcpu->kvm, as_id); } static inline bool kvm_memslots_empty(struct kvm_memslots *slots) { return RB_EMPTY_ROOT(&slots->gfn_tree); } bool kvm_are_all_memslots_empty(struct kvm *kvm); #define kvm_for_each_memslot(memslot, bkt, slots) \ hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ if (WARN_ON_ONCE(!memslot->npages)) { \ } else static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { struct kvm_memory_slot *slot; int idx = slots->node_idx; hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { if (slot->id == id) return slot; } return NULL; } /* Iterator used for walking memslots that overlap a gfn range. */ struct kvm_memslot_iter { struct kvm_memslots *slots; struct rb_node *node; struct kvm_memory_slot *slot; }; static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) { iter->node = rb_next(iter->node); if (!iter->node) return; iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); } static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, struct kvm_memslots *slots, gfn_t start) { int idx = slots->node_idx; struct rb_node *tmp; struct kvm_memory_slot *slot; iter->slots = slots; /* * Find the so called "upper bound" of a key - the first node that has * its key strictly greater than the searched one (the start gfn in our case). */ iter->node = NULL; for (tmp = slots->gfn_tree.rb_node; tmp; ) { slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); if (start < slot->base_gfn) { iter->node = tmp; tmp = tmp->rb_left; } else { tmp = tmp->rb_right; } } /* * Find the slot with the lowest gfn that can possibly intersect with * the range, so we'll ideally have slot start <= range start */ if (iter->node) { /* * A NULL previous node means that the very first slot * already has a higher start gfn. * In this case slot start > range start. */ tmp = rb_prev(iter->node); if (tmp) iter->node = tmp; } else { /* a NULL node below means no slots */ iter->node = rb_last(&slots->gfn_tree); } if (iter->node) { iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); /* * It is possible in the slot start < range start case that the * found slot ends before or at range start (slot end <= range start) * and so it does not overlap the requested range. * * In such non-overlapping case the next slot (if it exists) will * already have slot start > range start, otherwise the logic above * would have found it instead of the current slot. */ if (iter->slot->base_gfn + iter->slot->npages <= start) kvm_memslot_iter_next(iter); } } static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) { if (!iter->node) return false; /* * If this slot starts beyond or at the end of the range so does * every next one */ return iter->slot->base_gfn < end; } /* Iterate over each memslot at least partially intersecting [start, end) range */ #define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ for (kvm_memslot_iter_start(iter, slots, start); \ kvm_memslot_iter_is_valid(iter, end); \ kvm_memslot_iter_next(iter)) struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot * - delete an existing memory slot * - modify an existing memory slot * -- move it in the guest physical memory space * -- just change its flags * * Since flags can be changed by some of these operations, the following * differentiation is the best we can do for kvm_set_memory_region(): */ enum kvm_mr_change { KVM_MR_CREATE, KVM_MR_DELETE, KVM_MR_MOVE, KVM_MR_FLAGS_ONLY, }; int kvm_set_internal_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem); void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); /* flush all memory translations */ void kvm_arch_flush_shadow_all(struct kvm *kvm); /* flush memory translations pointing to 'slot' */ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages); struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write); static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { return __gfn_to_page(kvm, gfn, true); } unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable); static inline void kvm_release_page_unused(struct page *page) { if (!page) return; put_page(page); } void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page, bool unused, bool dirty) { lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused); if (!page) return; /* * If the page that KVM got from the *primary MMU* is writable, and KVM * installed or reused a SPTE, mark the page/folio dirty. Note, this * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if * the GFN is write-protected. Folios can't be safely marked dirty * outside of mmu_lock as doing so could race with writeback on the * folio. As a result, KVM can't mark folios dirty in the fast page * fault handler, and so KVM must (somewhat) speculatively mark the * folio dirty if KVM could locklessly make the SPTE writable. */ if (unused) kvm_release_page_unused(page); else if (dirty) kvm_release_page_dirty(page); else kvm_release_page_clean(page); } kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn, unsigned int foll, bool *writable, struct page **refcounted_page); static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool write, bool *writable, struct page **refcounted_page) { return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, write ? FOLL_WRITE : 0, writable, refcounted_page); } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); #define __kvm_get_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ __ret = get_user(v, __uaddr); \ __ret; \ }) #define kvm_get_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ \ __kvm_get_guest(__kvm, __gpa >> PAGE_SHIFT, \ offset_in_page(__gpa), v); \ }) #define __kvm_put_guest(kvm, gfn, offset, v) \ ({ \ unsigned long __addr = gfn_to_hva(kvm, gfn); \ typeof(v) __user *__uaddr = (typeof(__uaddr))(__addr + offset); \ int __ret = -EFAULT; \ \ if (!kvm_is_error_hva(__addr)) \ __ret = put_user(v, __uaddr); \ if (!__ret) \ mark_page_dirty(kvm, gfn); \ __ret; \ }) #define kvm_put_guest(kvm, gpa, v) \ ({ \ gpa_t __gpa = gpa; \ struct kvm *__kvm = kvm; \ \ __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ offset_in_page(__gpa), v); \ }) int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map, bool writable); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map); static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map) { return __kvm_vcpu_map(vcpu, gpa, map, true); } static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map) { return __kvm_vcpu_map(vcpu, gpa, map, false); } static inline void kvm_vcpu_map_mark_dirty(struct kvm_vcpu *vcpu, struct kvm_host_map *map) { if (kvm_vcpu_mapped(map)) kvm_vcpu_mark_page_dirty(vcpu, map->gfn); } unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, int len); int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); /** * kvm_gpc_init - initialize gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @kvm: pointer to kvm instance. * * This sets up a gfn_to_pfn_cache by initializing locks and assigning the * immutable attributes. Note, the cache must be zero-allocated (or zeroed by * the caller before init). */ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); /** * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest * physical address. * * @gpc: struct gfn_to_pfn_cache object. * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This primes a gfn_to_pfn_cache and links it into the @gpc->kvm's list for * invalidations to be processed. Callers are required to use kvm_gpc_check() * to ensure that the cache is valid before accessing the target page. */ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); /** * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. * * @gpc: struct gfn_to_pfn_cache object. * @hva: userspace virtual address to map. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * The semantics of this function are the same as those of kvm_gpc_activate(). It * merely bypasses a layer of address translation. */ int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); /** * kvm_gpc_check - check validity of a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: %true if the cache is still valid and the address matches. * %false if the cache is not valid. * * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock * while calling this function, and then continue to hold the lock until the * access is complete. * * Callers in IN_GUEST_MODE may do so without locking, although they should * still hold a read lock on kvm->scru for the memslot checks. */ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_refresh - update a previously initialized cache. * * @gpc: struct gfn_to_pfn_cache object. * @len: sanity check; the range being access must fit a single page. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. * -EFAULT for an untranslatable guest physical address. * * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful * return from this function does not mean the page can be immediately * accessed because it may have raced with an invalidation. Callers must * still lock and check the cache status, as this function does not return * with the lock still held to permit access. */ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); /** * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @gpc: struct gfn_to_pfn_cache object. * * This removes a cache from the VM's list to be processed on MMU notifier * invocation. */ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) { return gpc->active && !kvm_is_error_gpa(gpc->gpa); } static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) { return gpc->active && kvm_is_error_gpa(gpc->gpa); } void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); void kvm_vcpu_halt(struct kvm_vcpu *vcpu); bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); #ifndef CONFIG_S390 void __kvm_vcpu_kick(struct kvm_vcpu *vcpu, bool wait); static inline void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { __kvm_vcpu_kick(vcpu, false); } #endif int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min); int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc); void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc); void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); #endif void kvm_mmu_invalidate_begin(struct kvm *kvm); void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end); void kvm_mmu_invalidate_end(struct kvm *kvm); bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot); #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot); #endif int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu); int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs); int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state); int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state); #endif #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); #else static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING /* * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of * kvm_usage_count, i.e. at the beginning of the generic hardware enabling * sequence, and at the end of the generic hardware disabling sequence. */ void kvm_arch_enable_virtualization(void); void kvm_arch_disable_virtualization(void); /* * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to * do the actual twiddling of hardware bits. The hooks are called on all * online CPUs when KVM enables/disabled virtualization, and on a single CPU * when that CPU is onlined/offlined (including for Resume/Suspend). */ int kvm_arch_enable_virtualization_cpu(void); void kvm_arch_disable_virtualization_cpu(void); #endif bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); void kvm_arch_pre_destroy_vm(struct kvm *kvm); void kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* * All architectures that want to use vzalloc currently also * need their own kvm_arch_alloc_vm implementation. */ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc_obj(struct kvm, GFP_KERNEL_ACCOUNT); } #endif static inline void __kvm_arch_free_vm(struct kvm *kvm) { kvfree(kvm); } #ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { __kvm_arch_free_vm(kvm); } #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { return -ENOTSUPP; } #else int kvm_arch_flush_remote_tlbs(struct kvm *kvm); #endif #ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { return -EOPNOTSUPP; } #else int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages); #endif #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA void kvm_arch_register_noncoherent_dma(struct kvm *kvm); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm); bool kvm_arch_has_noncoherent_dma(struct kvm *kvm); #else static inline void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { } static inline void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { } static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) { return false; } #endif static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP return vcpu->arch.waitp; #else return &vcpu->wait; #endif } /* * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns * true if the vCPU was blocking and was awakened, false otherwise. */ static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); } static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) { return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); } #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and * ready to accept virtual IRQ. On some architectures the virtual interrupt * controller is dynamically instantiated and this is not always true. */ bool kvm_arch_intc_initialized(struct kvm *kvm); #else static inline bool kvm_arch_intc_initialized(struct kvm *kvm) { return true; } #endif #ifdef CONFIG_GUEST_PERF_EVENTS unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); void __kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void), void (*mediated_pmi_handler)(void)); static inline void kvm_register_perf_callbacks(void) { __kvm_register_perf_callbacks(NULL, NULL); } void kvm_unregister_perf_callbacks(void); #else static inline void kvm_register_perf_callbacks(void) {} static inline void kvm_unregister_perf_callbacks(void) {} #endif /* CONFIG_GUEST_PERF_EVENTS */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); struct kvm_irq_ack_notifier { struct hlist_node link; unsigned gsi; void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; int kvm_irq_map_gsi(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *entries, int gsi); int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin); int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, int irq_source_id, int level, bool line_status); int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_gsi(struct kvm *kvm, int gsi); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { if (!slot) return NULL; if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else return NULL; } /* * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * * With "approx" set returns the memslot also when the address falls * in a hole. In that case one of the memslots bordering the hole is * returned. */ static inline struct kvm_memory_slot * search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; struct rb_node *node; int idx = slots->node_idx; slot = NULL; for (node = slots->gfn_tree.rb_node; node; ) { slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); if (gfn >= slot->base_gfn) { if (gfn < slot->base_gfn + slot->npages) return slot; node = node->rb_right; } else node = node->rb_left; } return approx ? slot : NULL; } static inline struct kvm_memory_slot * ____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); slot = try_get_memslot(slot, gfn); if (slot) return slot; slot = search_memslots(slots, gfn, approx); if (slot) { atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } /* * __gfn_to_memslot() and its descendants are here to allow arch code to inline * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline * because that would bloat other code too much. */ static inline struct kvm_memory_slot * __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) { return ____gfn_to_memslot(slots, gfn, false); } static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { /* * The index was checked originally in search_memslots. To avoid * that a malicious guest builds a Spectre gadget out of e.g. page * table walks, do not let the processor speculate loads outside * the guest's registered memslots. */ unsigned long offset = gfn - slot->base_gfn; offset = array_index_nospec(offset, slot->npages); return slot->userspace_addr + offset * PAGE_SIZE; } static inline int memslot_id(struct kvm *kvm, gfn_t gfn) { return gfn_to_memslot(kvm, gfn)->id; } static inline gfn_t hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot) { gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT; return slot->base_gfn + gfn_offset; } static inline gpa_t gfn_to_gpa(gfn_t gfn) { return (gpa_t)gfn << PAGE_SHIFT; } static inline gfn_t gpa_to_gfn(gpa_t gpa) { return (gfn_t)(gpa >> PAGE_SHIFT); } static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { return (hpa_t)pfn << PAGE_SHIFT; } static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); return !kvm_is_error_hva(hva); } static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) { lockdep_assert_held(&gpc->lock); if (!gpc->memslot) return; mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa)); } enum kvm_stat_kind { KVM_STAT_VM, KVM_STAT_VCPU, }; struct kvm_stat_data { struct kvm *kvm; const struct kvm_stats_desc *desc; enum kvm_stat_kind kind; }; #define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ .flags = type | unit | base | \ BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ .exponent = exp, \ .size = sz, \ .bucket_size = bsz #define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, generic.stat), \ .name = #stat, \ } #define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, generic.stat), \ .name = #stat, \ } #define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vm_stat, stat), \ .name = #stat, \ } #define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ { \ STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ .offset = offsetof(struct kvm_vcpu_stat, stat), \ .name = #stat, \ } /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) #define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, \ unit, base, exponent, 1, 0) #define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, \ unit, base, exponent, 1, 0) #define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, \ unit, base, exponent, 1, 0) #define STATS_DESC_LINEAR_HIST(SCOPE, name, unit, base, exponent, sz, bsz) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LINEAR_HIST, \ unit, base, exponent, sz, bsz) #define STATS_DESC_LOG_HIST(SCOPE, name, unit, base, exponent, sz) \ STATS_DESC(SCOPE, name, KVM_STATS_TYPE_LOG_HIST, \ unit, base, exponent, sz, 0) /* Cumulative counter, read/write */ #define STATS_DESC_COUNTER(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Instantaneous counter, read only */ #define STATS_DESC_ICOUNTER(SCOPE, name) \ STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Peak counter, read/write */ #define STATS_DESC_PCOUNTER(SCOPE, name) \ STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE, \ KVM_STATS_BASE_POW10, 0) /* Instantaneous boolean value, read only */ #define STATS_DESC_IBOOLEAN(SCOPE, name) \ STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ KVM_STATS_BASE_POW10, 0) /* Peak (sticky) boolean value, read/write */ #define STATS_DESC_PBOOLEAN(SCOPE, name) \ STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_BOOLEAN, \ KVM_STATS_BASE_POW10, 0) /* Cumulative time in nanosecond */ #define STATS_DESC_TIME_NSEC(SCOPE, name) \ STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9) /* Linear histogram for time in nanosecond */ #define STATS_DESC_LINHIST_TIME_NSEC(SCOPE, name, sz, bsz) \ STATS_DESC_LINEAR_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9, sz, bsz) /* Logarithmic histogram for time in nanosecond */ #define STATS_DESC_LOGHIST_TIME_NSEC(SCOPE, name, sz) \ STATS_DESC_LOG_HIST(SCOPE, name, KVM_STATS_UNIT_SECONDS, \ KVM_STATS_BASE_POW10, -9, sz) #define KVM_GENERIC_VM_STATS() \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush), \ STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush_requests) #define KVM_GENERIC_VCPU_STATS() \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_successful_poll), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_attempted_poll), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_poll_invalid), \ STATS_DESC_COUNTER(VCPU_GENERIC, halt_wakeup), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns), \ STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); /** * kvm_stats_linear_hist_update() - Update bucket value for linear histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the linear histogram's bucket * @bucket_size: the size (width) of a bucket */ static inline void kvm_stats_linear_hist_update(u64 *data, size_t size, u64 value, size_t bucket_size) { size_t index = div64_u64(value, bucket_size); index = min(index, size - 1); ++data[index]; } /** * kvm_stats_log_hist_update() - Update bucket value for logarithmic histogram * statistics data. * * @data: start address of the stats data * @size: the number of bucket of the stats data * @value: the new value used to update the logarithmic histogram's bucket */ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) { size_t index = fls64(value); index = min(index, size - 1); ++data[index]; } #define KVM_STATS_LINEAR_HIST_UPDATE(array, value, bsize) \ kvm_stats_linear_hist_update(array, ARRAY_SIZE(array), value, bsize) #define KVM_STATS_LOG_HIST_UPDATE(array, value) \ kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value) extern const struct kvm_stats_header kvm_vm_stats_header; extern const struct kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct kvm_stats_desc kvm_vcpu_stats_desc[]; static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { if (unlikely(kvm->mmu_invalidate_in_progress)) return 1; /* * Ensure the read of mmu_invalidate_in_progress happens before * the read of mmu_invalidate_seq. This interacts with the * smp_wmb() in mmu_notifier_invalidate_range_end to make sure * that the caller either sees the old (non-zero) value of * mmu_invalidate_in_progress or the new (incremented) value of * mmu_invalidate_seq. * * PowerPC Book3s HV KVM calls this under a per-page lock rather * than under kvm->mmu_lock, for scalability, so can't rely on * kvm->mmu_lock to keep things ordered. */ smp_rmb(); if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } static inline int mmu_invalidate_retry_gfn(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { lockdep_assert_held(&kvm->mmu_lock); /* * If mmu_invalidate_in_progress is non-zero, then the range maintained * by kvm_mmu_notifier_invalidate_range_start contains all addresses * that might be being invalidated. Note that it may include some false * positives, due to shortcuts when handing concurrent invalidations. */ if (unlikely(kvm->mmu_invalidate_in_progress)) { /* * Dropping mmu_lock after bumping mmu_invalidate_in_progress * but before updating the range is a KVM bug. */ if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA || kvm->mmu_invalidate_range_end == INVALID_GPA)) return 1; if (gfn >= kvm->mmu_invalidate_range_start && gfn < kvm->mmu_invalidate_range_end) return 1; } if (kvm->mmu_invalidate_seq != mmu_seq) return 1; return 0; } /* * This lockless version of the range-based retry check *must* be paired with a * call to the locked version after acquiring mmu_lock, i.e. this is safe to * use only as a pre-check to avoid contending mmu_lock. This version *will* * get false negatives and false positives. */ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, unsigned long mmu_seq, gfn_t gfn) { /* * Use READ_ONCE() to ensure the in-progress flag and sequence counter * are always read from memory, e.g. so that checking for retry in a * loop won't result in an infinite retry loop. Don't force loads for * start+end, as the key to avoiding infinite retry loops is observing * the 1=>0 transition of in-progress, i.e. getting false negatives * due to stale start+end values is acceptable. */ if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) && gfn >= kvm->mmu_invalidate_range_start && gfn < kvm->mmu_invalidate_range_end) return true; return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; } #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */ bool kvm_arch_can_set_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); #else static inline void kvm_free_irq_routing(struct kvm *kvm) {} static inline int kvm_init_irq_routing(struct kvm *kvm) { return 0; } #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); void kvm_eventfd_init(struct kvm *kvm); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQCHIP int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { return -EINVAL; } static inline void kvm_irqfd_release(struct kvm *kvm) {} static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, unsigned int irqchip, unsigned int pin) { return false; } #endif /* CONFIG_HAVE_KVM_IRQCHIP */ void kvm_arch_irq_routing_update(struct kvm *kvm); static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's * caller. Paired with the smp_mb__after_atomic in kvm_check_request. */ smp_wmb(); set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Request that don't require vCPU action should never be logged in * vcpu->requests. The vCPU won't clear the request, so it will stay * logged indefinitely and prevent the vCPU from entering the guest. */ BUILD_BUG_ON(!__builtin_constant_p(req) || (req & KVM_REQUEST_NO_ACTION)); __kvm_make_request(req, vcpu); } #ifndef CONFIG_S390 static inline void kvm_make_request_and_kick(int req, struct kvm_vcpu *vcpu) { kvm_make_request(req, vcpu); __kvm_vcpu_kick(vcpu, req & KVM_REQUEST_WAIT); } #endif static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); } static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu) { return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu) { clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) { if (kvm_test_request(req, vcpu)) { kvm_clear_request(req, vcpu); /* * Ensure the rest of the request is visible to kvm_check_request's * caller. Paired with the smp_wmb in kvm_make_request. */ smp_mb__after_atomic(); return true; } else { return false; } } #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING extern bool enable_virt_at_load; extern bool kvm_rebooting; #endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; }; /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; /* * create is called holding kvm->lock and any operations not suitable * to do while holding the lock should be deferred to init (see * below). */ int (*create)(struct kvm_device *dev, u32 type); /* * init is called after create if create is successful and is called * outside of holding kvm->lock. */ void (*init)(struct kvm_device *dev); /* * Destroy is responsible for freeing dev. * * Destroy may be called before or after destructors are called * on emulated I/O regions, depending on whether a reference is * held by a vcpu or other kvm component that gets destroyed * after the emulated I/O. */ void (*destroy)(struct kvm_device *dev); /* * Release is an alternative method to free the device. It is * called when the device file descriptor is closed. Once * release is called, the destroy method will not be called * anymore as the device is removed from the device list of * the VM. kvm->lock is held. */ void (*release)(struct kvm_device *dev); int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, unsigned long arg); int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma); }; struct kvm_device *kvm_device_from_filp(struct file *filp); int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; extern struct kvm_device_ops kvm_arm_vgic_v3_ops; extern struct kvm_device_ops kvm_arm_vgic_v5_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { vcpu->spin_loop.in_spin_loop = val; } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { vcpu->spin_loop.dy_eligible = val; } #else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) { } static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) { } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot) { return (memslot && memslot->id < KVM_USER_MEM_SLOTS && !(memslot->flags & KVM_MEMSLOT_INVALID)); } struct kvm_vcpu *kvm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS) struct kvm_kernel_irqfd; bool kvm_arch_has_irq_bypass(void); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *, struct irq_bypass_producer *); void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd, struct kvm_kernel_irq_routing_entry *old, struct kvm_kernel_irq_routing_entry *new); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS /* If we wakeup during the poll time, was it a sucessful poll? */ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return vcpu->valid_wakeup; } #else static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) { return true; } #endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ #ifdef CONFIG_HAVE_KVM_NO_POLL /* Callback that tells if we must not poll */ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu); #else static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) { return false; } #endif /* CONFIG_HAVE_KVM_NO_POLL */ void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { return 0; } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ #ifdef CONFIG_VIRT_XFER_TO_GUEST_WORK static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu) { vcpu->run->exit_reason = KVM_EXIT_INTR; vcpu->stat.signal_exits++; } static inline int kvm_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu) { int r = xfer_to_guest_mode_handle_work(); if (r) { WARN_ON_ONCE(r != -EINTR); kvm_handle_signal_exit(vcpu); } return r; } #endif /* CONFIG_VIRT_XFER_TO_GUEST_WORK */ /* * If more than one page is being (un)accounted, @virt must be the address of * the first page of a block of pages what were allocated together (i.e * accounted together). * * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state() * is thread-safe. */ static inline void kvm_account_pgtable_pages(void *virt, int nr) { mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr); } /* * This defines how many reserved entries we want to keep before we * kick the vcpu to the userspace to avoid dirty ring full. This * value can be tuned to higher if e.g. PML is enabled on the host. */ #define KVM_DIRTY_RING_RSVD_ENTRIES 64 /* Max number of entries allowed for each kvm dirty ring */ #define KVM_DIRTY_RING_MAX_ENTRIES 65536 static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t size, bool is_write, bool is_exec, bool is_private) { vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT; vcpu->run->memory_fault.gpa = gpa; vcpu->run->memory_fault.size = size; /* RWX flags are not (yet) defined or communicated to userspace. */ vcpu->run->memory_fault.flags = 0; if (is_private) vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE; } static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot) { if (!IS_ENABLED(CONFIG_KVM_GUEST_MEMFD)) return false; return slot->flags & KVM_MEMSLOT_GMEM_ONLY; } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) { return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; } #else static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return false; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ #ifdef CONFIG_KVM_GUEST_MEMFD int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order); #else static inline int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order) { KVM_BUG_ON(1, kvm); return -EIO; } #endif /* CONFIG_KVM_GUEST_MEMFD */ #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); #endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE /** * kvm_gmem_populate() - Populate/prepare a GPA range with guest data * * @kvm: KVM instance * @gfn: starting GFN to be populated * @src: userspace-provided buffer containing data to copy into GFN range * (passed to @post_populate, and incremented on each iteration * if not NULL). Must be page-aligned. * @npages: number of pages to copy from userspace-buffer * @post_populate: callback to issue for each gmem page that backs the GPA * range * @opaque: opaque data to pass to @post_populate callback * * This is primarily intended for cases where a gmem-backed GPA range needs * to be initialized with userspace-provided data prior to being mapped into * the guest as a private page. This should be called with the slots->lock * held so that caller-enforced invariants regarding the expected memory * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. * * Returns the number of pages that were populated. */ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, struct page *page, void *opaque); long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); #endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif #ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range); #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING int kvm_enable_virtualization(void); void kvm_disable_virtualization(void); #else static inline int kvm_enable_virtualization(void) { return 0; } static inline void kvm_disable_virtualization(void) { } #endif #endif |
| 67 68 69 396 27 207 566 567 92 567 565 567 567 566 567 565 92 92 92 12 84 42 550 550 549 551 52 53 53 7 8 51 52 1 4 4 5 5 5 5 739 1519 1521 1 1530 1529 1537 1526 108 711 1456 1354 1466 3 3 117 21 133 135 133 19 3 3 | 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 | // 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 <linux/file_ref.h> #include <net/sock.h> #include <linux/init_task.h> #include "internal.h" static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt) { /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } return __file_ref_put_badval(ref, cnt); } EXPORT_SYMBOL_GPL(__file_ref_put); 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)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * 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 inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * 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, fdt_words(ofdt)); } /* * 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". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; 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. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * 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. * * 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 = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cachep objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc_obj(struct fdtable, GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_objs(struct file *, nr, 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 ERR_PTR(-ENOMEM); } /* * 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; 0 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 + 1); /* 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 (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); 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 0; } /* * 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 on success. * 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 error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* Can we expand? */ if (unlikely(nr >= sysctl_nr_open)) return -EMFILE; /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { 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, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); 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); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * 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. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); 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, punch_hole); /* * 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); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * 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, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; /* * We may be racing against fd allocation from other threads using this * files_struct, despite holding ->file_lock. * * alloc_fd() might have already claimed a slot, while fd_install() * did not populate it yet. Note the latter operates locklessly, so * the file can show up as we are walking the array below. * * At the same time we know no files will disappear as all other * operations take the lock. * * Instead of trying to placate userspace racing with itself, we * ref the file if we see it and mark the fd slot as unused otherwise. */ for (i = open_files; i != 0; i--) { struct file *f = rcu_dereference_raw(*old_fds++); if (f) { get_file(f); } else { __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; } 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 = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } 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 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; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * 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. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; 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 (likely(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 (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(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 while it is being resized. * * We need to make sure our update to the array does not get lost as the resizing * thread can be copying the content as we modify it. * * We have two ways to do it: * - go off CPU waiting for resize_in_progress to clear * - take the spin lock * * The latter is trivial to implement and saves us from having to might_sleep() * for debugging purposes. * * This is moved out of line from fd_install() to convince gcc to optimize that * routine better. */ static void noinline fd_install_slowpath(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); } /** * fd_install - install a file pointer in the fd array * @fd: file descriptor to install the file in * @file: the file to install * * 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) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); fd_install_slowpath(fd, file); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = rcu_dereference_raw(fdt->fd[fd]); if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; struct fdtable *fdt; unsigned n; spin_lock(&files->file_lock); fdt = files_fdtable(files); n = last_fd(fdt); max_fd = min(max_fd, n); for (fd = find_next_bit(fdt->open_fds, max_fd + 1, fd); fd <= max_fd; fd = find_next_bit(fdt->open_fds, max_fd + 1, fd + 1)) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * 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) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); 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; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } 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 struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (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 ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * 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) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } 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); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * 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. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd 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) { if (!(file->f_mode & FMODE_ATOMIC_POS)) return false; if (__file_ref_read_raw(&file->f_ref) != FILE_REF_ONEREF) return true; if (file->f_op->iterate_shared) return true; return false; } bool file_seek_cur_needs_f_lock(struct file *file) { if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared) return false; /* * Note that we are not guaranteed to be called after fdget_pos() on * this file obj, in which case the caller is expected to provide the * appropriate locking. */ return true; } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (likely(file) && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } 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; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); 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; /* * dup2() is expected to close the file installed in the target fd slot * (if any). However, userspace hand-picking a fd may be racing against * its own threads which happened to allocate it in open() et al but did * not populate it yet. * * Broadly speaking we may be racing against the following: * fd = get_unused_fd_flags(); // fd slot reserved, ->fd[fd] == NULL * file = hard_work_goes_here(); * fd_install(fd, file); // only now ->fd[fd] == file * * It is an invariant that a successfully allocated fd has a NULL entry * in the array until the matching fd_install(). * * If we fit the window, we have the fd to populate, yet no target file * to close. Trying to ignore it and install our new file would violate * the invariant and make fd_install() overwrite our file. * * Things can be done(tm) to handle this. However, the issue does not * concern legitimate programs and we only need to make sure the kernel * does not trip over it. * * The simplest way out is to return an error if we find ourselves here. * * POSIX is silent on the issue, we return -EBUSY. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = rcu_dereference_raw(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, flags & O_CLOEXEC); 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(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; err = do_dup2(files, file, fd, flags); if (err < 0) return err; return 0; out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @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(struct file *file, int __user *ufd, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; FD_PREPARE(fdf, o_flags, file); if (fdf.err) return fdf.err; get_file(file); if (ufd) { error = put_user(fd_prepare_fd(fdf), ufd); if (error) return error; } __receive_sock(fd_prepare_file(fdf)); return fd_publish(fdf); } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __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 = files_lookup_fd_locked(files, 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; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); 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) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, 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); |
| 16 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_IP6_ROUTE_H #define _NET_IP6_ROUTE_H #include <net/addrconf.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <net/sock.h> #include <net/lwtunnel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/route.h> #include <net/nexthop.h> struct route_info { __u8 type; __u8 length; __u8 prefix_len; #if defined(__BIG_ENDIAN_BITFIELD) __u8 reserved_h:3, route_pref:2, reserved_l:3; #elif defined(__LITTLE_ENDIAN_BITFIELD) __u8 reserved_l:3, route_pref:2, reserved_h:3; #endif __be32 lifetime; __u8 prefix[]; /* 0,8 or 16 */ }; #define RT6_LOOKUP_F_IFACE 0x00000001 #define RT6_LOOKUP_F_REACHABLE 0x00000002 #define RT6_LOOKUP_F_HAS_SADDR 0x00000004 #define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 #define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 #define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 #define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040 #define RT6_LOOKUP_F_DST_NOREF 0x00000080 /* We do not (yet ?) support IPv6 jumbograms (RFC 2675) * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header */ #define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr)) /* * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate * between IPV6_ADDR_PREFERENCES socket option values * IPV6_PREFER_SRC_TMP = 0x1 * IPV6_PREFER_SRC_PUBLIC = 0x2 * IPV6_PREFER_SRC_COA = 0x4 * and above RT6_LOOKUP_F_SRCPREF_xxx flags. */ static inline int rt6_srcprefs2flags(unsigned int srcprefs) { return (srcprefs & IPV6_PREFER_SRC_MASK) << 3; } static inline unsigned int rt6_flags2srcprefs(int flags) { return (flags >> 3) & IPV6_PREFER_SRC_MASK; } static inline bool rt6_need_strict(const struct in6_addr *daddr) { return ipv6_addr_type(daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } /* fib entries using a nexthop object can not be coalesced into * a multipath route */ static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { /* the RTF_ADDRCONF flag filters out RA's */ return !(f6i->fib6_flags & RTF_ADDRCONF) && !f6i->nh && f6i->fib6_nh->fib_nh_gw_family; } void ip6_route_input(struct sk_buff *skb); struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags); static inline struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { return ip6_route_output_flags(net, sk, fl6, 0); } /* Only conditionally release dst if flags indicates * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list. */ static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags) { if (!(flags & RT6_LOOKUP_F_DST_NOREF) || !list_empty(&rt->dst.rt_uncached)) ip6_rt_put(rt); } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags); struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int ifindex, struct flowi6 *fl6, const struct sk_buff *skb, int flags); void ip6_route_init_special_entries(void); int ip6_route_init(void); void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg); int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); int ip6_ins_rt(struct net *net, struct fib6_info *f6i); int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify); void rt6_flush_exceptions(struct fib6_info *f6i); void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now); static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i, const struct in6_addr *daddr, unsigned int prefs, int l3mdev_index, struct in6_addr *saddr) { struct net_device *l3mdev; struct net_device *dev; bool same_vrf; int err = 0; rcu_read_lock(); l3mdev = dev_get_by_index_rcu(net, l3mdev_index); if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev) dev = f6i ? fib6_info_nh_dev(f6i) : NULL; same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev; if (f6i && f6i->fib6_prefsrc.plen && same_vrf) *saddr = f6i->fib6_prefsrc.addr; else err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr); rcu_read_unlock(); return err; } struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int flags); u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *hkeys); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); void fib6_force_start_gc(struct net *net); struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack); struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags); /* * support functions for ND * */ struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev); struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime); void rt6_purge_dflt_routers(struct net *net); int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr); void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu); void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif); void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk); struct netlink_callback; struct rt6_rtnl_dump_arg { struct sk_buff *skb; struct netlink_callback *cb; struct net *net; struct fib_dump_filter filter; }; int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned char nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct fib6_info *f6i); void rt6_uncached_list_add(struct rt6_info *rt); void rt6_uncached_list_del(struct rt6_info *rt); static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); if (dst) return dst_rt6_info(dst); return NULL; } /* * Store a destination cache entry in a socket */ static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, bool daddr_set, bool saddr_set) { struct ipv6_pinfo *np = inet6_sk(sk); np->dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); sk_setup_caps(sk, dst); np->daddr_cache = daddr_set; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr_set; #endif } void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6); static inline bool ipv6_unicast_destination(const struct sk_buff *skb) { const struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); return rt->rt6i_flags & RTF_LOCAL; } static inline bool ipv6_anycast_destination(const struct dst_entry *dst, const struct in6_addr *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return rt->rt6i_flags & RTF_ANYCAST || (rt->rt6i_dst.plen < 127 && !(rt->rt6i_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) && ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Variant of dst_mtu() for IPv6 users */ static inline u32 dst6_mtu(const struct dst_entry *dst) { return INDIRECT_CALL_1(dst->ops->mtu, ip6_mtu, dst); } static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) { const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; const struct dst_entry *dst = skb_dst(skb); unsigned int mtu; if (np && READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE) { mtu = READ_ONCE(dst_dev(dst)->mtu); mtu -= lwtunnel_headroom(dst->lwtstate, mtu); } else { mtu = dst_mtu(dst); } return mtu; } static inline bool ip6_sk_accept_pmtu(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc != IPV6_PMTUDISC_INTERFACE && pmtudisc != IPV6_PMTUDISC_OMIT; } static inline bool ip6_sk_ignore_df(const struct sock *sk) { u8 pmtudisc = READ_ONCE(inet6_sk(sk)->pmtudisc); return pmtudisc < IPV6_PMTUDISC_DO || pmtudisc == IPV6_PMTUDISC_OMIT; } static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, const struct in6_addr *daddr) { if (rt->rt6i_flags & RTF_GATEWAY) return &rt->rt6i_gateway; else if (unlikely(rt->rt6i_flags & RTF_CACHE)) return &rt->rt6i_dst.addr; else return daddr; } static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) { struct fib6_nh *nha, *nhb; if (a->nh || b->nh) return nexthop_cmp(a->nh, b->nh); nha = a->fib6_nh; nhb = b->fib6_nh; return nha->fib_nh_dev == nhb->fib_nh_dev && ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) && !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws); } static inline unsigned int ip6_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct inet6_dev *idev; unsigned int mtu; if (!forwarding || dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; } mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst_dev_rcu(dst)); if (idev) mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr); #endif |
| 86 264 260 263 264 264 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006, Thomas Gleixner, Russell King * * This file contains the interrupt descriptor management code. Detailed * information is available in Documentation/core-api/genericirq.rst * */ #include <linux/irq.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/maple_tree.h> #include <linux/irqdomain.h> #include <linux/sysfs.h> #include <linux/string_choices.h> #include "internals.h" /* * lockdep: we want to handle all irq_desc locks as a single lock-class: */ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) static int __init irq_affinity_setup(char *str) { alloc_bootmem_cpumask_var(&irq_default_affinity); cpulist_parse(str, irq_default_affinity); /* * Set at least the boot cpu. We don't want to end up with * bugreports caused by random commandline masks */ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); return 1; } __setup("irqaffinity=", irq_affinity_setup); static void __init init_irq_default_affinity(void) { if (!cpumask_available(irq_default_affinity)) zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); if (cpumask_empty(irq_default_affinity)) cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) { } #endif #ifdef CONFIG_SMP static int alloc_masks(struct irq_desc *desc, int node) { if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity, GFP_KERNEL, node)) return -ENOMEM; #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK if (!zalloc_cpumask_var_node(&desc->irq_common_data.effective_affinity, GFP_KERNEL, node)) { free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif #ifdef CONFIG_GENERIC_PENDING_IRQ if (!zalloc_cpumask_var_node(&desc->pending_mask, GFP_KERNEL, node)) { #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif return 0; } static void irq_redirect_work(struct irq_work *work) { handle_irq_desc(container_of(work, struct irq_desc, redirect.work)); } static void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { if (!affinity) affinity = irq_default_affinity; cpumask_copy(desc->irq_common_data.affinity, affinity); #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_clear(desc->pending_mask); #endif #ifdef CONFIG_NUMA desc->irq_common_data.node = node; #endif desc->redirect.work = IRQ_WORK_INIT_HARD(irq_redirect_work); } static void free_masks(struct irq_desc *desc) { #ifdef CONFIG_GENERIC_PENDING_IRQ free_cpumask_var(desc->pending_mask); #endif free_cpumask_var(desc->irq_common_data.affinity); #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif } #else static inline int alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } static inline void free_masks(struct irq_desc *desc) { } #endif static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, const struct cpumask *affinity, struct module *owner) { desc->irq_common_data.handler_data = NULL; desc->irq_common_data.msi_desc = NULL; desc->irq_data.common = &desc->irq_common_data; desc->irq_data.irq = irq; desc->irq_data.chip = &no_irq_chip; desc->irq_data.chip_data = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); desc->handle_irq = handle_bad_irq; desc->depth = 1; desc->irq_count = 0; desc->irqs_unhandled = 0; desc->tot_count = 0; desc->name = NULL; desc->owner = owner; desc_smp_init(desc, node, affinity); } static unsigned int nr_irqs = NR_IRQS; /** * irq_get_nr_irqs() - Number of interrupts supported by the system. */ unsigned int irq_get_nr_irqs(void) { return nr_irqs; } EXPORT_SYMBOL_GPL(irq_get_nr_irqs); /** * irq_set_nr_irqs() - Set the number of interrupts supported by the system. * @nr: New number of interrupts. * * Return: @nr. */ unsigned int irq_set_nr_irqs(unsigned int nr) { nr_irqs = nr; return nr; } EXPORT_SYMBOL_GPL(irq_set_nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | MT_FLAGS_USE_RCU, sparse_irq_lock); static int irq_find_free_area(unsigned int from, unsigned int cnt) { MA_STATE(mas, &sparse_irqs, 0, 0); if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt)) return -ENOSPC; return mas.index; } static unsigned int irq_find_at_or_after(unsigned int offset) { unsigned long index = offset; struct irq_desc *desc; guard(rcu)(); desc = mt_find(&sparse_irqs, &index, nr_irqs); return desc ? irq_desc_get_irq(desc) : nr_irqs; } static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) { MA_STATE(mas, &sparse_irqs, irq, irq); WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0); } static void delete_irq_desc(unsigned int irq) { MA_STATE(mas, &sparse_irqs, irq, irq); mas_erase(&mas); } #ifdef CONFIG_SPARSE_IRQ static const struct kobj_type irq_kobj_type; #endif static int init_desc(struct irq_desc *desc, int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { desc->kstat_irqs = alloc_percpu(struct irqstat); if (!desc->kstat_irqs) return -ENOMEM; if (alloc_masks(desc, node)) { free_percpu(desc->kstat_irqs); return -ENOMEM; } raw_spin_lock_init(&desc->lock); lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); irq_resend_init(desc); #ifdef CONFIG_SPARSE_IRQ kobject_init(&desc->kobj, &irq_kobj_type); init_rcu_head(&desc->rcu); #endif return 0; } #ifdef CONFIG_SPARSE_IRQ static void irq_kobj_release(struct kobject *kobj); #ifdef CONFIG_SYSFS static struct kobject *irq_kobj_base; #define IRQ_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) static ssize_t per_cpu_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; char *p = ""; int cpu; for_each_possible_cpu(cpu) { unsigned int c = irq_desc_kstat_cpu(desc, cpu); ret += sysfs_emit_at(buf, ret, "%s%u", p, c); p = ","; } ret += sysfs_emit_at(buf, ret, "\n"); return ret; } IRQ_ATTR_RO(per_cpu_count); static ssize_t chip_name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); guard(raw_spinlock_irq)(&desc->lock); if (desc->irq_data.chip && desc->irq_data.chip->name) return sysfs_emit(buf, "%s\n", desc->irq_data.chip->name); return 0; } IRQ_ATTR_RO(chip_name); static ssize_t hwirq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); guard(raw_spinlock_irq)(&desc->lock); if (desc->irq_data.domain) return sysfs_emit(buf, "%lu\n", desc->irq_data.hwirq); return 0; } IRQ_ATTR_RO(hwirq); static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); guard(raw_spinlock_irq)(&desc->lock); return sysfs_emit(buf, "%s\n", irqd_is_level_type(&desc->irq_data) ? "level" : "edge"); } IRQ_ATTR_RO(type); static ssize_t wakeup_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); guard(raw_spinlock_irq)(&desc->lock); return sysfs_emit(buf, "%s\n", str_enabled_disabled(irqd_is_wakeup_set(&desc->irq_data))); } IRQ_ATTR_RO(wakeup); static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); guard(raw_spinlock_irq)(&desc->lock); if (desc->name) return sysfs_emit(buf, "%s\n", desc->name); return 0; } IRQ_ATTR_RO(name); static ssize_t actions_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); struct irqaction *action; ssize_t ret = 0; char *p = ""; scoped_guard(raw_spinlock_irq, &desc->lock) { for_each_action_of_desc(desc, action) { ret += sysfs_emit_at(buf, ret, "%s%s", p, action->name); p = ","; } } if (ret) ret += sysfs_emit_at(buf, ret, "\n"); return ret; } IRQ_ATTR_RO(actions); static struct attribute *irq_attrs[] = { &per_cpu_count_attr.attr, &chip_name_attr.attr, &hwirq_attr.attr, &type_attr.attr, &wakeup_attr.attr, &name_attr.attr, &actions_attr.attr, NULL }; ATTRIBUTE_GROUPS(irq); static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = irq_groups, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) { if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing * crucial and failures in the late irq_sysfs_init() * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); else desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* * Only invoke kobject_del() when kobject_add() was successfully * invoked for the descriptor. This covers both early boot, where * sysfs is not initialized yet, and the case of a failed * kobject_add() invocation. */ if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } static int __init irq_sysfs_init(void) { struct irq_desc *desc; int irq; /* Prevent concurrent irq alloc/free */ guard(mutex)(&sparse_irq_lock); irq_kobj_base = kobject_create_and_add("irq", kernel_kobj); if (!irq_kobj_base) return -ENOMEM; /* Add the already allocated interrupts */ for_each_irq_desc(irq, desc) irq_sysfs_add(irq, desc); return 0; } postcore_initcall(irq_sysfs_init); #else /* !CONFIG_SYSFS */ static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) {} static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ struct irq_desc *irq_to_desc(unsigned int irq) { return mtree_load(&sparse_irqs, irq); } #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE EXPORT_SYMBOL_GPL(irq_to_desc); #endif void irq_lock_sparse(void) { mutex_lock(&sparse_irq_lock); } void irq_unlock_sparse(void) { mutex_unlock(&sparse_irq_lock); } static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { struct irq_desc *desc; int ret; desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; ret = init_desc(desc, irq, node, flags, affinity, owner); if (unlikely(ret)) { kfree(desc); return NULL; } return desc; } static void irq_kobj_release(struct kobject *kobj) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); free_masks(desc); free_percpu(desc->kstat_irqs); kfree(desc); } static void delayed_free_desc(struct rcu_head *rhp) { struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu); kobject_put(&desc->kobj); } static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); irq_remove_debugfs_entry(desc); unregister_irq_proc(irq, desc); /* * sparse_irq_lock protects also show_interrupts() and * kstat_irq_usr(). Once we deleted the descriptor from the * sparse tree we can free it. Access in proc will fail to * lookup the descriptor. * * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ irq_sysfs_del(desc); delete_irq_desc(irq); /* * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } static int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { struct irq_desc *desc; int i; /* Validate affinity mask(s) */ if (affinity) { for (i = 0; i < cnt; i++) { if (cpumask_empty(&affinity[i].mask)) return -EINVAL; } } for (i = 0; i < cnt; i++) { const struct cpumask *mask = NULL; unsigned int flags = 0; if (affinity) { if (affinity->is_managed) { flags = IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN; } flags |= IRQD_AFFINITY_SET; mask = &affinity->mask; node = cpu_to_node(cpumask_first(mask)); affinity++; } desc = alloc_desc(start + i, node, flags, mask, owner); if (!desc) goto err; irq_insert_desc(start + i, desc); irq_sysfs_add(start + i, desc); irq_add_debugfs_entry(start + i, desc); } return start; err: for (i--; i >= 0; i--) free_desc(start + i); return -ENOMEM; } static bool irq_expand_nr_irqs(unsigned int nr) { if (nr > MAX_SPARSE_IRQS) return false; nr_irqs = nr; return true; } int __init early_irq_init(void) { int i, initcnt, node = first_online_node; struct irq_desc *desc; init_irq_default_affinity(); /* Let arch update nr_irqs and return the nr of preallocated irqs */ initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", NR_IRQS, nr_irqs, initcnt); if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) nr_irqs = MAX_SPARSE_IRQS; if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) initcnt = MAX_SPARSE_IRQS; if (initcnt > nr_irqs) nr_irqs = initcnt; for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); irq_insert_desc(i, desc); } return arch_early_irq_init(); } #else /* !CONFIG_SPARSE_IRQ */ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { [0 ... NR_IRQS-1] = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), } }; int __init early_irq_init(void) { int count, i, node = first_online_node; int ret; init_irq_default_affinity(); printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL); if (unlikely(ret)) goto __free_desc_res; } return arch_early_irq_init(); __free_desc_res: while (--i >= 0) { free_masks(irq_desc + i); free_percpu(irq_desc[i].kstat_irqs); } return ret; } struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); int cpu; scoped_guard(raw_spinlock_irqsave, &desc->lock) desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL); for_each_possible_cpu(cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { }; delete_irq_desc(irq); } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { u32 i; for (i = 0; i < cnt; i++) { struct irq_desc *desc = irq_to_desc(start + i); desc->owner = owner; irq_insert_desc(start + i, desc); } return start; } static inline bool irq_expand_nr_irqs(unsigned int nr) { return false; } void irq_mark_irq(unsigned int irq) { guard(mutex)(&sparse_irq_lock); irq_insert_desc(irq, irq_desc + irq); } #endif /* !CONFIG_SPARSE_IRQ */ int handle_irq_desc(struct irq_desc *desc) { struct irq_data *data; if (!desc) return -EINVAL; data = irq_desc_get_irq_data(desc); if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); return 0; } /** * generic_handle_irq - Invoke the handler for a particular irq * @irq: The irq number to handle * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_irq(unsigned int irq) { return handle_irq_desc(irq_to_desc(irq)); } EXPORT_SYMBOL_GPL(generic_handle_irq); /** * generic_handle_irq_safe - Invoke the handler for a particular irq from any * context. * @irq: The irq number to handle * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process context). It * will report an error if not invoked from IRQ context and the irq has been * marked to enforce IRQ-context only. */ int generic_handle_irq_safe(unsigned int irq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_to_desc(irq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_irq_safe); #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_domain_irq(struct irq_domain *domain, irq_hw_number_t hwirq) { return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); /** * generic_handle_irq_safe - Invoke the handler for a HW irq belonging * to a domain from any context. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process * context). If the interrupt is marked as 'enforce IRQ-context only' then * the function must be invoked from hard interrupt context. */ int generic_handle_domain_irq_safe(struct irq_domain *domain, irq_hw_number_t hwirq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe); /** * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an NMI context with irq regs * initialized. **/ int generic_handle_domain_nmi(struct irq_domain *domain, irq_hw_number_t hwirq) { WARN_ON_ONCE(!in_nmi()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } #ifdef CONFIG_SMP static bool demux_redirect_remote(struct irq_desc *desc) { guard(raw_spinlock)(&desc->lock); const struct cpumask *m = irq_data_get_effective_affinity_mask(&desc->irq_data); unsigned int target_cpu = READ_ONCE(desc->redirect.target_cpu); if (desc->irq_data.chip->irq_pre_redirect) desc->irq_data.chip->irq_pre_redirect(&desc->irq_data); /* * If the interrupt handler is already running on a CPU that's included * in the interrupt's affinity mask, redirection is not necessary. */ if (cpumask_test_cpu(smp_processor_id(), m)) return false; /* * The desc->action check protects against IRQ shutdown: __free_irq() sets * desc->action to NULL while holding desc->lock, which we also hold. * * Calling irq_work_queue_on() here is safe w.r.t. CPU unplugging: * - takedown_cpu() schedules multi_cpu_stop() on all active CPUs, * including the one that's taken down. * - multi_cpu_stop() acts like a barrier, which means all active * CPUs go through MULTI_STOP_DISABLE_IRQ and disable hard IRQs * *before* the dying CPU runs take_cpu_down() in MULTI_STOP_RUN. * - Hard IRQs are re-enabled at the end of multi_cpu_stop(), *after* * the dying CPU has run take_cpu_down() in MULTI_STOP_RUN. * - Since we run in hard IRQ context, we run either before or after * take_cpu_down() but never concurrently. * - If we run before take_cpu_down(), the dying CPU hasn't been marked * offline yet (it's marked via take_cpu_down() -> __cpu_disable()), * so the WARN in irq_work_queue_on() can't occur. * - Furthermore, the work item we queue will be flushed later via * take_cpu_down() -> cpuhp_invoke_callback_range_nofail() -> * smpcfd_dying_cpu() -> irq_work_run(). * - If we run after take_cpu_down(), target_cpu has been already * updated via take_cpu_down() -> __cpu_disable(), which eventually * calls irq_do_set_affinity() during IRQ migration. So, target_cpu * no longer points to the dying CPU in this case. */ if (desc->action) irq_work_queue_on(&desc->redirect.work, target_cpu); return true; } #else /* CONFIG_SMP */ static bool demux_redirect_remote(struct irq_desc *desc) { return false; } #endif /** * generic_handle_demux_domain_irq - Invoke the handler for a hardware interrupt * of a demultiplexing domain. * @domain: The domain where to perform the lookup * @hwirq: The hardware interrupt number to convert to a logical one * * Returns: True on success, or false if lookup has failed */ bool generic_handle_demux_domain_irq(struct irq_domain *domain, irq_hw_number_t hwirq) { struct irq_desc *desc = irq_resolve_mapping(domain, hwirq); if (unlikely(!desc)) return false; if (demux_redirect_remote(desc)) return true; return !handle_irq_desc(desc); } EXPORT_SYMBOL_GPL(generic_handle_demux_domain_irq); #endif /* Dynamic interrupt handling */ /** * irq_free_descs - free irq descriptors * @from: Start of descriptor range * @cnt: Number of consecutive irqs to free */ void irq_free_descs(unsigned int from, unsigned int cnt) { int i; if (from >= nr_irqs || (from + cnt) > nr_irqs) return; guard(mutex)(&sparse_irq_lock); for (i = 0; i < cnt; i++) free_desc(from + i); } EXPORT_SYMBOL_GPL(irq_free_descs); /** * __irq_alloc_descs - allocate and initialize a range of irq descriptors * @irq: Allocate for specific irq number if irq >= 0 * @from: Start the search from this irq number * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated * @owner: Owning module (can be NULL) * @affinity: Optional pointer to an affinity mask array of size @cnt which * hints where the irq descriptors should be allocated and which * default affinities to use * * Returns the first irq number or error code */ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct irq_affinity_desc *affinity) { int start; if (!cnt) return -EINVAL; if (irq >= 0) { if (from > irq) return -EINVAL; from = irq; } else { /* * For interrupts which are freely allocated the * architecture can force a lower bound to the @from * argument. x86 uses this to exclude the GSI space. */ from = arch_dynirq_lower_bound(from); } guard(mutex)(&sparse_irq_lock); start = irq_find_free_area(from, cnt); if (irq >=0 && start != irq) return -EEXIST; if (start + cnt > nr_irqs) { if (!irq_expand_nr_irqs(start + cnt)) return -ENOMEM; } return alloc_descs(start, cnt, node, affinity, owner); } EXPORT_SYMBOL_GPL(__irq_alloc_descs); /** * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * * Returns next irq number after offset or nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { return irq_find_at_or_after(offset); } struct irq_desc *__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check) { struct irq_desc *desc; desc = irq_to_desc(irq); if (!desc) return NULL; if (check & _IRQ_DESC_CHECK) { if ((check & _IRQ_DESC_PERCPU) && !irq_settings_is_per_cpu_devid(desc)) return NULL; if (!(check & _IRQ_DESC_PERCPU) && irq_settings_is_per_cpu_devid(desc)) return NULL; } if (bus) chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, *flags); return desc; } void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) __releases(&desc->lock) { raw_spin_unlock_irqrestore(&desc->lock, flags); if (bus) chip_bus_sync_unlock(desc); } int irq_set_percpu_devid(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || desc->percpu_enabled) return -EINVAL; desc->percpu_enabled = kzalloc_obj(*desc->percpu_enabled); if (!desc->percpu_enabled) return -ENOMEM; irq_set_percpu_devid_flags(irq); return 0; } void kstat_incr_irq_this_cpu(unsigned int irq) { kstat_incr_irqs_this_cpu(irq_to_desc(irq)); } /** * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu * @irq: The interrupt number * @cpu: The cpu number * * Returns the sum of interrupt counts on @cpu since boot for * @irq. The caller must ensure that the interrupt is not removed * concurrently. */ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask) { unsigned int sum = 0; int cpu; if (!irq_settings_is_per_cpu_devid(desc) && !irq_settings_is_per_cpu(desc) && !irq_is_nmi(desc)) return data_race(desc->tot_count); for_each_cpu(cpu, cpumask) sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu)); return sum; } static unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return kstat_irqs_desc(desc, cpu_possible_mask); } #ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT void kstat_snapshot_irqs(void) { struct irq_desc *desc; unsigned int irq; for_each_irq_desc(irq, desc) { if (!desc->kstat_irqs) continue; this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt)); } } unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref); } #endif /** * kstat_irqs_usr - Get the statistics for an interrupt from thread context * @irq: The interrupt number * * Returns the sum of interrupt counts on all cpus since boot for @irq. * * It uses rcu to protect the access since a concurrent removal of an * interrupt descriptor is observing an rcu grace period before * delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; rcu_read_lock(); sum = kstat_irqs(irq); rcu_read_unlock(); return sum; } #ifdef CONFIG_LOCKDEP void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, struct lock_class_key *request_class) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { lockdep_set_class(&desc->lock, lock_class); lockdep_set_class(&desc->request_mutex, request_class); } } EXPORT_SYMBOL_GPL(__irq_set_lockdep_class); #endif |
| 1 74 75 75 75 11 69 11 75 75 74 75 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/kstack_erase.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/io_uring_types.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <linux/unwind_deferred.h> #include <linux/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> /* For dup_mmap(). */ #include "../mm/internal.h" #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); /* * Allocated stacks are cached and later reused by new threads, so memcg * accounting is performed by the code assigning/releasing stacks to tasks. * We need a zeroed memory without __GFP_ACCOUNT. */ #define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO) struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node) { struct vm_struct *vm_area; unsigned int i; /* * If the node has memory, we are guaranteed the stacks are backed by local pages. * Otherwise the pages are arbitrary. * * Note that depending on cpuset it is possible we will get migrated to a different * node immediately after allocating here, so this does *not* guarantee locality for * arbitrary callers. */ scoped_guard(preempt) { if (node != NUMA_NO_NODE && numa_node_id() != node) return NULL; for (i = 0; i < NR_CACHED_STACKS; i++) { vm_area = this_cpu_xchg(cached_stacks[i], NULL); if (vm_area) return vm_area; } } return NULL; } static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area) { unsigned int i; int nid; /* * Don't cache stacks if any of the pages don't match the local domain, unless * there is no local memory to begin with. * * Note that lack of local memory does not automatically mean it makes no difference * performance-wise which other domain backs the stack. In this case we are merely * trying to avoid constantly going to vmalloc. */ scoped_guard(preempt) { nid = numa_node_id(); if (node_state(nid, N_MEMORY)) { for (i = 0; i < vm_area->nr_pages; i++) { struct page *page = vm_area->pages[i]; if (page_to_nid(page) != nid) return false; } } for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) return true; } } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); struct vm_struct *vm_area = vm_stack->stack_vm_area; if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_area->addr); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_area = cached_vm_stack_areas[i]; if (!vm_area) continue; vfree(vm_area->addr); cached_vm_stack_areas[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm_area) { int i; int ret; int nr_charged = 0; BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm_area; void *stack; vm_area = alloc_thread_stack_node_from_cache(tsk, node); if (vm_area) { if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; } /* Reset stack metadata. */ kasan_unpoison_range(vm_area->addr, THREAD_SIZE); stack = kasan_reset_tag(vm_area->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); tsk->stack_vm_area = vm_area; tsk->stack = stack; return 0; } stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_VMAP_STACK, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm_area = find_vm_area(stack); if (memcg_charge_kernel_stack(vm_area)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm_area; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } #else /* !CONFIG_VMAP_STACK */ /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ #if THREAD_SIZE >= PAGE_SIZE static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } #else /* !(THREAD_SIZE >= PAGE_SIZE) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } #endif /* THREAD_SIZE >= PAGE_SIZE */ #endif /* CONFIG_VMAP_STACK */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area; int i; vm_area = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && exe_file_deny_write_access(exe_file)) pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ #ifdef CONFIG_MM_ID static DEFINE_IDA(mm_ida); static inline int mm_alloc_id(struct mm_struct *mm) { int ret; ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL); if (ret < 0) return ret; mm->mm_id = ret; return 0; } static inline void mm_free_id(struct mm_struct *mm) { const mm_id_t id = mm->mm_id; mm->mm_id = MM_ID_DUMMY; if (id == MM_ID_DUMMY) return; if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX)) return; ida_free(&mm_ida, id); } #else /* !CONFIG_MM_ID */ static inline int mm_alloc_id(struct mm_struct *mm) { return 0; } static inline void mm_free_id(struct mm_struct *mm) {} #endif /* CONFIG_MM_ID */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) { pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld Comm:%s Pid:%d\n", mm, resident_page_types[i], x, current->comm, task_pid_nr(current)); } } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); unwind_task_free(tsk); io_uring_free(tsk); cgroup_task_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid.cid = MM_CID_UNSET; tsk->mm_cid.active = 0; INIT_HLIST_NODE(&tsk->mm_cid.node); #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; arch_uprobe_init_state(mm); #endif } static void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); mm_lock_seqcount_init(mm); #ifdef CONFIG_PER_VMA_LOCK rcuwait_init(&mm->vma_writer_wait); #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); mm_flags_clear_all(mm); if (current->mm) { unsigned long flags = __mm_flags_get_word(current->mm); __mm_flags_overwrite_word(mm, mmf_init_legacy_flags(flags)); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { __mm_flags_overwrite_word(mm, default_dump_filter); mm->def_flags = 0; } if (futex_mm_init(mm)) goto fail_mm_init; if (mm_alloc_pgd(mm)) goto fail_nopgd; if (mm_alloc_id(mm)) goto fail_noid; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_id(mm); fail_noid: mm_free_pgd(mm); fail_nopgd: futex_hash_free(mm); fail_mm_init: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); futex_hash_free(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with kthread_use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) mmget(mm); task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); static bool may_access_mm(struct mm_struct *mm, struct task_struct *task, unsigned int mode) { if (mm == current->mm) return true; if (ptrace_may_access(task, mode)) return true; if ((mode & PTRACE_MODE_READ) && perfmon_capable()) return true; return false; } struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (!mm) { mm = ERR_PTR(-ESRCH); } else if (!may_access_mm(mm, task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); if (err) uprobe_end_dup_mmap(); fail_nomem: return NULL; } static int copy_mm(u64 clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; return 0; } static int copy_fs(u64 clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ read_seqlock_excl(&fs->seq); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { read_sequnlock_excl(&fs->seq); return -EAGAIN; } fs->users++; read_sequnlock_excl(&fs->seq); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(u64 clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_sighand(u64 clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(u64 clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL); #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); #ifdef CONFIG_CGROUPS init_rwsem(&sig->cgroup_threadgroup_rwsem); #endif sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret_file: return the new pidfs file * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file) { struct file *pidfs_file; /* * PIDFD_STALE is only allowed to be passed if the caller knows * that @pid is already registered in pidfs and thus * PIDFD_INFO_EXIT information is guaranteed to be available. */ if (!(flags & PIDFD_STALE)) { /* * While holding the pidfd waitqueue lock removing the * task linkage for the thread-group leader pid * (PIDTYPE_TGID) isn't possible. Thus, if there's still * task linkage for PIDTYPE_PID not having thread-group * leader linkage for the pid means it wasn't a * thread-group leader in the first place. */ guard(spinlock_irq)(&pid->wait_pidfd.lock); /* Task has already been reaped. */ if (!pid_has_task(pid, PIDTYPE_PID)) return -ESRCH; /* * If this struct pid isn't used as a thread-group * leader but the caller requested to create a * thread-group leader pidfd then report ENOENT. */ if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID)) return -ENOENT; } CLASS(get_unused_fd, pidfd)(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfs_file)) return PTR_ERR(pidfs_file); *ret_file = pidfs_file; return take_fd(pidfd); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); mm_flags_set(MMF_MULTIPROCESS, tsk->mm); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { memset(&p->rv, 0, sizeof(p->rv)); } #else #define rv_task_fork(p) do {} while (0) #endif static bool need_futex_hash_allocate_default(u64 clone_flags) { if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM)) return false; return true; } /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * TID is cleared in mm_release() when the task exits */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; retval = io_uring_fork(p); if (unlikely(retval)) goto bad_fork_cleanup_delayacct; retval = -EAGAIN; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; lockdep_init_task(p); p->blocked_on = NULL; /* not blocked yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif unwind_task_init(p); /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * Allocate a default futex hash for the user process once the first * thread spawns. */ if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) goto bad_fork_cancel_cgroup; /* * If we fail beyond this point we don't free the allocated * futex hash map. We assume that another thread will be created * and makes use of it. The hash map will be freed once the main * thread terminates. */ } /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_nsproxy_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_sched_cancel_fork: sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: io_uring_free(p); delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_cred_namespaces(p); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO|CLONE_VM|CLONE_UNTRACED; struct kernel_clone_args args = { .flags = flags, .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (flags & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (flags & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; read_seqlock_excl(&fs->seq); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; read_sequnlock_excl(&fs->seq); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } static int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } static const struct ctl_table fork_sysctl_table[] = { { .procname = "threads-max", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = sysctl_max_threads, }, }; static int __init init_fork_sysctl(void) { register_sysctl_init("kernel", fork_sysctl_table); return 0; } subsys_initcall(init_fork_sysctl); |
| 7 134 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A security context is a set of security attributes * associated with each subject and object controlled * by the security policy. Security contexts are * externally represented as variable-length strings * that can be interpreted by a user or application * with an understanding of the security policy. * Internally, the security server uses a simple * structure. This structure is private to the * security server and can be changed without affecting * clients of the security server. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_CONTEXT_H_ #define _SS_CONTEXT_H_ #include "ebitmap.h" #include "mls_types.h" #include "security.h" /* * A security context consists of an authenticated user * identity, a role, a type and a MLS range. */ struct context { u32 user; u32 role; u32 type; u32 len; /* length of string in bytes */ struct mls_range range; char *str; /* string representation if context cannot be mapped. */ }; static inline void mls_context_init(struct context *c) { memset(&c->range, 0, sizeof(c->range)); } static inline int mls_context_cpy(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the low level of 'src'. */ static inline int mls_context_cpy_low(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the high level of 'src'. */ static inline int mls_context_cpy_high(struct context *dst, const struct context *src) { int rc; dst->range.level[0].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } static inline int mls_context_glblub(struct context *dst, const struct context *c1, const struct context *c2) { struct mls_range *dr = &dst->range; const struct mls_range *r1 = &c1->range, *r2 = &c2->range; int rc = 0; if (r1->level[1].sens < r2->level[0].sens || r2->level[1].sens < r1->level[0].sens) /* These ranges have no common sensitivities */ return -EINVAL; /* Take the greatest of the low */ dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens); /* Take the least of the high */ dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens); rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat, &r2->level[0].cat); if (rc) goto out; rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat, &r2->level[1].cat); if (rc) goto out; out: return rc; } static inline bool mls_context_equal(const struct context *c1, const struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && ebitmap_equal(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && ebitmap_equal(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) { ebitmap_destroy(&c->range.level[0].cat); ebitmap_destroy(&c->range.level[1].cat); mls_context_init(c); } static inline void context_init(struct context *c) { memset(c, 0, sizeof(*c)); } static inline int context_cpy(struct context *dst, const struct context *src) { int rc; dst->user = src->user; dst->role = src->role; dst->type = src->type; if (src->str) { dst->str = kstrdup(src->str, GFP_ATOMIC); if (!dst->str) return -ENOMEM; dst->len = src->len; } else { dst->str = NULL; dst->len = 0; } rc = mls_context_cpy(dst, src); if (rc) { kfree(dst->str); dst->str = NULL; dst->len = 0; return rc; } return 0; } static inline void context_destroy(struct context *c) { c->user = c->role = c->type = 0; kfree(c->str); c->str = NULL; c->len = 0; mls_context_destroy(c); } static inline bool context_equal(const struct context *c1, const struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && (c1->type == c2->type) && mls_context_equal(c1, c2)); } u32 context_compute_hash(const struct context *c); #endif /* _SS_CONTEXT_H_ */ |
| 10 135 136 136 136 136 9 9 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003 Tresys Technology, LLC * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" #include "hash.h" static struct kmem_cache *avtab_node_cachep __ro_after_init; static struct kmem_cache *avtab_xperms_cachep __ro_after_init; static inline u32 avtab_hash(const struct avtab_key *keyp, u32 mask) { return av_hash((u32)keyp->target_class, (u32)keyp->target_type, (u32)keyp->source_type, mask); } static struct avtab_node *avtab_insert_node(struct avtab *h, struct avtab_node **dst, const struct avtab_key *key, const struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } newnode->next = *dst; *dst = newnode; h->nel++; return newnode; } static int avtab_node_cmp(const struct avtab_key *key1, const struct avtab_key *key2) { u16 specified = key1->specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD); if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class == key2->target_class && (specified & key2->specified)) return 0; if (key1->source_type < key2->source_type) return -1; if (key1->source_type == key2->source_type && key1->target_type < key2->target_type) return -1; if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class < key2->target_class) return -1; return 1; } static int avtab_insert(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur, *newnode; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); /* extended perms may not be unique */ if (cmp == 0 && !(key->specified & AVTAB_XPERMS)) return -EEXIST; if (cmp <= 0) break; } newnode = avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node *avtab_insert_nonunique(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp <= 0) break; } return avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node *avtab_search_node(struct avtab *h, const struct avtab_key *key) { u32 hvalue; struct avtab_node *cur; int cmp; if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } struct avtab_node *avtab_search_node_next(struct avtab_node *node, u16 specified) { struct avtab_key tmp_key; struct avtab_node *cur; int cmp; if (!node) return NULL; tmp_key = node->key; tmp_key.specified = specified; for (cur = node->next; cur; cur = cur->next) { cmp = avtab_node_cmp(&tmp_key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } void avtab_destroy(struct avtab *h) { u32 i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { nslot = nrules > 3 ? rounddown_pow_of_two(nrules / 2) : 2; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } #ifdef CONFIG_SECURITY_SELINUX_DEBUG void avtab_hash_eval(struct avtab *h, const char *tag) { u32 i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += (unsigned long long)chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d, sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } #endif /* CONFIG_SECURITY_SELINUX_DEBUG */ /* clang-format off */ static const uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; /* clang-format on */ int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol, int (*insertf)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), void *p, bool conditional) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, i; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int rc; unsigned int set, vers = pol->policyvers; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32) * items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16) * 4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = hweight16(key.specified & (AVTAB_XPERMS | AVTAB_TYPE | AVTAB_AV)); if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if ((vers < POLICYDB_VERSION_COND_XPERMS) && (key.specified & AVTAB_XPERMS) && conditional) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules in conditional " "policies and one was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32) * ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL, false); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, const struct avtab_node *cur, struct policy_file *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp) { u32 i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = KMEM_CACHE(avtab_node, SLAB_PANIC); avtab_xperms_cachep = KMEM_CACHE(avtab_extended_perms, SLAB_PANIC); } |
| 1724 1722 12 12 1721 1722 1723 127 1723 8 8 1047 1049 1046 244 | 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 | /* 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/sched.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> token_context_lock(RCU, __reentrant_ctx_lock); token_context_lock_instance(RCU, RCU_SCHED); token_context_lock_instance(RCU, RCU_BH); /* * A convenience macro that can be used for RCU-protected globals or struct * members; adds type qualifier __rcu, and also enforces __guarded_by(RCU). */ #define __rcu_guarded __rcu __guarded_by(RCU) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #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() READ_ONCE(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) { if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); preempt_enable(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #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 */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_VIRT_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static __always_inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #define RCU_NOCB_LOCKDEP_WARN(c, s) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * 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); void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif #define rcu_tasks_qs(t, preempt) rcu_tasks_classic_qs((t), (preempt)) # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #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_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) */ 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; #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_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } 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_try_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(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #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) #ifndef 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 // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ 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) // See RCU_LOCKDEP_WARN() for an explanation of the double call to // debug_lockdep_rcu_enabled(). static __always_inline bool lockdep_assert_rcu_helper(bool c, const struct __ctx_lock_RCU *ctx) __assumes_shared_ctx_lock(RCU) __assumes_shared_ctx_lock(ctx) { return debug_lockdep_rcu_enabled() && (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && debug_lockdep_rcu_enabled(); } /** * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() * * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. */ #define lockdep_assert_in_rcu_read_lock() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map), RCU)) /** * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() * * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. * Note that local_bh_disable() and friends do not suffice here, instead an * actual rcu_read_lock_bh() is required. */ #define lockdep_assert_in_rcu_read_lock_bh() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map), RCU_BH)) /** * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() * * Splats if lockdep is enabled and there is no rcu_read_lock_sched() * in effect. Note that preempt_disable() and friends do not suffice here, * instead an actual rcu_read_lock_sched() is required. */ #define lockdep_assert_in_rcu_read_lock_sched() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map), RCU_SCHED)) /** * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader * * Splats if lockdep is enabled and there is no RCU reader of any * type in effect. Note that regions of code protected by things like * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify * as RCU readers. * * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY * kernels that are not also built with PREEMPT_COUNT. But if you have * lockdep enabled, you might as well also enable PREEMPT_COUNT. */ #define lockdep_assert_in_rcu_reader() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ !lock_is_held(&rcu_bh_lock_map) && \ !lock_is_held(&rcu_sched_lock_map) && \ preemptible(), RCU)) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #define lockdep_assert_in_rcu_read_lock() __assume_shared_ctx_lock(RCU) #define lockdep_assert_in_rcu_read_lock_bh() __assume_shared_ctx_lock(RCU_BH) #define lockdep_assert_in_rcu_read_lock_sched() __assume_shared_ctx_lock(RCU_SCHED) #define lockdep_assert_in_rcu_reader() __assume_shared_ctx_lock(RCU) #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__ */ #define __unrcu_pointer(p, local) \ context_unsafe( \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)) \ ) /** * 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) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, 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, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * 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) \ context_unsafe( \ 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)); \ ) /** * 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. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * 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. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __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), __UNIQUE_ID(rcu), \ (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(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (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(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /** * rcu_dereference_all_check() - rcu_dereference_all with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is similar to rcu_dereference_check(), but allows protection * by all forms of vanilla RCU readers, including preemption disabled, * bh-disabled, and interrupt-disabled regions of code. Note that "vanilla * RCU" excludes SRCU and the various Tasks RCU flavors. Please note * that this macro should not be backported to any Linux-kernel version * preceding v5.0 due to changes in synchronize_rcu() semantics prior * to that version. */ #define rcu_dereference_all_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_any_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), __UNIQUE_ID(rcu), 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), __UNIQUE_ID(rcu), (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_dereference_all() - fetch RCU-all-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_all(p) rcu_dereference_all_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. * * Both synchronize_rcu() and call_rcu() also wait for regions of code * with preemption disabled, including regions of code with interrupts or * softirqs disabled. * * 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) __acquires_shared(RCU) { __rcu_read_lock(); __acquire_shared(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 almost all situations, rcu_read_unlock() is immune from deadlock. * This deadlock immunity also extends to the scheduler's runqueue * and priority-inheritance spinlocks, courtesy of the quiescent-state * deferral that is carried out when rcu_read_unlock() is invoked with * interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) __releases_shared(RCU) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release_shared(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * 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) __acquires_shared(RCU) __acquires_shared(RCU_BH) { local_bh_disable(); __acquire_shared(RCU); __acquire_shared(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) __releases_shared(RCU) __releases_shared(RCU_BH) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release_shared(RCU_BH); __release_shared(RCU); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * 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) __acquires_shared(RCU) __acquires_shared(RCU_SCHED) { preempt_disable(); __acquire_shared(RCU); __acquire_shared(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) __acquires_shared(RCU) __acquires_shared(RCU_SCHED) { preempt_disable_notrace(); __acquire_shared(RCU); __acquire_shared(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) __releases_shared(RCU) __releases_shared(RCU_SCHED) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release_shared(RCU_SCHED); __release_shared(RCU); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) __releases_shared(RCU) __releases_shared(RCU_SCHED) { __release_shared(RCU_SCHED); __release_shared(RCU); preempt_enable_notrace(); } static __always_inline void rcu_read_lock_dont_migrate(void) __acquires_shared(RCU) { if (IS_ENABLED(CONFIG_PREEMPT_RCU)) migrate_disable(); rcu_read_lock(); } static inline void rcu_read_unlock_migrate(void) __releases_shared(RCU) { rcu_read_unlock(); if (IS_ENABLED(CONFIG_PREEMPT_RCU)) migrate_enable(); } /** * 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) \ context_unsafe( \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ ) /** * 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) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @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. In order to have a universal * callback function handling different offsets of rcu_head, the callback needs * to determine the starting address of the freed object, which can be a large * kmalloc or vmalloc allocation. To allow simply aligning the pointer down to * page boundary for those, only 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_arg_2(). 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. * * The object to be freed can be allocated either by kmalloc(), * kmalloc_nolock(), or kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * 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 * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by 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 kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) /* * In mm/slab_common.c, no suitable header to include here. */ void kvfree_call_rcu(struct rcu_head *head, void *ptr); /* * The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the * comment of kfree_rcu() for details. */ #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___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; DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) DECLARE_LOCK_GUARD_0_ATTRS(rcu, __acquires_shared(RCU), __releases_shared(RCU)) #endif /* __LINUX_RCUPDATE_H */ |
| 25 683 680 269 493 191 192 9 192 710 710 257 257 710 710 790 312 672 567 781 467 141 141 141 | 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 | /* 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. * * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() provide * acquire and release ordering for cases when the memory occupied by the * object might be reused to store another object. This is important for the * cases where secondary validation is required to detect such reuse, e.g. * SLAB_TYPESAFE_BY_RCU. The secondary validation checks have to happen after * the refcount is taken, hence acquire order is necessary. Similarly, when the * object is initialized, all stores to its attributes should be visible before * the refcount is set, otherwise a stale attribute value might be used by * another task which succeeds in taking a refcount to the new object. */ #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/refcount_types.h> #include <linux/spinlock_types.h> struct mutex; #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_set_release - set a refcount's value with release ordering * @r: the refcount * @n: value to which the refcount will be set * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides release memory ordering which will order previous memory operations * against this store. This ensures all updates to this object are visible * once the refcount is set and stale values from the object previously * occupying this memory are overwritten with new ones. * * This function should be called only after new object is fully initialized. * After this call the object should be considered visible to other tasks even * if it was not yet added into an object collection normally used to discover * it. This is because other tasks might have discovered the object previously * occupying the same memory and after memory reuse they can succeed in taking * refcount to the new object and start using it. */ static inline void refcount_set_release(refcount_t *r, int n) { atomic_set_release(&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 __signed_wrap 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 __must_check __signed_wrap bool __refcount_add_not_zero_limited_acquire(int i, refcount_t *r, int *oldp, int limit) { int old = refcount_read(r); do { if (!old) break; if (i > limit - old) { if (oldp) *oldp = old; return false; } } while (!atomic_try_cmpxchg_acquire(&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; } static inline __must_check bool __refcount_inc_not_zero_limited_acquire(refcount_t *r, int *oldp, int limit) { return __refcount_add_not_zero_limited_acquire(1, r, oldp, limit); } static inline __must_check __signed_wrap bool __refcount_add_not_zero_acquire(int i, refcount_t *r, int *oldp) { return __refcount_add_not_zero_limited_acquire(i, r, oldp, INT_MAX); } /** * refcount_add_not_zero_acquire - add a value to a refcount with acquire ordering unless it is 0 * * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides acquire memory ordering on success, 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_not_zero_acquire() 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_acquire(int i, refcount_t *r) { return __refcount_add_not_zero_acquire(i, r, NULL); } static inline __signed_wrap 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 __must_check bool __refcount_inc_not_zero_acquire(refcount_t *r, int *oldp) { return __refcount_add_not_zero_acquire(1, r, oldp); } /** * refcount_inc_not_zero_acquire - increment a refcount with acquire ordering unless it is 0 * @r: the refcount to increment * * Similar to refcount_inc_not_zero(), but provides acquire memory ordering on * success. * * This function should be used when memory occupied by the object might be * reused to store another object -- consider SLAB_TYPESAFE_BY_RCU. * * Provides acquire memory ordering on success, 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_acquire(refcount_t *r) { return __refcount_inc_not_zero_acquire(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 __signed_wrap 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 > 0 && 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) __cond_acquires(true, lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(true, lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock); #endif /* _LINUX_REFCOUNT_H */ |
| 7 7 7 7 3 53 51 53 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) { struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) { return __pte_alloc_one_kernel_noprof(mm); } #define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__)) #endif /** * pte_free_kernel - free PTE-level kernel page table memory * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { pagetable_dtor_free(virt_to_ptdesc(pte)); } /** * __pte_alloc_one - allocate memory for a PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) { struct ptdesc *ptdesc; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } return ptdesc_page(ptdesc); } #define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor(). * * Return: `struct page` referencing the ptdesc or %NULL on error */ static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm) { return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER); } #define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__)) #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table memory * @mm: the mm_struct of the current context * @pte_page: the `struct page` referencing the ptdesc */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { struct ptdesc *ptdesc = page_ptdesc(pte_page); pagetable_dtor_free(ptdesc); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate memory for a PMD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor(). * * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(mm, ptdesc)) { pagetable_free(ptdesc); return NULL; } if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_pud_ctor(ptdesc); if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate memory for a PUD-level page table * @mm: the mm_struct of the current context * * Allocate memory for a page table using %GFP_PGTABLE_USER for user context * and %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __pud_alloc_one_noprof(mm, addr); } #define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PUD_FREE static inline void pud_free(struct mm_struct *mm, pud_t *pud) { __pud_free(mm, pud); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_p4d_ctor(ptdesc); if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_P4D_ALLOC_ONE static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { return __p4d_alloc_one_noprof(mm, addr); } #define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d) { struct ptdesc *ptdesc = virt_to_ptdesc(p4d); BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_P4D_FREE static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) { if (!mm_p4d_folded(mm)) __p4d_free(mm, p4d); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 4 */ static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; ptdesc = pagetable_alloc_noprof(gfp, order); if (!ptdesc) return NULL; pagetable_pgd_ctor(ptdesc); if (mm == &init_mm) ptdesc_set_kernel(ptdesc); return ptdesc_address(ptdesc); } #define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__)) static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); pagetable_dtor_free(ptdesc); } #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { __pgd_free(mm, pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 263 263 258 5 3 264 264 264 264 264 261 264 264 3 3 3 2 257 225 225 222 1 2 4 1 3 2 1 1 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Authors: Alex Bennée <alex.bennee@linaro.org> * Oliver Upton <oliver.upton@linux.dev> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> static int cpu_has_spe(u64 dfr0) { return cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P); } /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { preempt_disable(); /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, *host_data_ptr(nr_event_counters)); vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug registers if the guest doesn't have ownership of them. */ if (!kvm_guest_owns_debug_regs(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; if (vcpu_has_nv(vcpu)) kvm_nested_setup_mdcr_el2(vcpu); /* Write MDCR_EL2 directly if we're already at EL2 */ if (has_vhe()) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); preempt_enable(); } void kvm_init_host_debug_data(void) { u64 dfr0 = read_sysreg(id_aa64dfr0_el1); if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)); *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0); *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0); if (cpu_has_spe(dfr0)) host_data_set_flag(HAS_SPE); if (has_vhe()) return; /* Check if we have BRBE implemented and available at the host */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_BRBE_SHIFT)) host_data_set_flag(HAS_BRBE); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) { /* Force disable trace in protected mode in case of no TRBE */ if (is_protected_kvm_enabled()) host_data_set_flag(EL1_TRACING_CONFIGURED); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) host_data_set_flag(HAS_TRBE); } } void kvm_debug_init_vhe(void) { /* Clear PMSCR_EL1.E{0,1}SPE which reset to UNKNOWN values. */ if (host_data_test_flag(HAS_SPE)) write_sysreg_el1(0, SYS_PMSCR); } /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. * * - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1. * * - Userspace is using the breakpoint/watchpoint registers to debug the * guest, and MDSCR_EL1.MDE is forced to 1. * * - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0, * masking all debug exceptions affected by the OS Lock. */ static void setup_external_mdscr(struct kvm_vcpu *vcpu) { /* * Use the guest's MDSCR_EL1 as a starting point, since there are * several other features controlled by MDSCR_EL1 that are not relevant * to the host. * * Clear the bits that KVM may use which also satisfies emulation of * the OS Lock as MDSCR_EL1.MDE is cleared. */ u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS | MDSCR_EL1_MDE | MDSCR_EL1_KDE); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) mdscr |= MDSCR_EL1_SS; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE; vcpu->arch.external_mdscr_el1 = mdscr; } void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) { u64 mdscr; /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); if (has_vhe()) *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); /* * Determine which of the possible debug states we're in: * * - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's * breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do * software step or emulate the effects of the OS Lock being enabled. * * - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and * the breakpoint/watchpoint registers need to be loaded eagerly. * * - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint * context needs to be loaded on the CPU. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED; setup_external_mdscr(vcpu); /* * Steal the guest's single-step state machine if userspace wants * single-step the guest. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS) vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING); else vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING); if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE)) vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; else vcpu->arch.debug_owner = VCPU_DEBUG_FREE; } kvm_arm_setup_mdcr_el2(vcpu); } void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { if (has_vhe()) write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; /* * Save the host's software step state and restore the guest's before * potentially returning to userspace. */ if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING); else vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; else *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; } /* * Updates ownership of the debug registers after a trapped guest access to a * breakpoint/watchpoint register. Host ownership of the debug registers is of * strictly higher priority, and it is the responsibility of the VMM to emulate * guest debug exceptions in this configuration. */ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu) { if (kvm_host_owns_debug_regs(vcpu)) return; vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; kvm_arm_setup_mdcr_el2(vcpu); } void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val) { if (val & OSLAR_EL1_OSLK) __vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, |=, OSLSR_EL1_OSLK); else __vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, &=, ~OSLSR_EL1_OSLK); preempt_disable(); kvm_arch_vcpu_put(vcpu); kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } static bool skip_trbe_access(bool skip_condition) { return (WARN_ON_ONCE(preemptible()) || skip_condition || is_protected_kvm_enabled() || !is_kvm_arm_initialised()); } void kvm_enable_trbe(void) { if (!skip_trbe_access(has_vhe())) host_data_set_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_enable_trbe); void kvm_disable_trbe(void) { if (!skip_trbe_access(has_vhe())) host_data_clear_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_disable_trbe); void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) { if (skip_trbe_access(false)) return; if (has_vhe()) { write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12); return; } *host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest; if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest) host_data_set_flag(EL1_TRACING_CONFIGURED); else host_data_clear_flag(EL1_TRACING_CONFIGURED); } EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration); |
| 873 871 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fault-inject.h> #include <linux/debugfs.h> #include <linux/error-injection.h> #include <linux/mm.h> static struct { struct fault_attr attr; bool ignore_gfp_highmem; bool ignore_gfp_reclaim; u32 min_order; } fail_page_alloc = { .attr = FAULT_ATTR_INITIALIZER, .ignore_gfp_reclaim = true, .ignore_gfp_highmem = true, .min_order = 1, }; static int __init setup_fail_page_alloc(char *str) { return setup_fault_attr(&fail_page_alloc.attr, str); } __setup("fail_page_alloc=", setup_fail_page_alloc); bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { int flags = 0; if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) return false; if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) return false; if (fail_page_alloc.ignore_gfp_reclaim && (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) flags |= FAULT_NOWARN; return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_page_alloc_debugfs(void) { umode_t mode = S_IFREG | 0600; struct dentry *dir; dir = fault_create_debugfs_attr("fail_page_alloc", NULL, &fail_page_alloc.attr); debugfs_create_bool("ignore-gfp-wait", mode, dir, &fail_page_alloc.ignore_gfp_reclaim); debugfs_create_bool("ignore-gfp-highmem", mode, dir, &fail_page_alloc.ignore_gfp_highmem); debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order); return 0; } late_initcall(fail_page_alloc_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TCP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on: * linux/net/ipv4/tcp.c * linux/net/ipv4/tcp_input.c * linux/net/ipv4/tcp_output.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file. */ #include <linux/bottom_half.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/jiffies.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/indirect_call_wrapper.h> #include <net/aligned_data.h> #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> #include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/inet_ecn.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/snmp.h> #include <net/dsfield.h> #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> #include <net/hotdata.h> #include <net/busy_poll.h> #include <net/rstreason.h> #include <net/psp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <crypto/md5.h> #include <crypto/utils.h> #include <trace/events/tcp.h> static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; const struct inet_connection_sock_af_ops ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #endif /* Helper returning the inet6 address from a given tcp socket. * It can be used in TCP stack instead of inet6_sk(sk). * This avoids a dereference and allow compiler optimizations. * It is a specialized version of inet6_sk_generic(). */ #define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \ struct tcp6_sock, tcp)->inet6) static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } } static union tcp_seq_and_ts_off tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcpv6_seq_and_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from tcp_v6_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct in6_addr *saddr = NULL, *final_p; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct ipv6_txoptions *opt; struct dst_entry *dst; struct flowi6 *fl6; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; fl6 = &inet_sk(sk)->cork.fl.u.ip6; memset(fl6, 0, sizeof(*fl6)); if (inet6_test_bit(SNDFLOW, sk)) { fl6->flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6->flowlabel); if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) { if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } if (tp->rx_opt.ts_recent_stamp && !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6->flowlabel; /* * TCP over IPv4 */ if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif err = tcp_v4_connect(sk, (struct sockaddr_unsized *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6->flowi6_proto = IPPROTO_TCP; fl6->daddr = sk->sk_v6_daddr; fl6->saddr = saddr ? *saddr : np->saddr; fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_oif = sk->sk_bound_dev_if; fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = usin->sin6_port; fl6->fl6_sport = inet->inet_sport; if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6->fl6_sport) fl6->flowi6_flags = FLOWI_FLAG_ANY_SPORT; fl6->flowi6_uid = sk_uid(sk); opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(fl6, opt, &np->final); security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); dst = ip6_dst_lookup_flow(net, sk, fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } tp->tcp_usec_ts = dst_tcp_usec_ts(dst); tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { saddr = &fl6->saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, false, false); icsk->icsk_ext_hdr_len = psp_sk_overhead(sk); if (opt) icsk->icsk_ext_hdr_len += opt->opt_flen + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; sk_set_txhash(sk); if (likely(!tp->repair)) { union tcp_seq_and_ts_off st; st = secure_tcpv6_seq_and_ts_off(net, np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); if (!tp->write_seq) WRITE_ONCE(tp->write_seq, st.seq); tp->tsoffset = st.ts_off; } if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto late_failure; err = tcp_connect(sk); if (err) goto late_failure; return 0; late_failure: tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; u32 mtu, dmtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); /* Drop requests trying to increase our current mss. * Check done in __ip6_rt_update_pmtu() is too late. */ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) return; dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; dmtu = dst6_mtu(dst); if (inet_csk(sk)->icsk_pmtu_cookie > dmtu) { tcp_sync_mss(sk, dmtu); tcp_simple_retransmit(sk); } } static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct net *net = dev_net_rcu(skb->dev); struct request_sock *fastopen; struct ipv6_pinfo *np; struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; bool fatal; int err; sk = __inet6_lookup_established(net, &hdr->daddr, th->dest, &hdr->saddr, ntohs(th->source), skb->dev->ifindex, inet6_sdif(skb)); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { /* To increase the counter of ignored icmps for TCP-AO */ tcp_ao_ignore_icmp(sk, AF_INET6, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, fatal); return 0; } if (tcp_ao_ignore_icmp(sk, AF_INET6, type, code)) { sock_put(sk); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = tcp_inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { u32 mtu = ntohl(info); /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; if (!ip6_sk_accept_pmtu(sk)) goto out; if (mtu < IPV6_MIN_MTU) goto out; WRITE_ONCE(tp->mtu_info, mtu); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); goto out; } /* Might be for an request_sock */ switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); if (!sock_owned_by_user(sk)) tcp_done_with_error(sk, err); else WRITE_ONCE(sk->sk_err_soft, err); goto out; case TCP_LISTEN: break; default: /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && type == ICMPV6_DEST_UNREACH && code == ICMPV6_NOROUTE) tcp_ld_RTO_revert(sk, seq); } if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM |